Integration of Artificial Intelligence in Triple-Negative Breast Cancer Research: A Bibliometric and Emerging Trends Analysis

Integration of Artificial Intelligence in Triple-Negative Breast Cancer Research: A Bibliometric and Emerging Trends Analysis | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Systematic Review Integration of Artificial Intelligence in Triple-Negative Breast Cancer Research: A Bibliometric and Emerging Trends Analysis Israel Ogwuche Ogra, Jeremiah Zaphnathpaaneah Adaji, Hadiza Joy Umar, and 12 more This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7830165/v1 This work is licensed under a CC BY 4.0 License Status: Posted Version 1 posted You are reading this latest preprint version Abstract Triple-negative breast cancer (TNBC) is defined by the absence of estrogen and progesterone receptors and low expression of the human epidermal growth factor receptor 2 (HER2) protein, which limits the efficacy of available treatment strategies. Recent advances in data science have spurred the application of artificial intelligence (AI) in TNBC research, leading to notable progress. The purpose of this study was to evaluate the current landscape, primary research areas, and emerging trends in AI integration in TNBC research. The analysis aimed to provide a comprehensive overview of research progress and to identify future research directions. Using the Bibliometrix R package and VOSviewer, 461 documents indexed in the Scopus database from 2011 to 2025 were examined. Results indicate rapid expansion in this research field, with an annual growth rate of 38.02%. China and the United States of America emerged as the leading contributors, with the USA leading in global collaboration. The journal Cancers had the highest number of publications and the greatest impact in this field. The University of Texas MD Anderson Cancer Center was the most relevant affiliation, while Zhang J and Wang X emerged as the most productive and impactful authors, respectively. Biomarkers , radiomics , and feature selection were among the top emerging trends in this field. Identified future research directions include clinical translation of AI models, multi-omics for personalized therapy, non-invasive diagnostics, liquid biopsy, and the tumor microenvironment. Increased and sustained collaboration among authors is needed to shape the research landscape on AI integration into TNBC research. Triple-negative breast cancer machine learning bibliometrics emerging trends Scopus Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 Figure 6 Figure 7 Figure 8 Figure 9 1.0 Introduction Triple-negative breast cancer (TNBC) is a subtype of breast cancer that does not overexpress the human epidermal growth factor receptor 2 (HER2) protein and lacks both estrogen (ER) and progesterone (PR) receptors [ 1 , 2 ]. It is the most aggressive breast cancer (BC) subtype both clinically and physiologically and often associated with early relapse, strong invasiveness, and a dismal outcome [ 1 , 3 ]. Despite accounting for approximately 10–15% of BC cases, it contributes substantially to BC-associated mortalities [ 4 – 6 ]. Younger women, especially those of African descent, and individuals with BRCA1 mutations are more likely to have TNBC [ 7 , 8 ]. Its lack of actionable hormone or HER2 targets limits therapeutic options to chemotherapy, often with poor long-term outcomes [ 9 ]. Because TNBC is genomically unstable, highly proliferative, and exhibits heterogeneous tumor biology, it serves as a robust preclinical model for studying breast cancer progression, therapeutic resistance, and novel treatment strategies, making it central to translational and experimental oncology research [ 10 , 11 ]. Recent advances in data science have seen the application of Artificial Intelligence (AI) to TNBC research. AI refers to computer systems capable of performing tasks that typically require human intelligence, such as learning, reasoning, and decision-making [ 12 ]. AI assists in improving diagnosis, treatment planning, medication discovery, and patient monitoring in healthcare by enabling sophisticated data analysis, pattern recognition, and predictive modelling [ 13 ]. Precision medicine has been enhanced through the application of machine learning (ML) and deep learning (DL) algorithms to imaging, genomics, and clinical datasets. In TNBC research, AI enables radiomics, histopathological image analysis, and multi-omics data integration to forecast prognosis, pinpoint therapeutic targets, and stratify patients for specialized therapies [ 14 ]. Additionally, medication repurposing and biomarker identification in TNBC have been facilitated by AI-driven models, which may provide answers to the disease's high heterogeneity and lack of effective targeted therapy. AI continues to influence TNBC research, propelling advancements toward earlier detection and more efficient, individualized treatments as computing power and biomedical datasets continue to expand [ 15 – 17 ]. To study or evaluate the impact of AI on TNBC research, several research approaches or methods are commonly used, one of which is bibliometric analysis. Bibliometric analysis is a systematic study that is carried out on scholarly articles in order to identify patterns, trends, and impact within a certain field. It is a technique that is used for assessing a huge amount of scientific data [ 18 ]. The growing interest in the field of breast cancer, especially triple-negative breast cancer research, has led to an exponential growth of scholarly articles; therefore, a bibliometric analysis has emerged as a pertinent method to map the intellectual landscape, identify key research trends, key players, collaboration networks, publication patterns, and also highlight influential studies that can guide future research. Understanding these dynamics is essential for framing the on-going discourse on the integration of artificial intelligence in TNBC research. Software tools such as VOSviewer, the R package Bibliometrix, and CiteSpace are among the most commonly used for conducting bibliometric analyses. These tools are widely recognized in bibliometric research across diverse scientific disciplines, including the biomedical sciences, for their ability to map research landscapes, identify collaboration networks, and detect emerging trends with high precision [ 19 – 21 ]. When applied to AI-driven TNBC literature mapping, they enable the systematic visualization of research hotspots, thematic evolution, and knowledge gaps, thereby guiding future investigations and fostering targeted innovation in this challenging breast cancer subtype. Bibliometrics has been extensively employed to objectively and quantitatively assess research trends and emerging topics on the integration of artificial intelligence in breast cancer research. Some of such studies include “Evolution of research trends in artificial intelligence for breast cancer diagnosis and prognosis over the past two decades: A bibliometric analysis” [ 22 ]; “The top 100 most-cited articles on artificial intelligence in breast radiology: A bibliometric analysis” [ 23 ]; “Artificial intelligence-assisted multimodal imaging for the clinical applications of breast cancer: A bibliometric analysis” [ 24 ]; and “Decoding breast cancer imaging trends: the role of AI and radiomics through bibliometric insights” [ 25 ]. A few bibliometric analyses have been conducted with mention of AI as a future research direction in TNBC research. Li et al. [ 26 ] and Wang et al. [ 27 ] both highlighted AI/ML as an important current/future theme in TNBC research. Although prior bibliometric studies [ 28 ] have mapped TNBC research using machine-learning approaches, no bibliometric analysis has yet been dedicated specifically to AI integration within TNBC research, necessitating this study and making it the first bibliometric analysis focusing on AI integration in TNBC research. The Scopus database has a broad coverage of peer-reviewed scientific literature, strong citation-tracking features, and compatibility with popular bibliometric software. Therefore, the bibliometric dataset for this study was obtained from the Scopus database, guaranteeing a thorough and reproducible analysis pipeline [ 29 ]. The aim of this study was to use bibliometric scientific mapping and visualization methods to perform a bibliometric and emerging trends analysis on the integration of artificial intelligence in TNBC research. An analysis of the distribution of publications retrieved from the Scopus database was carried out, topics were categorized, and research progress was tracked over time. Additionally, the country contributions and author collaboration were examined with particular emphasis on research topics and emerging research areas. Finally, important future research directions in this area were also highlighted. 2.0 Methods 2.1 Bibliometric method and data collection The Scopus database was used to retrieve the data for this study on July 19, 2025 ( Fig. 1 ). This database is widely recognized for its comprehensive coverage and reliable content. It houses numerous publications from reputable publishers. The following search string was used: (“Triple Negative Breast cancer*” OR “Triple-Negative Breast Cancer*” OR “Triple Negative Breast Neoplasm*” OR “Triple-Negative Breast Neoplasm*” OR “ER-Negative PR-Negative HER2-Negative Breast Neoplasm*” OR “ER-Negative PR-Negative HER2-Negative Breast Cancer*”) AND ("artificial intelligence*" OR "deep learn*" OR "machine learn*" OR "neural network*" OR "compu* intelligen*" OR "robot*"). The study considered publications from 2011 to 2025. This timeframe was chosen to reflect the earliest period of AI integration in TNBC research and provide clear insight into the research patterns and trends. The search included titles, abstracts, and keywords, yielding an initial pool of 813 documents in all languages. Manual screening of titles, abstracts, and main text was performed to exclude publications outside the subject area. After excluding 352 articles, only final published articles were retained, resulting in a total of 461 documents for further analysis. 2.2 Data Analysis The extracted dataset, consisting of 461 documents from the Scopus search, was saved in CSV format for further analysis. Bibliometric tools, specifically VOSviewer and the "Bibliometrix" R package [ 19 , 21 ], along with Microsoft Excel, were used for analysis and result visualization. VOSviewer software was employed to generate visual maps based on keywords, authors, and their interrelationships. Additionally, Bibliometrix facilitated the illustration of scientific trends and productivity, identifying the most productive authors and influential articles published on the subject. This package encompasses powerful and comprehensive capabilities for bibliometric analysis, comprising analyses of authors, institutions, countries, and regions, as well as journal clustering and temporal trends [ 19 ]. Keywords are essential components of scholarly works, playing a crucial role in information retrieval and research endeavors [ 30 ]. In this study, VOSviewer was used to analyze all keywords and authors’ keywords using the full counting method, with a minimum occurrence threshold of 5. Similarly, it was also used to reveal the co-authorship-countries network, where set parameters included a maximum of 25 countries per publication and a minimum of 5 publications per country. Meanwhile, for thematic map and thematic evolution analysis, parameters were set at word counts of 150 and 250, respectively, with a minimum cluster frequency of 5 per thousand documents [ 21 ]. 3.0 Results 3.1 Descriptive statistics The research output on the integration of artificial intelligence in TNBC research, based on the Scopus database, revealed that 461 documents were published in 248 sources between 2011 and 2025, as shown in Table 1 . These publications were contributed by 2781 authors. The overall number of publications has increased, with an annual rise of 38.02%. Of the 461 documents, articles were the most abundant, totaling 419. Conference papers constituted 41, while one document was classified as a review paper [ 31 ]. However, further investigations revealed that this was actually original research, not a review. It was erroneously classified as a review instead of an article in the Scopus database. Correcting this anomaly brings the total number of articles to 420. The international co-authorship rate stood at 28.2%. Most of the documents were published in English (456), with Chinese (3), Russian (1), and Turkish (1) contributing a minor fraction. Table 1 Summary of the main information on the analyzed data Description Results MAIN INFORMATION ABOUT DATA Timespan 2011:2025 Sources (Journals, Books, etc) 248 Documents 461 Annual Growth Rate % 38.02 Document Average Age 2.5 Average citations per doc 20.29 References 20948 DOCUMENT CONTENTS Keywords Plus (ID) 4136 Author's Keywords (DE) 1088 AUTHORS Authors 2781 Authors of single-authored docs 1 AUTHORS COLLABORATION Single-authored docs 1 Co-Authors per Doc 8.66 International co-authorships % 28.2 DOCUMENT TYPES Article 419 Conference paper 41 Review 1 LANGUAGE English 456 Chinese 3 Russian 1 Turkish 1 3.2 Publication year The publications’ production over time showed an increase in research output on AI integration in TNBC research within the period under review. As shown in the graph ( Fig. 2A ), there was a steady growth in publications, reflecting progressive interest in this field. From 2011 to 2017, the number of annual publications was under 10. After 2017, the number of publications followed an upward trajectory. The peak period of publication was observed in 2024 with 92 documents. It is important to note that only about seven months were covered in 2025 (January to July 19, when the documents were retrieved). Therefore, it is projected that the current year will have the highest number of annual publications so far in this field. There have been fluctuations in the average citations of scientific publications during the period under review. The highest citations were observed in 2017 and 2013, respectively. The number of annual citations has since declined after 2017 ( Fig. 2B ). 3.3 Publication by country Figure 3 A depicts the worldwide distribution of publications on AI integration in TNBC research, with deep blue indicating high publication counts. According to the bar chart, China and the United States lead with 1464 and 1085 publications, respectively. The remaining top ten countries each contributed fewer than 200 publications. The most cited countries on the integration of AI in TNBC research were the United States and China, with a total of 3549 and 3412 citations, respectively, as shown in Fig. 3 B. India, the Netherlands, the United Kingdom, Korea, France, Germany, Canada, and Austria are the other countries amongst the top ten; however, with fewer than 500 citations each. 3.4 Publication by institutions and sources The outcome of affiliation analysis is shown in Fig. 4 A, in which the top 10 most relevant affiliations of scientific publications on the integration of artificial intelligence in TNBC research are represented. From the figure, the most relevant affiliation was the University of Texas MD Anderson Cancer Center, with a total of 115 publications. This is followed by Fudan University (52 documents), Harbin Medical University (51), Southern Medical University (51 documents), and Sun Yat-Sen University Cancer Center (48 documents). Others include Harvard Medical School (39 documents), Mayo Clinic (39 documents), Memorial Sloan Kettering Cancer Center (38 documents), Radboud University Medical Center (38 documents), and Fudan University Shanghai (36 documents). Figure 4 B shows the top 10 most relevant sources out of the 248 sources on AI integration in TNBC research, ranked according to the number of documents. Cancers was the most relevant source in which AI in TNBC research was published, with a total of 24 documents. This is followed by Scientific Reports (16), Frontiers in Oncology (14), and Frontiers in Immunology (12). All other relevant sources within the top 10 each had fewer than 10 documents published. The quintet of Breast Cancer Research and Treatment, Computers in Biology and Medicine , European Radiology , International Journal of Cancer , and Nature Communications each had 7, while Academic Radiology had 6. Figure 4 C depicts the impact of the sources with respect to the h-index. Cancers , with an h-index of 10, showed the highest impact, followed by Frontiers in Oncology (h-index of 8) and Frontiers in Immunology (h-index of 7). European Radiology and Scientific Reports both had an h-index of 6, while Computer in Biology and Medicine , International Journal of Cancer , Journal of Magnetic Resonance , and Nature Communications each had an h-index of 5. Breast Cancer Research and Treatment concludes the top 10 with an h-index of 4. 3.5 Most productive authors Within the reviewed period, 2,781 authors contributed to publications on the integration of AI in TNBC research, with only one producing a single-authored document. The top-producing authors, according to the number of documents, are presented in Fig. 5 A. Both Zhang J and Zhang Y top the list with 20 publications each. They are followed by Wang Y, Zhang X, Wang X, Li X, and Li Y with 19, 18, 17, 16, and 14 documents, respectively. Other relevant authors include Li J, Wang L, and Wang S, with 13 documents each. Figure 5 B presents the productivity of the top 10 productive authors from 2011 to 2025. All authors are currently productively active. Notably, some authors share the same period of productivity- Zhang J and Zhang Y (2021–2025), while Wang Y, Zhang X, Li Y, Li J, and Wang S also share the same period of 2019–2025. Wang X shows a different productivity pattern (2018–2025), and so does Li X (2020–2025). Wang L was the only author represented with a publication start year of 2017. Table 2 presents the impact ranking of relevant authors and outlines parameters such as h-index, g-index, m-index, total citations, number of publications (NP), and publication start year (PY start). Among these authors, Wang X was the most impactful based on h-index and total citations, with an h-index of 10 and TC of 796. In contrast, Zhang Y leads when considering g-index (20), m-index (1.8), and number of publications (20). Notably, Wang X was the only author with a publication start year of 2018. Across all authors, four publication start years were identified, namely 2018, 2019, 2020, and 2021. Table 2 The top 10 most impactful authors on AI integration in TNBC research Author h_index g_index m_index TC NP PY_start WANG X 10 17 1.25 796 17 2018 ZHANG Y 9 20 1.8 764 20 2021 LIN Y 8 10 1.333 447 10 2020 WANG Y 8 16 1.143 268 19 2019 LI H 7 11 1.4 235 11 2021 LI J 7 13 1 222 13 2019 LI X 7 16 1.167 278 16 2020 LIU Y 7 11 1 145 11 2019 ZHANG X 7 17 1 301 18 2019 HUANG Y 6 10 1 355 10 2020 3.6 Top most cited documents Table 3 presents the top ten most cited documents on the integration of AI in TNBC research. Keren et al. [ 32 ] leads as the most cited document, with 714 citations. This is followed by Braman et al. [ 33 ], He et al. [ 34 ], and Zou et al. [ 35 ] with 516, 399, and 277 citations, respectively. Others include Meyer et al. [ 36 ], Saha [ 37 ], Xiao et al. [ 38 ], Mostavi et al. [ 39 ], Wu and Hicks [ 40 ], and Cain et al. [ 41 ] with document citations of 232, 218, 213, 179, 174, and 148, respectively. Table 3 The top ten most cited documents on the integration of AI in TNBC research S/No Author Title Journal Total Citations 1 Keren et al. [ 32 ] A structured tumor-immune microenvironment in triple negative breast cancer revealed by multiplexed ion beam imaging Cell 714 2 Braman et al. [ 33 ] Intratumoral and peritumoral radiomics for the pretreatment prediction of pathological complete response to neoadjuvant chemotherapy based on breast DCE-MRI Breast cancer research 516 3 He et al. [ 34 ] Classification of triple-negative breast cancers based on Immunogenomic profiling Journal of Experimental & Clinical Cancer Research 399 4 Zou et al. [ 35 ] Leveraging diverse cell-death patterns to predict the prognosis and drug sensitivity of triple-negative breast cancer patients after surgery International journal of surgery 277 5 Meyer et al. [ 36 ] The receptor AXL diversifies EGFR signaling and limits the response to EGFR-targeted inhibitors in triple-negative breast cancer cells Science signalling 232 6 Saha [ 37 ] A machine learning approach to radiogenomics of breast cancer: A study of 922 subjects and 529 dce-mri features British journal of cancer 218 7 Xiao et al. [ 38 ] Comprehensive metabolomics expands precision medicine for triple-negative breast cancer Cell research 213 8 Mostavi et al. [ 39 ] Convolutional neural network models for cancer type prediction based on gene expression BMC medical genomics 179 9 Wu and Hicks [ 40 ] Breast cancer type classification using machine learning Journal of personalized medicine 174 10 Cain et al. [ 41 ] Multivariate machine learning models for prediction of pathologic response to neoadjuvant therapy in breast cancer using MRI features: a study using an independent validation set Breast cancer research and treatment 148 TC -Total citations, NP- Number of publications, PY_start- Publication year start 3.7 Keywords co-occurrence network analysis Following the analysis with VOSviewer, the network map of all keyword clusters is shown in Fig. 6 A. Different clusters could be identified from the network map, with different keywords shown according to the occurrence. Cluster 1, depicted in red, is made up of highly occurring keywords such as triple negative breast cancer , machine learning , genetics , and gene expression . Breast cancer, breast tumor, cohort analysis, human tissue, major clinical study , and pathology were among the most occurring keywords in cluster 2 (green). The third cluster, represented in blue, is composed of diverse keywords with deep learning, diseases, algorithm, and artificial intelligence as the keywords with high frequency. Tumor associated leukocyte, tumor recurrence, tumor-infiltrating lymphocytes , and the Kaplan-Meier method make up the topmost occurring concepts in cluster 4, depicted in yellow. The fifth cluster (purple) has the following keywords in high occurrence, namely, scoring system, machine learning algorithm, classification , and least absolute shrinkage and selection operator. Cluster 6 (turquoise) is made up of only two keywords: early detection of cancer and early cancer diagnosis. Figure 6 B presents the authors’ keyword co-occurrence network. Different clusters could be identified from the network map, with different keywords shown according to the occurrence. Cluster 1, depicted in red, is made up of highly occurring keywords such as triple negative breast cancer , machine learning , biomarker , and classification . Breast cancer, artificial intelligence, neoadjuvant chemotherapy , and pathological complete response were among the most occurring keywords in cluster 2 (green). The third cluster, represented in blue, is composed of several keywords, with deep learning, prognosis, triple-negative breast cancer, and nuclei segmentation as the keywords with high frequency. Cancer, digital pathology, histopathology , and convoluted neural networks make up the topmost occurring keywords in cluster 4, depicted in yellow. The fifth cluster (purple) has the following keywords in high occurrence, namely, breast neoplasms, magnetic resonance imaging, radiomics , and molecular subtypes. Cluster 6 (turquoise) is made up of the following keywords: chemotherapy, immunotherapy, tumor micro-environment , and triple negative breast cancer. Finally, cluster 7 (orange) is made up of only 2 keywords- molecular subtype and ultrasound . 3.8 Thematic evolution and trend topics The thematic map of authors’ keywords is presented in Fig. 7 A, which is divided into four quadrants. The bottom left quadrant consists of emerging or declining themes, such as graph neural network(s). Along the border between the bottom left (emerging or declining) and the top left (niche) quadrants, concepts like tnbc subtypes , artificial intelligence (ai) , and deep neural network are positioned, indicating their transition from one theme type to another. The basic themes in the bottom right quadrant include groupings such as machine learning, triple-negative breast cancer, artificial intelligence ; breast cancer, deep learning, radiomics ; and nuclei segmentation, histopathology images, convolutional neural networks . At the top left, the niche themes comprise concepts like class, classifier evaluation , diseases; breast cancer subtypes , differential gene expression, ensemble learning; and cell segmentation, feature extraction in respective clusters. The top right quadrant contains the motor themes, with examples such as attention mechanism, multi-omics data, graph convolutional network ; and immune checkpoint inhibitor, machine learning algorithm, cancer-associated fibroblasts in unique clusters. Figure 7 B provides the thematic evolution based on the author’s keywords on the integration of AI in TNBC research. Between 2011 and 2017, breast cancer and machine learning were the dominant themes. From the period of 2018 to 2022, bioinformatics , biomarkers, breast cancer, computer-aided diagnosis, nuclei segmentation, precision medicine, segmentation, single-cell rna-seq, tnbc, triple negative breast cancer, tumor microenvironment became the most dominant themes. However, from 2023 up to the current period, the most dominant authors’ keywords were breast cancer, computer-aided diagnosis, digital pathology, feature selection, histopathology, immune infiltration, machine learning, subtype, racial disparity, support vector machine, survival analysis and triple-negative breast cancer (tnbc) . Figure 8 shows the trends in topic and research concepts based on the integration of AI in TNBC research. The size of the dot represented its frequency, while the horizontal line represented its period in years. The topics span different periods, with notable trends for each year indicated by the dot. From the figure, the trending topics between 2020 and 2022 included bioinformatics, molecular subtypes, biomarker, digital pathology , and triple negative breast cancer . However, from 2023 up to 2024, the trending topics are triple-negative breast cancer, machine learning, breast cancer, tnbc, magnetic resonance imaging , and artificial intelligence. 3.9 Countries and authors’ collaboration network From Table 4 , China, the United States, and India were the top 3 countries in terms of relevance estimated by the corresponding author’s country. Looking more closely at publication types, China, the USA, India, Korea, and Canada had more single-country publications (SCP) than multiple-country publications (MCP). In contrast, the UK, Georgia, Germany, France, and the Netherlands had more multiple-country publications (MCP) than single-country publications (SCP). Furthermore, while India, China, and Korea dominated in terms of a higher percentage of SCP in relation to total publications, the Netherlands led in having a higher MCP relative to total publications. Table 4 Most relevant countries of publications based on the corresponding author Country Articles SCP MCP % SCP to total publications % MCP to total publications CHINA 173 151 22 87.3 12.7 USA 91 59 32 64.8 35.2 INDIA 29 28 1 96.6 3.4 KOREA 21 18 3 85.7 14.3 UNITED KINGDOM 11 4 7 36.4 63.6 GEORGIA 10 4 6 40 60 GERMANY 10 3 7 30 70 FRANCE 9 4 5 44.4 55.6 NETHERLANDS 7 1 6 14.3 85.7 CANADA 6 4 2 66.7 33.3 Six (6) clusters can be seen in the network of co-authorship country analysis presented in Fig. 9 A. The largest cluster, which is cluster 1 depicted in red, is made up of countries like Australia, Belgium, India, the Netherlands, Poland, Saudi Arabia, and Sweden. Austria, France, Italy, Spain, the United Kingdom, and the United States make up cluster 2 depicted in green. While cluster 3 (blue) is made up of China and Taiwan, cluster 4 (yellow) comprises Iran and Canada. Both cluster 5 (purple) and cluster 6 (turquoise) are made up of two countries each-Norway and Brazil, and Germany and South Korea, respectively. Figure 9 B presents the authors’ collaboration network. Three (3) clusters can be seen in the figure and are loosely connected together. Aneja R and Bhattarai S are present in cluster 1 (red). Cluster 2 (green) is the largest cluster and comprises authors such as Wang Y, Wang X, Zhang X, Zhang J, and Zhang Y. Lastly, cluster 3 (blue) has Yang W, Sun J, Chen H, Xu Z, and Valero V. 4.0 Discussion 4.1 Research growth An in-depth bibliometric analysis was conducted on the research output on the integration of artificial intelligence in TNBC research from 2011 to 2025 using scientific literature records from the Scopus database. Particular emphasis was placed on the field's worldwide research trends, which included research hotspots, key contributors, conceptual development, and anticipated future research directions. The findings showed that knowledge in this area has advanced quickly during the period under review. The annual growth rate (38.02%) indicates that the body of knowledge is growing steadily with novel concepts, investigations, and deductions introduced annually. This further suggests that the discipline is dynamic. Similarly, the international co-authorship percentage (28.20%) highlights considerable global networking in generating scientific information on the integration of artificial intelligence in TNBC research. This indicates that international collaboration is responsible for approximately one-third of publications on the integration of AI in TNBC research, thereby increasing the diversity of viewpoints and expertise invested in its research. In line with best practices in bibliometrics, this study considered only original research articles and conference papers, given their importance in AI-related fields, as these represent validated, novel scientific contributions, while excluding reviews, editorials, and letters that primarily synthesize or comment on existing knowledge [ 18 , 19 , 42 ]. Results indicate that there has been growth in research interests on the integration of AI in TNBC research, leading to an annual increase in publications. This growth in research is similar to that reported by [ 43 ], who observed a general exponential rise in AI-related publications across scientific disciplines, and by [ 44 ], who highlighted an increasing trend of AI applications within breast cancer research. Likewise, recent bibliometric analyses in oncology, [ 45 , 46 ] also documented steady growth in the adoption of AI-driven methodologies, indicating that the surge observed in TNBC aligns with broader global trends in AI integration within medical research. The yearly average citations of scientific publications on AI integration in TNBC research ( Fig. 2B ) exhibited notable fluctuations, with peaks observed in 2013 and 2017. These increases are attributable to influential studies that shaped subsequent research directions and citation patterns. Since 2017, average annual citations have declined, likely due to citation dilution resulting from a rapid increase in publication volume, which disperses citations across more articles. Additional contributing factors include a time-lag effect, as recent publications have not yet accumulated substantial citations, and a shift in focus toward emerging subfields such as explainable AI, multi-omics integration, and deep learning within oncology. This trend is consistent with bibliometric analyses in related disciplines, which indicate that publication surges often correspond with temporary decreases in average annual citations [ 43 , 44 , 46 , 47 ]. 4.2 Influential countries, affiliations and sources The USA and China lead AI-integrated TNBC research due to large investments and structural advantages. The USA supports cancer research with significant funding for precision oncology and therapeutics, along with access to open resources such as TCGA and TCIA, which enable AI modeling. China takes advantage of its strong policy support, advanced digital infrastructures, and translational experience, resulting in high publication output [ 48 – 50 ]. A bibliometric study on the tumor microenvironment in TNBC confirmed that the USA and China are the top contributors in terms of publication volume and citation impact [ 51 ]. Similarly, a bibliometric analysis of deep learning in cancer research found that China leads in publication volume, while the USA produces higher-impact, widely cited work due to global collaborations and research visibility [ 46 ]. The aggressive nature and lack of targeted therapies for TNBC make it a global research focus, giving both countries strong motivation to lead AI innovation in this area [ 52 ]. Affiliations are useful in bibliometric analyses for evaluating research trends and institutional output in a given body of knowledge. Authors usually conduct their research from institutions or organizations to which they are affiliated. The top 10 most relevant affiliations for AI in TNBC research are equally concentrated in the USA (50%) and China (50%) (Fig. 4 A). These are the top two nations with high research output and citations on this topic (Fig. 3 A and 3 B). Institutions from the USA include the University of Texas MD Anderson Cancer Center, Harvard Medical School, Mayo Clinic, Memorial Sloan Kettering Cancer Center, and Radboud University Medical Center. Together, they contributed 269 documents, representing 53.06% of the top ten affiliations' total publications. Similarly, Chinese institutions such as Fudan University, Harbin Medical University, Southern Medical University, Sun Yat-sen University Cancer Center, and Fudan University Shanghai contributed 238 documents, making up 46.94% of the total. This result highlights the geographic dominance of scientific leadership in this field. Both the USA and China have prioritized and invested heavily in artificial intelligence and oncology research. These investments have produced robust institutional frameworks, excellent access to comprehensive datasets, and funding structures that encourage interdisciplinary collaboration. Scientific information is usually published in journals and conference proceedings. These serve as primary channels of scholarly communication. From Fig. 4 B, Cancers was the most relevant source for publishing research on the integration of AI in TNBC. This suggests that it is a prominent venue in this emerging field. It was followed by Scientific Reports , Frontiers in Oncology , and Frontiers in Immunology , indicating that much of this research appears in open-access sources. This maximizes research visibility and global reach. The presence of Frontiers in Immunology highlights the significance of artificial intelligence in immuno-oncology. This focus is particularly relevant for TNBC, which lacks hormone receptors and depends on immune-based biomarkers and predictive modeling for diagnosis and treatment. Other journals, such as Breast Cancer Research and Treatment , Computers in Biology and Medicine, European Radiology, and Academic Radiology , show that research covers cancer-specific, imaging, and computational disciplines. This underlines the field's multidisciplinary scope. The inclusion of Nature Communications and the International Journal of Molecular Sciences shows that AI in TNBC is gaining attention in high-impact, general science, and applied informatics journals further reflecting its growing scientific significance. Ninety per cent (90%) of the most relevant sources were also present as journals with the highest impact according to their h-impact measure, re-enforcing the fact that these journals not only publish high volumes but also carry significant scientific influence in this field. Academic Radiology did not make the list of the top 10 most impactful sources in which the integration of AI in TNBC research was published; instead, the Journal of Magnetic Resonance Imaging (h-impact 5) appeared in its place. Cancers was also the most impactful journal in which AI in TNBC research was published, with an h-impact of 10. The inclusion of additional open-access journals, such as Scientific Reports, Frontiers in Oncology, and Frontiers in Immunology , supports the trend illustrated in Fig. 4 B toward broader dissemination and accessibility of artificial intelligence (AI) integration in triple-negative breast cancer research. This trend is significant for the multidisciplinary nature of this field, which requires rapid information exchange and collaboration across disciplines. Other journals with comparatively high impact factors include European Radiology, Computers in Biology and Medicine, International Journal of Cancer Research, Nature Communications , and Breast Cancer Research and Treatment . The prominence of specialized open-access oncology journals indicates that these publications are currently influencing the development of AI in TNBC research more substantially than traditional high-impact generalist journals. 4.3 Influential authors Figure 5 A provides a graphical summary of the most productive authors based on the number of published documents. Zhang J and Zhang Y each stood out as the leading authors, followed by Wang Y, Zhang X, Wang X, and Li X. When analyzing Fig. 5 A, it becomes evident that the leading authors in artificial intelligence (AI) integration in triple-negative breast cancer (TNBC) research are primarily affiliated with institutions in China. This concentration likely results from significant national investment in AI and oncology, as well as from access to extensive patient datasets and established collaborative networks among major Chinese cancer research centers such as Fudan University, Sun Yat-Sen University Cancer Center, Shanghai Jiao Tong University, and the Chinese Academy of Sciences. These findings indicate that the most productive authors are integrated within institutional clusters and collaborative research networks in China [ 17 , 26 , 28 ]. Analysis of the top authors' productivity period (Fig. 5 B) indicates that all top 10 authors remain active in AI integration in TNBC research. Wang L has the longest publication span, beginning in 2017, followed by Wang X, who began publishing in 2018. A cluster of authors, including Wang S, Li J, Li Y, Zhang X, and Wang Y, commenced publishing in 2019. Zhang Y and Zhang J began their contributions in 2021, while Li X started in 2020. The publication period for these leading authors (2017–2025) aligns with the observed growth in AI integration within TNBC research ( Fig. 2A ), which suggests that these individuals are among the foundational contributors to this field. Several indicators are commonly used in bibliometrics to measure researchers’ productivity and impact over time. The h-index, proposed by Hirsch [ 53 ], measures both the productivity and citation impact of a researcher. It balances quantity and quality by ignoring both lowly cited papers and the disproportionately high influence of a single publication. The g-index, introduced by Egghe [ 54 ], improves upon the h-index by giving more weight to highly cited publications. Thus, it recognizes the impact of exceptionally influential papers that the h-index might overlook. The m-index (or m-quotient) is derived by dividing the h-index by the number of years since the researcher’s first publication. It normalizes the h-index for academic age, allowing fairer comparisons between early-career and senior researchers [ 53 ]. Table 2 highlights the top 10 most impactful authors in the integration of AI in TNBC research based on h-index. Among them, Wang X emerged topmost with the highest h-index (10), total citations (TC = 796), and an early research start year (2018), suggesting consistent productivity and citation visibility over time. Interestingly, despite starting more recently (2021), Zhang Y demonstrates the strongest research momentum, with the highest g-index (20) and m-index (1.8). This indicates rapid accumulation of both publications (NP = 20) and citations (TC = 764) within a short span, reflecting high-impact and possibly trend-setting work. Strong relative productivity adjusted for career length is also demonstrated by other authors, such as Lin Y (m-index = 1.333) and Li H (m-index = 1.4), indicating that their contributions are highly impactful given how recently they entered this field. Authors such as Li J and Liu Y, on the other hand, have lower m-indices (1.0) and moderate citation counts (TC = 222 and 145, respectively), indicating a stable but slower impact compared to their colleagues. About 60% of the top 10 most impactful authors are also among the most productive authors, implying that they not only have high-volume publications, but these publications are equally impactful within this field. This result also corroborates the fact that the most impactful authors on the integration of AI in TNBC research are affiliated with institutions in China, aligning with broader trends where China and the USA lead in AI-driven oncology research output. The data also points to a relatively recent spike in research activity, with the majority of authors starting their contributions after 2018, highlighting the fact that AI applications in TNBC remain an emerging but rapidly expanding field. 4.4 Influential documents The most cited studies that have influenced the use of artificial intelligence in triple-negative breast cancer research are shown in Table 3 . The main study topics and approaches that have garnered a lot of scholarly interest are highlighted in these citations. Published in Cell , [ 32 ] is the most cited publication. The tumor-immune microenvironment in TNBC was mapped using multiplexed ion beam imaging in this study, providing important information about immunological heterogeneity that supports existing AI-based predictive modeling. This shows how AI-driven spatial biology approaches have provided foundational knowledge for TNBC research. The second most influential study [ 33 ], was the first to use DCE-MRI data to predict therapy response using radiomics. The early focus on radiomics and imaging-based AI applications in TNBC prognosis and therapy response was also highlighted by [ 41 ], who validated multivariate machine learning MRI models. In terms of genomics, [ 34 ] used immunogenomic profiling to classify TNBC subtypes, while [ 39 , 40 ] showed the value of machine learning and convolutional neural networks in gene expression-based TNBC classification. The shift in AI applications from imaging to multi-omics and molecular data integration is highlighted by these contributions. Recent research shows that AI is becoming increasingly relevant in precision medicine, where metabolomics, cell-death signatures, and drug sensitivity prediction are being utilized for personalized therapy. Examples of these studies include [ 35 , 38 ]. Remarkably, despite being earlier, [ 36 ] was nonetheless highly referenced for detecting AXL-mediated EGFR resistance, which has influenced subsequent AI research on signaling circuit modelling. Finally, [ 37 ] made a substantial contribution as well by integrating machine learning and radiogenomics in a sizable dataset on breast cancer. A comparison of Tables 2 and 3 reveals that the most productive and impactful authors do not fully correspond with those responsible for the most cited publications. Table 2 identifies Wang X, Zhang Y, Lin Y, and Li H as the leading contributors, based on the h-index. However, these authors do not appear among the top ten most cited papers. Conversely, highly cited works [ 32 – 34 ] dominate Table 3 but are not linked to the most recurrently productive authors in Table 2 . This pattern reveals a divergence between researchers who drive cumulative output in the integration of artificial intelligence in triple-negative breast cancer research and those who produce pioneering studies with significant citation impact. Table 2 illustrates the sustained productivity and influence of specific authors, whereas Table 3 highlights pivotal publications that have shifted research directions or introduced new methodologies. These complementary perspectives provide a comprehensive understanding of the development of AI in TNBC research, shaped by both consistent author productivity and milestone publications that serve as intellectual foundations. 4.5 Keyword co-occurrence network The co-occurrence network of all keywords, shown in Fig. 6 A, outlines the thematic structure of research integrating artificial intelligence in TNBC. Node size reflects keyword frequency, and links represent co-occurrence relationships. The visualization highlights the multidisciplinary convergence of AI with molecular biology, clinical oncology, and imaging, underscoring its growing role in precision medicine for TNBC. Distinct clusters represent unique methodological and clinical research directions. Cluster 1 (red) focuses on biological and genomic aspects, including triple negative breast cancer , machine learning , genetics , and gene expression , indicating a strong emphasis on omics-driven approaches. Cluster 2 (green) addresses clinical and translational topics, such as breast cancer , breast tumors , pathology , and cohort analysis , highlighting the application of artificial intelligence in patient stratification and diagnosis. Cluster 3 (blue) centers on computational themes, including deep learning , algorithm , and artificial intelligence , underscoring the importance of advanced algorithms in oncology research. Cluster 4 (yellow) is associated with prognostic markers, such as tumor-infiltrating lymphocytes , tumor recurrence , and Kaplan-Meier analysis , linking artificial intelligence to survival outcome predictions. Cluster 5 (purple) highlights statistical and algorithmic methods, including classification and least absolute shrinkage and selection operator (LASSO) , while cluster 6 (turquoise) emphasizes early detection. These findings align with recent bibliometric reviews, which indicate that all-keyword mapping demonstrates a balanced interplay between artificial intelligence methodologies and clinical applications in oncology, and that TNBC research is emerging as a critical area [ 51 , 52 , 55 ]. On the other hand, the authors’ keywords co-occurrence network in Fig. 6 B provides further insight into the intellectual structure of AI-driven TNBC research, capturing the self-defined priorities of contributing researchers. Cluster 1 (red) emphasizes methodological advances, including triple-negative breast cancer , machine learning , biomarker , and classification . These terms reflect the integration of AI into biomarker discovery and predictive modeling. Cluster 2 (green) addresses translational and therapeutic aspects, featuring artificial intelligence , neoadjuvant chemotherapy , and pathological complete response . This cluster demonstrates the expanding role of AI in treatment monitoring. Cluster 3 (blue) focuses on imaging and computational approaches, with deep learning , prognosis , and nuclei segmentation indicating an emphasis on automated histopathological analysis. Cluster 4 (yellow) consolidates concepts related to cancer diagnosis and digital pathology, signifying a transition toward AI-enhanced pathological workflows. Cluster 5 (purple) encompasses radiomics and imaging modalities, while cluster 6 (turquoise) connects therapeutic themes such as chemotherapy , immunotherapy , and tumor microenvironment , suggesting interaction between computational tools and immuno-oncology. Cluster 7 (orange), though the smallest, identifies emerging directions, including ultrasound and molecular subtyping . The authors’ keywords network indicates that researchers’ selected keywords represent both established research areas and emerging frontiers. This complements the broader thematic scope presented by all keywords in Fig. 6 A. A comparative analysis of the co-occurrence networks in Fig.s 6A and 6B reveals both convergence and divergence in thematic focus when comparing all keywords with authors’ keywords. The all-keywords map (Fig. 6 A) displays a broader range of indexed terms. Its clusters include clinical and pathological aspects such as breast cancer , pathology , and cohort analysis . Computational methodologies, including deep learning , algorithm , and artificial intelligence , are also prominent. In contrast, the authors’ keywords map (Fig. 6 B) reflects researchers’ intentional framing of their studies. This map emphasizes translational and methodological priorities such as biomarker , classification , neoadjuvant chemotherapy , prognosis , and digital pathology . Both maps identify triple-negative breast cancer and artificial intelligence or machine learning techniques as central themes. However, the authors’ network assigns greater importance to clinical applications such as pathological complete response , immunotherapy , and tumor microenvironment , as well as to precision tools such as radiomics and nuclei segmentation . The all-keywords network, by comparison, encompasses a wider array of general oncology and methodological terms. This comparison suggests that database-driven indexing using all keywords provides a more comprehensive but less focused perspective. In contrast, author-specified keywords highlight the strategic priorities and emerging research frontiers identified by the scientific community [ 18 , 19 , 21 ]. 4.6 Thematic evolution and trending topics The thematic map (Fig. 7 A) illustrates the progression of artificial intelligence integration in triple-negative breast cancer research by organizing authors’ keywords into four quadrants according to relevance and development. Basic themes, including m achine learning, deep learning, radiomics, artificial intelligence , and triple-negative breast cancer , underscore the foundational role of these concepts in the field. These keywords highlight the increasing application of computational models for image analysis, biomarker identification, and predictive modeling. Their classification as basic themes suggest ongoing refinement and methodological advancement. In contrast, motor themes such as attention mechanisms, multi-omics data integration, graph convolutional networks , and immune checkpoint inhibitors indicate a shift toward more complex and biologically informed AI methodologies. This development demonstrates a growing emphasis on advanced algorithms to address TNBC’s molecular heterogeneity and its interactions with the tumor microenvironment. Niche themes, such as breast cancer subtype classification, differential gene expression , and ensemble learning , provide specialized but less central contributions. Emerging or declining themes (low centrality and low density), including graph neural network(s) may represent either early-stage innovations or concepts encountering barriers to broader adoption. Themes such as deep neural network, artificial intelligence (ai) , and tnbc subtype are currently between the niche and emerging or declining themes. They are specialized yet not fully part of mainstream TNBC research. Their low centrality indicates limited engagement with the wider oncology community, while rising internal density suggests active work by specialized groups. This stage signifies that clinical success and broader adoption could render these themes central to the field. If they are not well-integrated, they may remain peripheral or decline. Strategic investment and collaboration across domains are needed to reach their potential. In general, the thematic mapping reveals a transition from foundational AI applications in TNBC to more sophisticated, integrative strategies that advance precision oncology. The thematic evolution of authors’ keywords in the integration of AI in TNBC research from 2011 to 2025, as shown in Fig. 7 B, demonstrates a progressive shift in research priorities. Between 2011 and 2017, the research mainly focused on broad topics such as breast cancer and machine learning . From 2018 to 2022, research broadened to strategies for understanding tumor biology and image analysis. This is evidenced by keywords like single-cell rna-seq , tumor microenvironment , and nuclei segmentation . During this period, research on TNBC also became increasingly specialized. Between 2023 and 2025, the focus is projected to move toward radiomics, diagnosis, and prognosis prediction. The appearance of keywords such as computer-aided diagnosis , digital pathology , feature selection , and survival analysis suggests a shift toward improving diagnostic tools and methods. This aims for better patient outcomes. Throughout the period, breast cancer has remained a central theme. The increased use of computational tools underscores the interdisciplinary nature of contemporary oncological research. Figure 8 presents the temporal emergence and frequency of trend topics related to the integration of AI in TNBC research; the analysis utilized the authors’ keywords. This figure demonstrates a marked increase in the use of terms such as bioinformatics , molecular subtypes , biomarker , digital pathology, and triple-negative breast cancer from 2020 to 2022, indicating increased adoption of computational tools and representing key areas where AI is transforming TNBC research, enabling advanced data analysis, precise disease classification, biomarker discovery, and enhanced diagnostic imaging. However, by 2023, topics such as triple-negative breast cancer , machine learning , and breast cancer dominated this research landscape, signaling a strong convergence of oncology and artificial intelligence in scholarly focus. By 2024, tnbc , magnetic resonance imaging , and artificial intelligence emerged as the most frequently discussed topics, reflecting a sharp focus on data-driven diagnostics and precision imaging in TNBC research. The rising frequency of these terms over time highlights the expanding influence of AI in improving diagnostic accuracy, personalizing treatment, and increasing research efficiency in TNBC. This development is consistent with broader bibliometric analyses that demonstrate the interdisciplinary convergence of oncology, data science, and medical imaging [ 28 , 56 , 57 ]. 4.7 Countries and authors’ collaboration The nation of the corresponding author provides insight into leadership and teamwork within the international research environment. China and the United States are the leading countries for corresponding authors (Table 4 ), which is consistent with their status as the most cited and productive nations ( Fig.s 3B and 3A ). Articles are classified as either single-country publications (SCP), where all authors are from the same nation and intra-country collaboration is indicated, or multiple-country publications (MCP), which involve contributors from different nations and represent inter-country collaboration [ 19 ]. Countries in Asia and North America, such as China, the USA, India, Korea, and Canada, produce more SCPs than MCPs, indicating a stronger focus on domestic research. This pattern suggests that these research powerhouses depend primarily on established domestic infrastructure, funding, and networks to advance AI integration in TNBC research, while international collaboration remains secondary. In contrast, European countries, including the UK, Georgia, Germany, France, and the Netherlands, rely more extensively on international partnerships, consistent with evidence that transnational collaboration is more prevalent in regions with supportive cross-border policies [ 58 , 59 ]. Although the USA has more SCPs than MCPs, it has a high proportion of internationally co-authored work, highlighting its central role in global research networks. India, despite its relatively high output, relies predominantly on domestic collaborations, indicating limited international integration. The Netherlands exhibits a notably high MCP rate compared to its SCP rate. These differences underscore the strategic value of international collaboration in enhancing the integration of AI in TNBC research beyond mere publication volume. Figure 9 A identifies six co-authorship clusters in the integration of AI in TNBC research. Cluster 1, in red, includes Australia, Belgium, India, the Netherlands, Poland, Saudi Arabia, and Sweden, and demonstrates growing regional collaborations between emerging and established research nations. This agrees with previous studies that showed that India and the Netherlands are increasing their contributions to AI-enabled oncology research [ 25 , 60 ]. Cluster 2, in green, comprises Austria, France, Italy, Spain, the United Kingdom, and the United States, forming the primary hub of research activity. The United States leads in citation impact and is second only to China in terms of publication volume and serves as a central mediator for international collaboration, particularly with European countries [ 58 , 59 ]. Cluster 3, in blue, consists of China and Taiwan, reflecting China's prominent role in breast cancer immunology and AI research, supported by strong institutional partnerships that enhance regional research output [ 25 , 60 ]. The remaining clusters, cluster 4 (Iran and Canada), cluster 5 (Norway and Brazil), and cluster 6 (Germany and South Korea), represent bilateral or specialized collaborations that supplement the global research network. These patterns align with broader trends in international scientific collaboration, where geographic proximity, policy frameworks, and institutional capacity influence the structure and intensity of co-authorship networks [ 58 , 59 ]. Figure 9 B presents the authors’ collaboration network, revealing three distinct and loosely connected co-authorship clusters. Cluster 1 (red) is the smallest and comprises Aneja R and Bhattarai S, demonstrating an active partnership with limited integration into the wider research community, a pattern consistent with peripheral dyadic collaborations in AI-cancer research [ 61 ]. Cluster 2 (green) is the largest and most central, led by prolific authors including Wang Y, Wang X, Zhang X, Zhang J, and Zhang Y. This cluster highlights the substantial contributions of authors with primary affiliation to Chinese-based institutions, who are among the most productive in the integration of AI in TNBC research and frequently engage in high-volume, intra-country collaborations [ 26 , 46 ]. Cluster 3 (blue) consists of Yang W, Sun J, Chen H, Xu Z, and Valero V, forming a subgroup with strong internal collaboration but weaker connections to the central green cluster. Collaborations between research clusters remain fragmented, with limited cross-linkages between Western and Asian scholars. This fragmentation is consistent with bibliometric evidence showing that research on AI integration in biomedical science is concentrated in regional hubs, including the United States, China, and Europe, with trans-regional co-authorship relatively uncommon [ 62 , 63 ]. Increasing inter-cluster collaborations could promote knowledge exchange, methodological diversity, and broader global research impact [ 57 ]. 4.8 Emerging trends analysis The integration of artificial intelligence into triple-negative breast cancer research has accelerated, reshaping oncological investigation and clinical practice. This section examines emerging trends identified through bibliometric mapping. Analysis of the keyword co-occurrence network, topic trends, thematic map, and thematic evolution reveals key developments in this research field. 4.8.1 Digital Pathology and Radiomics Advanced imaging and digital pathology represent foundational yet evolving elements in triple-negative breast cancer research. Thematic evolution analysis indicates that digital pathology , feature selection , and histopathology have emerged as significant themes since 2023 (Fig. 7 B). Trend topics data demonstrate a growing adoption of digital pathology and magnetic resonance imaging (Fig. 8 ). Furthermore, thematic mapping identifies histopathology images , nuclei segmentation , and radiomics as basic themes, suggesting they are highly relevant but not yet fully developed (Fig. 7 A). AI-enhanced imaging supports precise tumor delineation, automated feature extraction, and longitudinal monitoring of treatment response. Digital pathology platforms utilizing convolutional neural networks (CNNs) enable reproducible, high-throughput histological assessments. Radiomics, which transforms medical images into quantitative data, is increasingly used to predict treatment outcomes and identify phenotypic biomarkers. As these technologies mature and further integrate with artificial intelligence, they are likely to become central to innovation in TNBC diagnostics and to advance personalized, data-driven clinical decision-making for patients with TNBC. 4.8.2 Biomarker discovery and predictive modeling Due to the absence of ER, PR, and HER2 receptors, research is currently being intensified to identify therapeutic targets for improved prognosis. Biomarker discovery has become a central focus in triple-negative breast cancer research, particularly as artificial intelligence methods increasingly identify clinically relevant molecular indicators. Thematic evolution indicates biomarker and feature selection as key themes around 2018 to 2022 and 2023 to 2025, respectively (Fig. 7 B). This is supported by the trends’ topic analysis, which showed biomarker as the most frequent term in 2022 (Fig. 8 ). Artificial intelligence models are applied to genomic, proteomic, and radiomic datasets to identify biomarkers associated with TNBC aggressiveness, drug resistance, and survival outcomes. Feature selection methods isolate the most predictive variables, thereby improving model interpretability and clinical applicability. These predictive models facilitate risk stratification and inform personalized treatment planning, which can enhance therapeutic efficacy and minimize adverse effects. The continued expansion of data-driven biomarker research is anticipated to advance precision oncology and translational clinical applications. 4.8.3 Varied artificial intelligence algorithms Artificial intelligence is becoming increasingly influential in triple-negative breast cancer research, facilitating high-throughput data analysis, predictive modeling, and automated diagnostics. Thematic evolution analyses reveal a notable increase in the use of terms such as machine learning and support vector machine from 2023 to 2025, with trend frequency data highlighting the prominence of machine learning in 2023 and artificial intelligence in 2024 (Fig. 7 B, 8 ). Deep neural networks and artificial intelligence are positioned between niche and emerging or declining themes, while graph neural network(s ) are categorized within the emerging or declining quadrant of the thematic map (Fig. 7 A). This placement suggests that, although interest in these technologies is growing, their integration into mainstream TNBC workflows remains limited. Furthermore, deep learning , machine learning , artificial intelligence, convolutional neural networks are placed in the basic theme quadrant indicating that these themes are fundamental, widely connected to other themes in this field but are still evolving. Machine learning (ML) and deep learning (DL) methods are increasingly applied to histopathological image segmentation, biomarker identification, and clinical decision support, resulting in improved diagnostic accuracy and efficiency. As computational oncology advances, AI is anticipated to transition from a peripheral innovation to a central component of TNBC research, reflecting a broader shift toward data-driven medicine. The application of ML and DL algorithms enables the identification of complex patterns in genomic and imaging data, ultimately contributing to earlier detection and more personalized treatment strategies that improve patient outcomes. 4. 9 Future research directions 4.9.1 Clinical translation of AI models The thematic map (Fig. 7 A) identifies artificial intelligence and deep neural networks as emerging technologies that are increasing in relevance yet remain insufficiently integrated into clinical workflows. Subsequent research should focus on developing explainable AI models that are validated and implemented in practical oncology environments. Key priorities include ensuring regulatory compliance, enhancing clinical interpretability, and facilitating integration with electronic health records to promote usability and trust among oncologists [ 64 ]. 4.9.2 Multi-omics integration for personalized therapy The increasing use of multi-omics data and feature selection , as demonstrated in the thematic map (motor theme) and thematic evolution (2023 to 2023), respectively, reflects a transition toward systems-level analysis (Fig. 7 A, B). Future research on triple-negative breast cancer should investigate the application of artificial intelligence to integrate genomic, transcriptomic, proteomic, and epigenomic data for the development of dynamic, patient-specific treatment algorithms. This approach aims to advance precision medicine from static molecular profiling to adaptive, real-time therapeutic guidance [ 65 , 66 ]. 4.9.3 Non-invasive diagnostics and liquid biopsy While currently peripheral in the thematic map (Fig. 7 A), biomarker and feature selection research is increasingly focused on non-invasive diagnostics. Artificial intelligence is expected to significantly advance the analysis of circulating tumor DNA (ctDNA), exosomes, and other liquid biopsy components, facilitating early detection and real-time monitoring of TNBC without the need for tissue samples [ 67 ]. 4.9.4 Immuno-oncology and tumor microenvironment modeling Thematic clustering focused on immune checkpoint inhibitors and cancer-associated fibroblasts ( Fig. 7 A ) indicates increasing scholarly attention to the tumor microenvironment. Future research is expected to employ artificial intelligence to model immune interactions, predict responses to immunotherapies, and identify novel immune biomarkers. These advancements are anticipated to facilitate the development of personalized immuno-oncology strategies specifically adapted to the unique immune landscape of triple-negative breast cancer [ 68 ]. 4.9.5 Increased and sustained collaboration between authors Increased and sustained collaboration between authors is essential for advancing AI integration in TNBC research. Currently, co-authorship networks are split by region and institution. Figure 9 B shows three weakly linked groups. Cluster 1 (red) represents a peripheral partnership between Aneja R and Bhattarai S. Cluster 2 (green) comprises Chinese-based authors, such as Wang Y and Zhang Y, who collaborate primarily within their own country. Cluster 3 (blue) has Western researchers such as Yang W and Valero V (both affiliated with the University of Texas MD Anderson Cancer Center), who work closely together but rarely with members of other clusters. This divide matches other trends that show research clusters stay regional, with few global co-authorships in AI integration in the biosciences [ 62 , 63 ]. This limits both methodological diversity and worldwide impact. Promoting links between groups through international consortia, data sharing, and targeted funding can close these gaps, encourage knowledge exchange, and facilitate innovation. Such efforts also address the isolation of some collaborations [ 69 , 70 ]. Given the status of TNBC as a global health scourge, increased and sustained national and international collaborations will be required in this field to address this threat. 4.10 Limitations This study offers important insights into the integration of artificial intelligence in triple-negative breast cancer research on a global scale. Nevertheless, certain limitations should be acknowledged. The exclusive use of the Scopus database, while recognized for its reliability, resulted in the exclusion of other major databases such as Web of Science, Google Scholar, Dimensions, and Lens. This restriction may have limited the comprehensiveness of the literature reviewed. The study also included only publications up to July 19th of the current year, when documents were retrieved. Research and citation counts may have increased since then, possibly affecting the results. Future research should address these shortcomings. Despite these limitations, the study remains valid and useful, offering valuable insights into current and future directions for AI integration in TNBC research. 5.0 Conclusion Bibliometric analysis was employed to examine the yearly publications, prolific authors, prominent journals, contributing nations, popular keywords, general progress, and evolution in artificial intelligence integration in TNBC research from 2011 to 2025. This paper is the first to analyze the topic using a bibliometric approach based on the Scopus database, offering a comprehensive assessment of research output, including analysis of authors, sources, documents, themes, trends, and future priorities. The publications analyzed in this study were contributed by 2,781 authors affiliated with diverse institutions across the globe. With the annual rise of 38.02%, the body of knowledge is growing steadily. Furthermore, the international co-authorship percentage (28.20%) highlights significant networking in generating scientific information on artificial intelligence integration in triple-negative breast cancer research, albeit in isolated clusters. China and the United States were the most productive and most cited countries, respectively, with the USA leading in global collaboration per published document. The University of Texas MD Anderson Cancer Center was the most relevant affiliation. Cancers was the most productive and impactful source. Zhang J was the most productive author, while Wang X emerged as the most impactful author in the field. Biomarker, radiomics and feature selection were some of the emerging trends in this field. Future research should address clinical translation of AI models, multi-omics for personalized therapy, non-invasive diagnostics and liquid biopsy, immuno-oncology and tumor microenvironment, along with an increased and sustained collaboration between authors to shape the research landscape on AI integration into TNBC research. Declarations Acknowledgements Not applicable Authors' contributions Conceptualization : Israel Ogwuche Ogra, Jeremiah Zaphnathpaaneah Adaji; Methodology : Israel Ogwuche Ogra, Jeremiah Zaphnathpaaneah Adaji, Emohchonne Utos Jonathan, Faustina Ntim Opoku; Formal analysis and investigation: Jeremiah Zaphnathpaaneah Adaji; Precious Ezinne Nebo, Evelyn Omolola Ajibua, Eneh Philip; Data curation: Jeremiah Zaphnathpaaneah Adaji, Shadrack Dangabar Apollos, Daniel Gbenga Adekanmi, Daniel Thakuma Tizhe; Writing - original draft preparation: Jeremiah Zaphnathpaaneah Adaji; Israel Ogwuche Ogra; Writing - review and editing: Israel Ogwuche Ogra, Uche Samuel Ndidi, Umezuruike Linus Opara; Project administration: Israel Ogwuche Ogra, Hadiza Joy Umar, David John Burman Ladan, Kodjovi Sossou; Supervision : Uche Samuel Ndidi, Umezuruike Linus Opara. Funding No funding was received for this research. Data availability Data is provided within the manuscript or supplementary information files. Competing interests The authors have no conflict of interest to declare that are relevant to the content of this article. Ethical approval and consent to participate No aspect of our research required formal ethical approval or usage of participants. Clinical trial number Not applicable. Consent for publication The authors agree on the transfer of the copyright to the Publisher on acceptance of this manuscript for publication. References Dent R, Trudeau M, Pritchard KI, Hanna WM, Kahn HK, Sawka CA, et al. Triple-negative breast cancer: clinical features and patterns of recurrence. Clin Cancer Res. 2007;13(15):4429–34. https://doi.org/10.1158/1078-0432.CCR-06-3045. Elsawaf Z, Sinn HP. Triple-negative breast cancer: clinical and histological correlations. Breast Care. 2011;6(4):273–8. https://doi.org/10.1159/000331643. Carey LA, Dees EC, Sawyer L, Gatti L, Moore DT, Collichio F, et al. The triple negative paradox: primary tumor chemosensitivity of breast cancer subtypes. Clin Cancer Res. 2007;13(8):2329–34. https://doi.org/10.1158/1078-0432.CCR-06-1109. American Cancer Society. Triple-negative Breast Cancer | Details, Diagnosis, and Signs. American Cancer Society; 2023. https://www.cancer.org/cancer/types/breast-cancer/about/types-of-breast-cancer/triple-negative.html. Accessed 20 August 2025 Mediratta K, El-Sahli S, D’Costa V, Wang L. Current progresses and challenges of immunotherapy in triple-negative breast cancer. Cancers. 2020;12(12):3529. https://doi.org/10.3390/cancers12123529. Wu Q, Siddharth S, Sharma D. Triple negative breast cancer: a mountain yet to be scaled despite the triumphs. Cancers. 2021;13(15):3697. https://doi.org/10.3390/cancers13153697. Bayard S, Martini R, Chen Y, Jenkins B, Elhussin I, Cheng E, et al. Abstract PO-139: BRCA sequence variants in breast cancer patients with African ancestry. Cancer Epidemiol Biomarkers Prev. 2022;31(1 Suppl):PO-139. Yao S, Wei L, Hu Q, Liu S, Manojlovic Z, Fiorica PN, et al. Mutational landscape of triple-negative breast cancer in African American women. Nat Genet. 2025;1(1). https://doi.org/10.1038/s41588-025-02322-y. Leon-Ferre RA, Goetz MP. Advances in systemic therapies for triple negative breast cancer. BMJ. 2023;381:p1173. https://doi.org/10.1136/bmj-2022-071674 . Asleh K, Riaz N, Nielsen TO. Heterogeneity of triple negative breast cancer: current advances in subtyping and treatment implications. J Exp Clin Cancer Res. 2022;41(1):265. https://doi.org/10.1186/s13046-022-02476-1. Marra A, Trapani D, Viale G, Criscitiello C, Curigliano G. Practical classification of triple-negative breast cancer: intratumoral heterogeneity, mechanisms of drug resistance, and novel therapies. NPJ Breast Cancer. 2020;6:54. https://doi.org/10.1038/s41523-020-00197-2. Russell SJ, Norvig P. Artificial Intelligence: A Modern Approach. Prentice Hall; 1995. Topol E. Deep Medicine: How Artificial Intelligence Can Make Healthcare Human Again. Hachette UK; 2019. Guo J, Hu J, Zheng Y, Zhao S, Ma J. Artificial intelligence: opportunities and challenges in the clinical applications of triple-negative breast cancer. Br J Cancer. 2023;128(12):2141–9. https://doi.org/10.1038/s41416-023-02215-z. Ocana A, Pandiella A, Privat C, Bravo I, Luengo-Oroz M, Amir E, et al. Integrating artificial intelligence in drug discovery and early drug development: a transformative approach. Biomark Res. 2025;13(1):45. https://doi.org/10.1186/s40364-025-00758-2. Rajput HPS, Lodhi S. AI in drug repurposing. Int J Pharm Sci. 2025;3(5):2098–103. https://doi.org/10.5281/zenodo.15396590. Wan Y, Shen Y, Wang J, Zhang T, Fu X. Knowledge mapping of ultrasound technology and triple-negative breast cancer: a visual and bibliometric analysis. Discov Oncol. 2025;16(1):1248. https://doi.org/10.1007/s12672-025-03063-4. Donthu N, Kumar S, Mukherjee D, Pandey N, Lim WM. How to conduct a bibliometric analysis: an overview and guidelines. J Bus Res. 2021;133:285–96. https://doi.org/10.1016/j.jbusres.2021.04.070. Aria M, Cuccurullo C. bibliometrix: An R-tool for comprehensive science mapping analysis. J Informetr. 2017;11(4):959–75. https://doi.org/10.1016/j.joi.2017.08.007. Chen C. CiteSpace II: detecting and visualizing emerging trends and transient patterns in scientific literature. J Am Soc Inf Sci Technol. 2006;57(3):359–77. https://doi.org/10.1002/asi.20317. van Eck N, Waltman L. Software survey: VOSviewer, a computer program for bibliometric mapping. Scientometrics. 2010;84(2):523–38. https://doi.org/10.1007/s11192-009-0146-3. Syed AH, Khan T. Evolution of research trends in artificial intelligence for breast cancer diagnosis and prognosis over the past two decades: a bibliometric analysis. Front Oncol. 2022;12:854927. https://doi.org/10.3389/fonc.2022.854927. Singh S, Healy NA. The top 100 most-cited articles on artificial intelligence in breast radiology: a bibliometric analysis. Insights Imaging. 2024;15(1):297. https://doi.org/10.1186/s13244-024-01869-4. Hou C, Huang T, Hu K, Ye Z, Guo J, Zhou H. Artificial intelligence-assisted multimodal imaging for the clinical applications of breast cancer: a bibliometric analysis. Discov Oncol. 2025;16(1):537. https://doi.org/10.1007/s12672-025-02329-1. Wu X, Xia Y, Lou X, Huang K, Wu L, Gao C. Decoding breast cancer imaging trends: the role of AI and radiomics through bibliometric insights. Breast Cancer Res. 2025;27(1):29. https://doi.org/10.1186/s13058-025-01983-1. Li S, Zhang N, Zhang H, Zhou R, Li Z, Yang X, et al. Artificial intelligence learning landscape of triple-negative breast cancer uncovers new opportunities for enhancing outcomes and immunotherapy responses. J Big Data. 2023;10(1):132. https://doi.org/10.1186/s40537-023-00809-1. Wang X, Li X, Dong T, Yu W, Jia Z, Hou Y, et al. Global biomarker trends in triple-negative breast cancer research: a bibliometric analysis. Int J Surg. 2024;110(12):7962–83. https://doi.org/10.1097/JS9.0000000000001799. Wang K, Zheng C, Xue L, Deng D, Zeng L, Li M, et al. A bibliometric analysis of 16,826 triple-negative breast cancer publications using multiple machine learning algorithms: progress in the past 17 years. Front Med. 2023;10:999312. https://doi.org/10.3389/fmed.2023.999312. Burnham JF. Scopus database: a review. Biomed Digit Libr. 2006;3(1):1. https://doi.org/10.1186/1742-5581-3-1. Grant MJ. Keywords and their role in information retrieval. Health Inf Libr J. 2010;27(3):173–5. https://doi.org/10.1111/j.1471-1842.2010.00904.x. Alzate-Granados JP, Niño LF. Prediction of overall and relapse-free survival in triple-negative breast cancer patients through machine learning-based clustering on clinical data. Clin Breast Cancer. 2025. https://doi.org/10.1016/j.clbc.2025.07.027. Keren L, Bosse M, Marquez D, Angoshtari R, Jain S, Varma S, et al. A structured tumor-immune microenvironment in triple negative breast cancer revealed by multiplexed ion beam imaging. Cell. 2018;174(6):1373–87. https://doi.org/10.1016/j.cell.2018.08.039. Braman NM, Etesami M, Prasanna P, Dubchuk C, Gilmore H, Tiwari P, et al. Intratumoral and peritumoral radiomics for the pretreatment prediction of pathological complete response to neoadjuvant chemotherapy based on breast DCE-MRI. Breast Cancer Res. 2017;19(1):57. https://doi.org/10.1186/s13058-017-0846-1. He Y, Jiang Z, Chen C, Wang X. Classification of triple-negative breast cancers based on immunogenomic profiling. J Exp Clin Cancer Res. 2018;37(1):327. https://doi.org/10.1186/s13046-018-1002-1. Zou Y, Xie J, Zheng S, Liu W, Tang Y, Tian W, et al. Leveraging diverse cell-death patterns to predict the prognosis and drug sensitivity of triple-negative breast cancer patients after surgery. Int J Surg. 2022;107:106936. https://doi.org/10.1016/j.ijsu.2022.106936. Meyer AS, Miller MA, Gertler FB, Lauffenburger DA. The receptor AXL diversifies EGFR signaling and limits the response to EGFR-targeted inhibitors in triple-negative breast cancer cells. Sci Signal. 2013;6(287):ra66. https://doi.org/10.1126/scisignal.2004155. Saha A, Harowicz MR, Grimm LJ, Kim CE, Ghate SV, Walsh R, et al. A machine learning approach to radiogenomics of breast cancer: a study of 922 subjects and 529 DCE-MRI features. Br J Cancer. 2018;119(4):508–16. https://doi.org/10.1038/s41416-018-0185-8. Xiao Y, Ma D, Yang YS, Yang Y, Ding JH, Gong Y, et al. Comprehensive metabolomics expands precision medicine for triple-negative breast cancer. Cell Res. 2022;32(5):477–90. https://doi.org/10.1038/s41422-022-00614-0. Mostavi M, Chiu YC, Huang Y, Chen Y. Convolutional neural network models for cancer type prediction based on gene expression. BMC Med Genomics. 2020;13(Suppl 5):44. https://doi.org/10.1186/s12920-020-0712-5. Wu J, Hicks C. Breast cancer type classification using machine learning. J Pers Med. 2021;11(2):61. https://doi.org/10.3390/jpm11020061. Cain EH, Saha A, Harowicz MR, Marks JR, Marcom PK, Mazurowski MA. Multivariate machine learning models for prediction of pathologic response to neoadjuvant therapy in breast cancer using MRI features: a study using an independent validation set. Breast Cancer Res Treat. 2019;173(2):455–63. https://doi.org/10.1007/s10549-018-4990-9. Zupic I, Čater T. Bibliometric methods in management and organization. Organ Res Methods. 2015;18(3):429–72. https://doi.org/10.1177/1094428114562629. Duede E, Dolan W, Bauer A, Foster I, Lakhani K. Oil & water? Diffusion of AI within and across scientific fields. arXiv preprint. 2024;arXiv:2405.15828. https://doi.org/10.48550/arXiv.2405.15828. Wang X, Ahmad I, Javeed D, Zaidi SA, Alotaibi FM, Ghoneim ME, et al. Intelligent hybrid deep learning model for breast cancer detection. Electronics. 2022;11(17):2767. https://doi.org/10.3390/electronics11172767. Dong H, Wang X, Zheng Y, Li J, Liu Z, Wang A, et al. Mapping the rapid growth of multi-omics in tumor immunotherapy: bibliometric evidence of technology convergence and paradigm shifts. Hum Vaccin Immunother. 2025;21(1):2493539. https://doi.org/10.1080/21645515.2025.2493539. Wang R, Huang S, Wang P, Shi X, Li S, Ye Y, et al. Bibliometric analysis of the application of deep learning in cancer from 2015 to 2023. Cancer Imaging. 2024;24(1):85. https://doi.org/10.1186/s40644-024-00737-0. Hajkowicz S, Sanderson C, Karimi S, Bratanova A, Naughtin C. Artificial intelligence adoption in the physical sciences, natural sciences, life sciences, social sciences and the arts and humanities: a bibliometric analysis of research publications from 1960–2021. arXiv preprint. 2023;arXiv:2306.09145. https://doi.org/10.48550/arXiv.2306.09145. Guo Q, Geng C, Yao N, Zhao L. Can digital infrastructure enhance economic efficiency? Evidence from China. Qual Quant. 2024;58(2):1729–52. https://doi.org/10.1007/s11135-023-01710-y. Roberts H, Cowls J, Hine E, Morley J, Wang V, Taddeo M, et al. Governing artificial intelligence in China and the European Union: comparing aims and promoting ethical outcomes. Inf Soc. 2023;39(2):79–97. https://doi.org/10.1080/01972243.2022.2124565. Webster G, Creemers R, Kania E, Triolo P. Full translation: China’s “new generation artificial intelligence development plan” (2017). DigiChina, Stanford University; 2017. https://digichina.stanford.edu/work/full-translation-chinas-new-generation-artificial-intelligence-development-plan-2017/. Accessed 15 September 2025. Li P, Li J, Tong X, Xiao Z, Diao W, Zhong C, et al. Global research trends and prospects related to tumor microenvironment within triple-negative breast cancer: a bibliometric analysis. Front Immunol. 2023;14:1261290. https://doi.org/10.3389/fimmu.2023.1261290. Xiong N, Wu H, Yu Z. Advancements and challenges in triple-negative breast cancer: a comprehensive review of therapeutic and diagnostic strategies. Front Oncol. 2024;14:1405491. https://doi.org/10.3389/fonc.2024.1405491. Hirsch JE. An index to quantify an individual’s scientific research output. Proc Natl Acad Sci U S A. 2005;102(46):16569–72. https://doi.org/10.1073/pnas.0507655102. Egghe L. Theory and practise of the g-index. Scientometrics. 2006;69(1):131–52. doi:10.1007/s11192-006-0144-7. Ekinci B, Tekedere H. Bibliometric analysis of research on artificial intelligence applications in breast cancer diagnosis. Technol Health Care. 2025;09287329251362602. https://doi.org/10.3233/THC-240037. Bhalla K, Xiao Q, Luna JM, Podany E, Ahmad T, Ademuyiwa FO, et al. Radiologic imaging biomarkers in triple-negative breast cancer: a literature review about the role of artificial intelligence and the way forward. BJR Artif Intell. 2024;1(1):ubae016. https://doi.org/10.1093/bjrai/ubae016. Wang SH, Chen G, Zhong X, Lin T, Shen Y, Fan X, et al. Global development of artificial intelligence in cancer field: a bibliometric analysis range from 1983 to 2022. Front Oncol. 2023;13:1215729. https://doi.org/10.3389/fonc.2023.1215729. Kwiek M. International research collaboration and international research orientation: comparative findings about European academics. J Stud Int Educ. 2018;22(2):136–60. https://doi.org/10.1177/1028315317747084. Wagner CS, Park HW, Leydesdorff L. The continuing growth of global cooperation networks in research: a conundrum for national governments. PLoS One. 2015;10(7):e0131816. https://doi.org/10.1371/journal.pone.0131816. Singh A, Singh A, Bhattacharya S. Research trends on AI in breast cancer diagnosis, and treatment over two decades. Discov Oncol. 2024;15(1):772. https://doi.org/10.1007/s12672-024-01671-0. Lin L, Liang L, Wang M, Huang R, Gong M, Song G, et al. A bibliometric analysis of worldwide cancer research using machine learning methods. Cancer Innov. 2023;2(3):219–32. https://doi.org/10.1002/cai2.68. Koçak M, Akçalı Z. The published role of artificial intelligence in drug discovery and development: a bibliometric and social network analysis from 1990 to 2023. J Cheminform. 2025;17(1):71. https://doi.org/10.1186/s13321-025-00988-4. Xu Q, Feng X, Qin S, Hong Y, Cui R, Liang J, et al. Research on therapeutic clinical trials including immunotherapy in triple-negative breast cancer: a bibliometric analysis. Front Oncol. 2024;14:1423924. https://doi.org/10.3389/fonc.2024.1423924. Liao J, Li X, Gan Y, Han S, Rong P, Wang W, et al. Artificial intelligence assists precision medicine in cancer treatment. Front Oncol. 2023;12:998222. https://doi.org 10.3389/fonc.2022.998222. Yang S, Wang Z, Wang C, Li C, Wang B. Comparative evaluation of machine learning models for subtyping triple-negative breast cancer: a deep learning-based multi-omics data integration approach. J Cancer. 2024;15(12):3943–54. https://doi.org/10.7150/jca.93215. Zhang N, Zhang Y, Yang RF, Chu HQ, Rehman A, Yang LY, et al. Multi-omics integration uncovers key transcriptional regulators in triple-negative breast cancer spatial heterogeneity. Front Genet. 2025;16:1614254. https://doi.org/10.3389/fgene.2025.1614254. Sheng J, Zong X. Liquid biopsy in TNBC: significance in diagnostics, prediction, and treatment monitoring. Front Oncol. 2025;15:1607960. https://doi.org/10.3389/fonc.2025.1607960. Guo Z, Zhu Z, Lin X, Wang S, Wen Y, Wang L, et al. Tumor microenvironment and immunotherapy for triple-negative breast cancer. Biomark Res. 2024;12(1):166. https://doi.org/10.1186/s40364-024-00714-6. Liang H, Yin G, Feng D, Chen H, Liu X, Li J. Research trends on nanomaterials in triple-negative breast cancer (TNBC): a bibliometric analysis from 2010 to 2024. Drug Deliv Transl Res. 2024;1–6. https://doi.org/10.1007/s13346-024-01704-9. Ndidi US, Ogra IO, Jonathan EU, Iroha OK. Drug repurposing in cancer research: a bibliometric analysis. Discov Oncol. 2025;16:1796. https://doi.org/10.1007/s12672-025-02895-4. Additional Declarations No competing interests reported. Supplementary Files GraphicAbstract.jpg Cite Share Download PDF Status: Posted Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-7830165","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Systematic Review","associatedPublications":[],"authors":[{"id":528053503,"identity":"a54c2fdd-09f8-4907-9b1c-45771f3cadb8","order_by":0,"name":"Israel Ogwuche Ogra","email":"","orcid":"","institution":"UNESCO International Centre for Biotechnology","correspondingAuthor":false,"prefix":"","firstName":"Israel","middleName":"Ogwuche","lastName":"Ogra","suffix":""},{"id":528053504,"identity":"692d12ce-4eee-4284-b782-0d0bde7ccb57","order_by":1,"name":"Jeremiah Zaphnathpaaneah Adaji","email":"","orcid":"","institution":"Maduka University Ekwegbe-Nsukka","correspondingAuthor":false,"prefix":"","firstName":"Jeremiah","middleName":"Zaphnathpaaneah","lastName":"Adaji","suffix":""},{"id":528053505,"identity":"71ac434a-acb9-405a-813e-371a76eb6798","order_by":2,"name":"Hadiza Joy Umar","email":"","orcid":"","institution":"Sydani Group","correspondingAuthor":false,"prefix":"","firstName":"Hadiza","middleName":"Joy","lastName":"Umar","suffix":""},{"id":528053506,"identity":"36a5d510-a9d6-47b0-a36c-addf6d98d598","order_by":3,"name":"Shadrack Dangabar Apollos","email":"","orcid":"","institution":"Ahmadu Bello University","correspondingAuthor":false,"prefix":"","firstName":"Shadrack","middleName":"Dangabar","lastName":"Apollos","suffix":""},{"id":528053507,"identity":"e2d7e6fd-12a4-47b9-aa27-a57a3dfff149","order_by":4,"name":"Daniel Gbenga Adekanmi","email":"","orcid":"","institution":"Autonomous University of Coahuila","correspondingAuthor":false,"prefix":"","firstName":"Daniel","middleName":"Gbenga","lastName":"Adekanmi","suffix":""},{"id":528053508,"identity":"0bf3ea1d-fd6a-4572-820a-d2fce9ce826a","order_by":5,"name":"Daniel Thakuma Tizhe","email":"","orcid":"","institution":"Adamawa State Post Primary Schools Management Board","correspondingAuthor":false,"prefix":"","firstName":"Daniel","middleName":"Thakuma","lastName":"Tizhe","suffix":""},{"id":528053509,"identity":"b39ba1dc-f250-4264-911c-81d60a6caff7","order_by":6,"name":"Precious Ezinne Nebo","email":"","orcid":"","institution":"Ahmadu Bello University","correspondingAuthor":false,"prefix":"","firstName":"Precious","middleName":"Ezinne","lastName":"Nebo","suffix":""},{"id":528053510,"identity":"bd44ac77-532b-4fd7-a3ca-c782e7781813","order_by":7,"name":"David John Burman Ladan","email":"","orcid":"","institution":"University of Jos","correspondingAuthor":false,"prefix":"","firstName":"David","middleName":"John Burman","lastName":"Ladan","suffix":""},{"id":528053511,"identity":"00d5473a-6e01-4f81-a829-2a8ac92a9002","order_by":8,"name":"Evelyn Omolola Ajibua","email":"","orcid":"","institution":"University of Benin","correspondingAuthor":false,"prefix":"","firstName":"Evelyn","middleName":"Omolola","lastName":"Ajibua","suffix":""},{"id":528053512,"identity":"74dddb3e-1d71-4294-b88a-5650a0c4b11f","order_by":9,"name":"Eneh Philip","email":"","orcid":"","institution":"UNESCO International Centre for Biotechnology","correspondingAuthor":false,"prefix":"","firstName":"Eneh","middleName":"","lastName":"Philip","suffix":""},{"id":528053513,"identity":"d567a71a-f412-443c-8323-47030f264e05","order_by":10,"name":"Faustina Ntim Opoku","email":"","orcid":"","institution":"Tomsk Polytechnic University","correspondingAuthor":false,"prefix":"","firstName":"Faustina","middleName":"Ntim","lastName":"Opoku","suffix":""},{"id":528053514,"identity":"31bf217b-3472-452a-a0a2-cd004d7cc12a","order_by":11,"name":"Emohchonne Utos Jonathan","email":"","orcid":"","institution":"Federal University Wukari","correspondingAuthor":false,"prefix":"","firstName":"Emohchonne","middleName":"Utos","lastName":"Jonathan","suffix":""},{"id":528053515,"identity":"ece5dcd9-f90b-45ac-8168-967d62907b56","order_by":12,"name":"Uche Samuel Ndidi","email":"","orcid":"","institution":"Ahmadu Bello University","correspondingAuthor":false,"prefix":"","firstName":"Uche","middleName":"Samuel","lastName":"Ndidi","suffix":""},{"id":528053516,"identity":"6af3d3fb-a8c2-4235-9172-50897724474e","order_by":13,"name":"Kodjovi Sossou","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA5UlEQVRIiWNgGAWjYDACHgYGCQkQxXyA8QGIz0e8FrYEZgMQn40oLWAGWwIbmEFQi3zP4YM3LCoOyzCw8T6r/JpjJ8PGwPzw0Q08WgzOtiVbSJw5DHQYu9lt2W3JQIexGRvn4NPCz2MmIdmWxsMg38Z2W3IbM1ALD5s0Pi3y/TAtbGxsxZLb6glrYTjbA9JiA9bC+HHbYcJaDM4cA/nFhgeog1macdtxHjZmAn6R70k+eFuiQsKeH2TJz23V9vzszQ8f43UYEDCD4gMUHcw8YC4B5SDA+AHG+EGE6lEwCkbBKBh5AAA1DjYpUamPmwAAAABJRU5ErkJggg==","orcid":"","institution":"LaSBASE: Laboratoire des Sciences Biomédicales, Alimentaires et de Santé Environnementale","correspondingAuthor":true,"prefix":"","firstName":"Kodjovi","middleName":"","lastName":"Sossou","suffix":""},{"id":528053517,"identity":"fd1eecd4-c031-40b1-9512-48f268bea17f","order_by":14,"name":"Umezuruike Linus Opara","email":"","orcid":"","institution":"UNESCO International Centre for Biotechnology","correspondingAuthor":false,"prefix":"","firstName":"Umezuruike","middleName":"Linus","lastName":"Opara","suffix":""}],"badges":[],"createdAt":"2025-10-10 21:08:16","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7830165/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7830165/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":93566210,"identity":"6d2371cb-d553-4179-a305-625dff9ec03a","added_by":"auto","created_at":"2025-10-15 08:28:34","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1515480,"visible":true,"origin":"","legend":"","description":"","filename":"Manuscript.docx","url":"https://assets-eu.researchsquare.com/files/rs-7830165/v1/9ec7cb22d7549338a17403cf.docx"},{"id":93564845,"identity":"3f3314b8-ead2-4c48-af82-cbfb7b63935d","added_by":"auto","created_at":"2025-10-15 08:20:34","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":14794,"visible":true,"origin":"","legend":"","description":"","filename":"812fdace7b254cd2a269ec8e8f2050e4.json","url":"https://assets-eu.researchsquare.com/files/rs-7830165/v1/e2e1a020d6d7a0efca0431e9.json"},{"id":93564848,"identity":"5274658f-412c-4287-aa06-f22d864b1371","added_by":"auto","created_at":"2025-10-15 08:20:34","extension":"jpg","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":130260,"visible":true,"origin":"","legend":"","description":"","filename":"GraphicAbstract.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7830165/v1/0f9c05671cbd8a084d569052.jpg"},{"id":93566715,"identity":"04659565-4d5c-41dc-9c70-1ff8c276216d","added_by":"auto","created_at":"2025-10-15 08:36:34","extension":"xml","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":236377,"visible":true,"origin":"","legend":"","description":"","filename":"812fdace7b254cd2a269ec8e8f2050e41enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-7830165/v1/1cf48a6f4735b175b55a13e5.xml"},{"id":93564852,"identity":"8e1335d5-13d6-4dfb-b836-5527758dc0b8","added_by":"auto","created_at":"2025-10-15 08:20:34","extension":"png","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":217575,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7830165/v1/c7cd41270119f360ba7ec103.png"},{"id":93564847,"identity":"8ebc5e0f-2fad-4ecf-a0f6-461b9b217c0e","added_by":"auto","created_at":"2025-10-15 08:20:34","extension":"png","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":41176,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7830165/v1/30f6921c04f234c04c901865.png"},{"id":93566214,"identity":"b3a74832-ccd7-4052-9079-4c27d19baf47","added_by":"auto","created_at":"2025-10-15 08:28:35","extension":"png","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":69395,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7830165/v1/9da5e694e21737c306ad39db.png"},{"id":93566213,"identity":"ffaef3ab-7d21-4d31-923b-27a64891079e","added_by":"auto","created_at":"2025-10-15 08:28:34","extension":"png","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":24904,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-7830165/v1/b4263b7869a52eaa54004c03.png"},{"id":93564856,"identity":"762957ba-e8b3-44b0-83ee-794fd3716b8d","added_by":"auto","created_at":"2025-10-15 08:20:34","extension":"png","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":76424,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-7830165/v1/af548249d98caf6871220083.png"},{"id":93564854,"identity":"662bcb5a-a53d-4609-a2e7-50719576ebb2","added_by":"auto","created_at":"2025-10-15 08:20:34","extension":"png","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":646201,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-7830165/v1/8391c1e63724003ae0489e3a.png"},{"id":93564868,"identity":"d8641b24-232d-4962-9e4e-7da7a1bc14e5","added_by":"auto","created_at":"2025-10-15 08:20:35","extension":"png","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":193989,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-7830165/v1/326597f430b7848873a18099.png"},{"id":93564857,"identity":"9f5e38a6-1471-463a-9280-9b00e2d93eac","added_by":"auto","created_at":"2025-10-15 08:20:34","extension":"png","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":47447,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage8.png","url":"https://assets-eu.researchsquare.com/files/rs-7830165/v1/a766be8d7ace57dc9533f195.png"},{"id":93568128,"identity":"c9dce44f-bfcc-46cd-94b8-a642a5e5c63e","added_by":"auto","created_at":"2025-10-15 08:44:35","extension":"png","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":113164,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage9.png","url":"https://assets-eu.researchsquare.com/files/rs-7830165/v1/e7b96f24762b4df7dd989370.png"},{"id":93564859,"identity":"dd23b05f-2a2a-4dc8-883e-24851a5d812d","added_by":"auto","created_at":"2025-10-15 08:20:35","extension":"png","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":47357,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7830165/v1/c53b9899879c14d757951bb8.png"},{"id":93564864,"identity":"0ab39f35-be43-4f1e-95f3-6726d18475e6","added_by":"auto","created_at":"2025-10-15 08:20:35","extension":"png","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":17426,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7830165/v1/3876d4f1e11aa6244acfb029.png"},{"id":93564860,"identity":"73d8d706-5bda-4231-a40b-4e613ebb158b","added_by":"auto","created_at":"2025-10-15 08:20:35","extension":"png","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":25192,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7830165/v1/8877ec0b171caaf83be2a4ca.png"},{"id":93564858,"identity":"eb84d840-bef7-48de-b30e-46ff29037260","added_by":"auto","created_at":"2025-10-15 08:20:34","extension":"png","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":13525,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-7830165/v1/b959971ff7cb82e33e570982.png"},{"id":93564862,"identity":"54f61643-b4b3-410c-a6ca-a67f209e33e9","added_by":"auto","created_at":"2025-10-15 08:20:35","extension":"png","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":19197,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-7830165/v1/bd2c67bf8cd2914d4524cdac.png"},{"id":93564866,"identity":"49fcf60d-8a01-4110-a7fb-bf62833d546e","added_by":"auto","created_at":"2025-10-15 08:20:35","extension":"png","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":92583,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-7830165/v1/bcd71ecadd57bfd4ba99b2bc.png"},{"id":93566717,"identity":"7bde7445-33da-42b4-a677-abfac806eab0","added_by":"auto","created_at":"2025-10-15 08:36:35","extension":"png","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":30705,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-7830165/v1/6636a91e2db221e17591382f.png"},{"id":93566217,"identity":"bb8b8db3-b203-4910-ab47-67771a73f163","added_by":"auto","created_at":"2025-10-15 08:28:35","extension":"png","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":15641,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage8.png","url":"https://assets-eu.researchsquare.com/files/rs-7830165/v1/2c6b75903246fc7fbdf6e590.png"},{"id":93564863,"identity":"5c5e81ae-a761-46f0-ae7b-d39023b07ef5","added_by":"auto","created_at":"2025-10-15 08:20:35","extension":"png","order_by":21,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":16948,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage9.png","url":"https://assets-eu.researchsquare.com/files/rs-7830165/v1/4da89ffe1ea7a4016bfd3af6.png"},{"id":93564875,"identity":"c0a3a196-2a1a-4608-98d2-94cc408642da","added_by":"auto","created_at":"2025-10-15 08:20:35","extension":"xml","order_by":22,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":236728,"visible":true,"origin":"","legend":"","description":"","filename":"812fdace7b254cd2a269ec8e8f2050e41structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7830165/v1/92cbdbbfa74cf95add5fe38b.xml"},{"id":93564874,"identity":"8ec93973-919c-43a1-be91-df1fe5974257","added_by":"auto","created_at":"2025-10-15 08:20:35","extension":"html","order_by":23,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":260429,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-7830165/v1/b922d2afff342eae8aecd0da.html"},{"id":93564840,"identity":"f0fc40cf-14d4-421a-9804-ddaebd3473f6","added_by":"auto","created_at":"2025-10-15 08:20:34","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":217575,"visible":true,"origin":"","legend":"\u003cp\u003ePRISMA flow diagram\u003c/p\u003e","description":"","filename":"floatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-7830165/v1/d66746e5c0943b7f5d8f90c1.png"},{"id":93566207,"identity":"76cdae4f-32e0-45c2-8015-b7db02fce030","added_by":"auto","created_at":"2025-10-15 08:28:34","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":41176,"visible":true,"origin":"","legend":"\u003cp\u003e\u0026nbsp;(A) Yearly distribution of scientific publications on the integration of artificial intelligence in TNBC research (B) Yearly average citations of scientific publications on the integration of artificial intelligence in TNBC research\u003c/p\u003e","description":"","filename":"floatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-7830165/v1/fc56a067f894d5a096e58389.png"},{"id":93566208,"identity":"1e2d4666-5b1a-4f7c-8630-ae4f7943d88f","added_by":"auto","created_at":"2025-10-15 08:28:34","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":69395,"visible":true,"origin":"","legend":"\u003cp\u003e(A) The distribution of scientific publications on artificial intelligence integration in TNBC research by world map, with the deep blue color representing the countries with a higher number of publications and a bar chart showing the number of publications from the top 10 countries involved in artificial intelligence integration in TNBC research; (B) Total citations of the top 10 countries on AI integration in TNBC research\u003c/p\u003e","description":"","filename":"floatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-7830165/v1/298b4abe6db96cfbcd5328b9.png"},{"id":93564861,"identity":"9684056e-b0d2-441a-b097-d14e823f5d5f","added_by":"auto","created_at":"2025-10-15 08:20:35","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":24904,"visible":true,"origin":"","legend":"\u003cp\u003e(A) The most relevant affiliations of scientific publications on the integration of AI in TNBC research; (B) The top 10 relevant sources of scientific publications on the integration of AI in TNBC research; (C) The source impact of scientific publications on the integration of AI in TNBC research\u003c/p\u003e","description":"","filename":"floatimage4.png","url":"https://assets-eu.researchsquare.com/files/rs-7830165/v1/6f67ed61333a1b1baf864cf3.png"},{"id":93564843,"identity":"69a2bc59-cd8d-4526-ad1d-79ae7ede7a05","added_by":"auto","created_at":"2025-10-15 08:20:34","extension":"png","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":76424,"visible":true,"origin":"","legend":"\u003cp\u003e(A) The most relevant authors of scientific publications on the integration of AI in TNBC research; (B) Top authors’ productivity over time from 2017 to 2025\u003c/p\u003e","description":"","filename":"floatimage5.png","url":"https://assets-eu.researchsquare.com/files/rs-7830165/v1/a080c2f75e0fc207f66f148f.png"},{"id":93566212,"identity":"7886f5a6-164e-4a27-b286-d9ebef0633a8","added_by":"auto","created_at":"2025-10-15 08:28:34","extension":"png","order_by":6,"title":"Figure 6","display":"","copyAsset":false,"role":"figure","size":646201,"visible":true,"origin":"","legend":"\u003cp\u003eKeywords co-occurrence network analysis. (A) All keywords co-occurrence network; (B) Authors’ keywords co-occurrence network\u003c/p\u003e","description":"","filename":"floatimage6.png","url":"https://assets-eu.researchsquare.com/files/rs-7830165/v1/a4cdf024828adf7458e6a24c.png"},{"id":93564872,"identity":"9173c85f-04f7-4ba4-8e75-b7afb17c8c69","added_by":"auto","created_at":"2025-10-15 08:20:35","extension":"png","order_by":7,"title":"Figure 7","display":"","copyAsset":false,"role":"figure","size":193989,"visible":true,"origin":"","legend":"\u003cp\u003e(A) Thematic map of authors’ keywords; (B) Thematic evolution of authors’ keywords\u003c/p\u003e","description":"","filename":"floatimage7.png","url":"https://assets-eu.researchsquare.com/files/rs-7830165/v1/01028f341605f729b5170160.png"},{"id":93566716,"identity":"ac939279-c2a5-471a-8a23-9e59cd64feab","added_by":"auto","created_at":"2025-10-15 08:36:34","extension":"png","order_by":8,"title":"Figure 8","display":"","copyAsset":false,"role":"figure","size":47447,"visible":true,"origin":"","legend":"\u003cp\u003eTrend topics on AI integration in TNBC research based on authors’ keywords\u003c/p\u003e","description":"","filename":"floatimage8.png","url":"https://assets-eu.researchsquare.com/files/rs-7830165/v1/df2e95982536409c93979440.png"},{"id":93564851,"identity":"e56a8834-c2cb-4e51-b9de-7849bdd6ec89","added_by":"auto","created_at":"2025-10-15 08:20:34","extension":"png","order_by":9,"title":"Figure 9","display":"","copyAsset":false,"role":"figure","size":113164,"visible":true,"origin":"","legend":"\u003cp\u003e(A) Network of the co-authorship countries; (B) Authors’ collaboration network\u003c/p\u003e","description":"","filename":"floatimage9.png","url":"https://assets-eu.researchsquare.com/files/rs-7830165/v1/dd1b5926ab6fb839fbc0cdb2.png"},{"id":94469131,"identity":"5eec0e28-9c45-4e70-a199-f8e73f4fd46b","added_by":"auto","created_at":"2025-10-27 15:27:03","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":3120062,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7830165/v1/36c8f2ba-4634-454d-b785-d7cbdfbb5d99.pdf"},{"id":93564842,"identity":"8d3a1594-405d-4ae3-add5-7ec2efd7cce0","added_by":"auto","created_at":"2025-10-15 08:20:34","extension":"jpg","order_by":0,"title":"","display":"","copyAsset":false,"role":"supplement","size":130260,"visible":true,"origin":"","legend":"","description":"","filename":"GraphicAbstract.jpg","url":"https://assets-eu.researchsquare.com/files/rs-7830165/v1/2024365693e512cedfe44f10.jpg"}],"financialInterests":"No competing interests reported.","formattedTitle":"Integration of Artificial Intelligence in Triple-Negative Breast Cancer Research: A Bibliometric and Emerging Trends Analysis","fulltext":[{"header":"1.0 Introduction","content":"\u003cp\u003eTriple-negative breast cancer (TNBC) is a subtype of breast cancer that does not overexpress the human epidermal growth factor receptor 2 (HER2) protein and lacks both estrogen (ER) and progesterone (PR) receptors [\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e, \u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e]. It is the most aggressive breast cancer (BC) subtype both clinically and physiologically and often associated with early relapse, strong invasiveness, and a dismal outcome [\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e, \u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e]. Despite accounting for approximately 10\u0026ndash;15% of BC cases, it contributes substantially to BC-associated mortalities [\u003cspan additionalcitationids=\"CR5\" citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e]. Younger women, especially those of African descent, and individuals with BRCA1 mutations are more likely to have TNBC [\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e, \u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e]. Its lack of actionable hormone or HER2 targets limits therapeutic options to chemotherapy, often with poor long-term outcomes [\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e]. Because TNBC is genomically unstable, highly proliferative, and exhibits heterogeneous tumor biology, it serves as a robust preclinical model for studying breast cancer progression, therapeutic resistance, and novel treatment strategies, making it central to translational and experimental oncology research [\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e, \u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e].\u003c/p\u003e\u003cp\u003eRecent advances in data science have seen the application of Artificial Intelligence (AI) to TNBC research. AI refers to computer systems capable of performing tasks that typically require human intelligence, such as learning, reasoning, and decision-making [\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e]. AI assists in improving diagnosis, treatment planning, medication discovery, and patient monitoring in healthcare by enabling sophisticated data analysis, pattern recognition, and predictive modelling [\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e]. Precision medicine has been enhanced through the application of machine learning (ML) and deep learning (DL) algorithms to imaging, genomics, and clinical datasets. In TNBC research, AI enables radiomics, histopathological image analysis, and multi-omics data integration to forecast prognosis, pinpoint therapeutic targets, and stratify patients for specialized therapies [\u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e]. Additionally, medication repurposing and biomarker identification in TNBC have been facilitated by AI-driven models, which may provide answers to the disease's high heterogeneity and lack of effective targeted therapy. AI continues to influence TNBC research, propelling advancements toward earlier detection and more efficient, individualized treatments as computing power and biomedical datasets continue to expand [\u003cspan additionalcitationids=\"CR16\" citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e].\u003c/p\u003e\u003cp\u003eTo study or evaluate the impact of AI on TNBC research, several research approaches or methods are commonly used, one of which is bibliometric analysis. Bibliometric analysis is a systematic study that is carried out on scholarly articles in order to identify patterns, trends, and impact within a certain field. It is a technique that is used for assessing a huge amount of scientific data [\u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e]. The growing interest in the field of breast cancer, especially triple-negative breast cancer research, has led to an exponential growth of scholarly articles; therefore, a bibliometric analysis has emerged as a pertinent method to map the intellectual landscape, identify key research trends, key players, collaboration networks, publication patterns, and also highlight influential studies that can guide future research. Understanding these dynamics is essential for framing the on-going discourse on the integration of artificial intelligence in TNBC research. Software tools such as VOSviewer, the R package Bibliometrix, and CiteSpace are among the most commonly used for conducting bibliometric analyses. These tools are widely recognized in bibliometric research across diverse scientific disciplines, including the biomedical sciences, for their ability to map research landscapes, identify collaboration networks, and detect emerging trends with high precision [\u003cspan additionalcitationids=\"CR20\" citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e]. When applied to AI-driven TNBC literature mapping, they enable the systematic visualization of research hotspots, thematic evolution, and knowledge gaps, thereby guiding future investigations and fostering targeted innovation in this challenging breast cancer subtype.\u003c/p\u003e\u003cp\u003eBibliometrics has been extensively employed to objectively and quantitatively assess research trends and emerging topics on the integration of artificial intelligence in breast cancer research. Some of such studies include \u0026ldquo;Evolution of research trends in artificial intelligence for breast cancer diagnosis and prognosis over the past two decades: A bibliometric analysis\u0026rdquo; [\u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e]; \u0026ldquo;The top 100 most-cited articles on artificial intelligence in breast radiology: A bibliometric analysis\u0026rdquo; [\u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e23\u003c/span\u003e]; \u0026ldquo;Artificial intelligence-assisted multimodal imaging for the clinical applications of breast cancer: A bibliometric analysis\u0026rdquo; [\u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e24\u003c/span\u003e]; and \u0026ldquo;Decoding breast cancer imaging trends: the role of AI and radiomics through bibliometric insights\u0026rdquo; [\u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e25\u003c/span\u003e]. A few bibliometric analyses have been conducted with mention of AI as a future research direction in TNBC research. Li et al. [\u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e26\u003c/span\u003e] and Wang et al. [\u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e27\u003c/span\u003e] both highlighted AI/ML as an important current/future theme in TNBC research. Although prior bibliometric studies [\u003cspan citationid=\"CR28\" class=\"CitationRef\"\u003e28\u003c/span\u003e] have mapped TNBC research using machine-learning approaches, no bibliometric analysis has yet been dedicated specifically to AI integration within TNBC research, necessitating this study and making it the first bibliometric analysis focusing on AI integration in TNBC research.\u003c/p\u003e\u003cp\u003eThe Scopus database has a broad coverage of peer-reviewed scientific literature, strong citation-tracking features, and compatibility with popular bibliometric software. Therefore, the bibliometric dataset for this study was obtained from the Scopus database, guaranteeing a thorough and reproducible analysis pipeline [\u003cspan citationid=\"CR29\" class=\"CitationRef\"\u003e29\u003c/span\u003e].\u003c/p\u003e\u003cp\u003eThe aim of this study was to use bibliometric scientific mapping and visualization methods to perform a bibliometric and emerging trends analysis on the integration of artificial intelligence in TNBC research. An analysis of the distribution of publications retrieved from the Scopus database was carried out, topics were categorized, and research progress was tracked over time. Additionally, the country contributions and author collaboration were examined with particular emphasis on research topics and emerging research areas. Finally, important future research directions in this area were also highlighted.\u003c/p\u003e"},{"header":"2.0 Methods","content":"\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e\u003ch2\u003e2.1 Bibliometric method and data collection\u003c/h2\u003e\u003cp\u003eThe Scopus database was used to retrieve the data for this study on July 19, 2025 \u003cb\u003e(\u003c/b\u003eFig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e\u003cb\u003e).\u003c/b\u003e This database is widely recognized for its comprehensive coverage and reliable content. It houses numerous publications from reputable publishers. The following search string was used: (\u0026ldquo;Triple Negative Breast cancer*\u0026rdquo; OR \u0026ldquo;Triple-Negative Breast Cancer*\u0026rdquo; OR \u0026ldquo;Triple Negative Breast Neoplasm*\u0026rdquo; OR \u0026ldquo;Triple-Negative Breast Neoplasm*\u0026rdquo; OR \u0026ldquo;ER-Negative PR-Negative HER2-Negative Breast Neoplasm*\u0026rdquo; OR \u0026ldquo;ER-Negative PR-Negative HER2-Negative Breast Cancer*\u0026rdquo;) AND (\"artificial intelligence*\" OR \"deep learn*\" OR \"machine learn*\" OR \"neural network*\" OR \"compu* intelligen*\" OR \"robot*\"). The study considered publications from 2011 to 2025. This timeframe was chosen to reflect the earliest period of AI integration in TNBC research and provide clear insight into the research patterns and trends. The search included titles, abstracts, and keywords, yielding an initial pool of 813 documents in all languages. Manual screening of titles, abstracts, and main text was performed to exclude publications outside the subject area. After excluding 352 articles, only final published articles were retained, resulting in a total of 461 documents for further analysis.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec4\" class=\"Section2\"\u003e\u003ch2\u003e2.2 Data Analysis\u003c/h2\u003e\u003cp\u003eThe extracted dataset, consisting of 461 documents from the Scopus search, was saved in CSV format for further analysis. Bibliometric tools, specifically VOSviewer and the \"Bibliometrix\" R package [\u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e, \u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e], along with Microsoft Excel, were used for analysis and result visualization. VOSviewer software was employed to generate visual maps based on keywords, authors, and their interrelationships. Additionally, Bibliometrix facilitated the illustration of scientific trends and productivity, identifying the most productive authors and influential articles published on the subject. This package encompasses powerful and comprehensive capabilities for bibliometric analysis, comprising analyses of authors, institutions, countries, and regions, as well as journal clustering and temporal trends [\u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e].\u003c/p\u003e\u003cp\u003eKeywords are essential components of scholarly works, playing a crucial role in information retrieval and research endeavors [\u003cspan citationid=\"CR30\" class=\"CitationRef\"\u003e30\u003c/span\u003e]. In this study, VOSviewer was used to analyze all keywords and authors\u0026rsquo; keywords using the full counting method, with a minimum occurrence threshold of 5. Similarly, it was also used to reveal the co-authorship-countries network, where set parameters included a maximum of 25 countries per publication and a minimum of 5 publications per country. Meanwhile, for thematic map and thematic evolution analysis, parameters were set at word counts of 150 and 250, respectively, with a minimum cluster frequency of 5 per thousand documents [\u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e].\u003c/p\u003e\u003c/div\u003e"},{"header":"3.0 Results","content":"\u003cdiv id=\"Sec6\" class=\"Section2\"\u003e\u003ch2\u003e3.1 Descriptive statistics\u003c/h2\u003e\u003cp\u003eThe research output on the integration of artificial intelligence in TNBC research, based on the Scopus database, revealed that 461 documents were published in 248 sources between 2011 and 2025, as shown in Table\u0026nbsp;\u003cspan refid=\"Tab1\" class=\"InternalRef\"\u003e1\u003c/span\u003e. These publications were contributed by 2781 authors. The overall number of publications has increased, with an annual rise of 38.02%. Of the 461 documents, articles were the most abundant, totaling 419. Conference papers constituted 41, while one document was classified as a review paper [\u003cspan citationid=\"CR31\" class=\"CitationRef\"\u003e31\u003c/span\u003e]. However, further investigations revealed that this was actually original research, not a review. It was erroneously classified as a review instead of an article in the Scopus database. Correcting this anomaly brings the total number of articles to 420. The international co-authorship rate stood at 28.2%. Most of the documents were published in English (456), with Chinese (3), Russian (1), and Turkish (1) contributing a minor fraction.\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab1\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eSummary of the main information on the analyzed data\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"2\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eDescription\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eResults\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eMAIN INFORMATION ABOUT DATA\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/th\u003e\u003c/tr\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eTimespan\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003e2011:2025\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eSources (Journals, Books, etc)\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u003cb\u003e248\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eDocuments\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u003cb\u003e461\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eAnnual Growth Rate %\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u003cb\u003e38.02\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eDocument Average Age\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u003cb\u003e2.5\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eAverage citations per doc\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u003cb\u003e20.29\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eReferences\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u003cb\u003e20948\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eDOCUMENT CONTENTS\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eKeywords Plus (ID)\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u003cb\u003e4136\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eAuthor's Keywords (DE)\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u003cb\u003e1088\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eAUTHORS\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eAuthors\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u003cb\u003e2781\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eAuthors of single-authored docs\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u003cb\u003e1\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eAUTHORS COLLABORATION\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eSingle-authored docs\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u003cb\u003e1\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eCo-Authors per Doc\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u003cb\u003e8.66\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eInternational co-authorships %\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u003cb\u003e28.2\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eDOCUMENT TYPES\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eArticle\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u003cb\u003e419\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eConference paper\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u003cb\u003e41\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eReview\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u003cb\u003e1\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eLANGUAGE\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u0026nbsp;\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eEnglish\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u003cb\u003e456\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eChinese\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u003cb\u003e3\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eRussian\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u003cb\u003e1\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eTurkish\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003e\u003cb\u003e1\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec7\" class=\"Section2\"\u003e\u003ch2\u003e3.2 Publication year\u003c/h2\u003e\u003cp\u003eThe publications\u0026rsquo; production over time showed an increase in research output on AI integration in TNBC research within the period under review. As shown in the graph (\u003cb\u003eFig.\u0026nbsp;2A\u003c/b\u003e), there was a steady growth in publications, reflecting progressive interest in this field. From 2011 to 2017, the number of annual publications was under 10. After 2017, the number of publications followed an upward trajectory. The peak period of publication was observed in 2024 with 92 documents. It is important to note that only about seven months were covered in 2025 (January to July 19, when the documents were retrieved). Therefore, it is projected that the current year will have the highest number of annual publications so far in this field. There have been fluctuations in the average citations of scientific publications during the period under review. The highest citations were observed in 2017 and 2013, respectively. The number of annual citations has since declined after 2017 (\u003cb\u003eFig.\u0026nbsp;2B\u003c/b\u003e).\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec8\" class=\"Section2\"\u003e\u003ch2\u003e3.3 Publication by country\u003c/h2\u003e\u003cp\u003eFigure\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e3\u003c/span\u003eA depicts the worldwide distribution of publications on AI integration in TNBC research, with deep blue indicating high publication counts. According to the bar chart, China and the United States lead with 1464 and 1085 publications, respectively. The remaining top ten countries each contributed fewer than 200 publications. The most cited countries on the integration of AI in TNBC research were the United States and China, with a total of 3549 and 3412 citations, respectively, as shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e3\u003c/span\u003eB. India, the Netherlands, the United Kingdom, Korea, France, Germany, Canada, and Austria are the other countries amongst the top ten; however, with fewer than 500 citations each.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec9\" class=\"Section2\"\u003e\u003ch2\u003e3.4 Publication by institutions and sources\u003c/h2\u003e\u003cp\u003eThe outcome of affiliation analysis is shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e4\u003c/span\u003eA, in which the top 10 most relevant affiliations of scientific publications on the integration of artificial intelligence in TNBC research are represented. From the figure, the most relevant affiliation was the University of Texas MD Anderson Cancer Center, with a total of 115 publications. This is followed by Fudan University (52 documents), Harbin Medical University (51), Southern Medical University (51 documents), and Sun Yat-Sen University Cancer Center (48 documents). Others include Harvard Medical School (39 documents), Mayo Clinic (39 documents), Memorial Sloan Kettering Cancer Center (38 documents), Radboud University Medical Center (38 documents), and Fudan University Shanghai (36 documents).\u003c/p\u003e\u003cp\u003eFigure\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e4\u003c/span\u003eB shows the top 10 most relevant sources out of the 248 sources on AI integration in TNBC research, ranked according to the number of documents. \u003cem\u003eCancers\u003c/em\u003e was the most relevant source in which AI in TNBC research was published, with a total of 24 documents. This is followed by \u003cem\u003eScientific Reports\u003c/em\u003e (16), \u003cem\u003eFrontiers in Oncology\u003c/em\u003e (14), and \u003cem\u003eFrontiers in Immunology\u003c/em\u003e (12). All other relevant sources within the top 10 each had fewer than 10 documents published. The quintet of \u003cem\u003eBreast Cancer Research and Treatment, Computers in Biology and Medicine\u003c/em\u003e, \u003cem\u003eEuropean Radiology\u003c/em\u003e, \u003cem\u003eInternational Journal of Cancer\u003c/em\u003e, and \u003cem\u003eNature Communications\u003c/em\u003e each had 7, while \u003cem\u003eAcademic Radiology\u003c/em\u003e had 6.\u003c/p\u003e\u003cp\u003eFigure\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e4\u003c/span\u003eC depicts the impact of the sources with respect to the h-index. \u003cem\u003eCancers\u003c/em\u003e, with an h-index of 10, showed the highest impact, followed by \u003cem\u003eFrontiers in Oncology\u003c/em\u003e (h-index of 8) and \u003cem\u003eFrontiers in Immunology\u003c/em\u003e (h-index of 7). \u003cem\u003eEuropean Radiology\u003c/em\u003e and \u003cem\u003eScientific Reports\u003c/em\u003e both had an h-index of 6, while \u003cem\u003eComputer in Biology and Medicine\u003c/em\u003e, \u003cem\u003eInternational Journal of Cancer\u003c/em\u003e, \u003cem\u003eJournal of Magnetic Resonance\u003c/em\u003e, and \u003cem\u003eNature Communications\u003c/em\u003e each had an h-index of 5. \u003cem\u003eBreast Cancer Research and Treatment\u003c/em\u003e concludes the top 10 with an h-index of 4.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec10\" class=\"Section2\"\u003e\u003ch2\u003e3.5 Most productive authors\u003c/h2\u003e\u003cp\u003eWithin the reviewed period, 2,781 authors contributed to publications on the integration of AI in TNBC research, with only one producing a single-authored document. The top-producing authors, according to the number of documents, are presented in Fig.\u0026nbsp;\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e5\u003c/span\u003eA. Both Zhang J and Zhang Y top the list with 20 publications each. They are followed by Wang Y, Zhang X, Wang X, Li X, and Li Y with 19, 18, 17, 16, and 14 documents, respectively. Other relevant authors include Li J, Wang L, and Wang S, with 13 documents each.\u003c/p\u003e\u003cp\u003eFigure\u0026nbsp;\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e5\u003c/span\u003eB presents the productivity of the top 10 productive authors from 2011 to 2025. All authors are currently productively active. Notably, some authors share the same period of productivity- Zhang J and Zhang Y (2021\u0026ndash;2025), while Wang Y, Zhang X, Li Y, Li J, and Wang S also share the same period of 2019\u0026ndash;2025. Wang X shows a different productivity pattern (2018\u0026ndash;2025), and so does Li X (2020\u0026ndash;2025). Wang L was the only author represented with a publication start year of 2017.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cp\u003eTable\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e presents the impact ranking of relevant authors and outlines parameters such as h-index, g-index, m-index, total citations, number of publications (NP), and publication start year (PY start). Among these authors, Wang X was the most impactful based on h-index and total citations, with an h-index of 10 and TC of 796. In contrast, Zhang Y leads when considering g-index (20), m-index (1.8), and number of publications (20). Notably, Wang X was the only author with a publication start year of 2018. Across all authors, four publication start years were identified, namely 2018, 2019, 2020, and 2021.\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab2\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eThe top 10 most impactful authors on AI integration in TNBC research\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"7\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eAuthor\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eh_index\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eg_index\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003em_index\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c5\"\u003e\u003cp\u003eTC\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c6\"\u003e\u003cp\u003eNP\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c7\"\u003e\u003cp\u003ePY_start\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eWANG X\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e10\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e17\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e1.25\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e796\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e17\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e2018\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eZHANG Y\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e9\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e20\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e1.8\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e764\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e20\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e2021\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eLIN Y\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e8\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e10\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e1.333\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e447\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e10\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e2020\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eWANG Y\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e8\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e16\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e1.143\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e268\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e19\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e2019\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eLI H\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e7\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e11\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e1.4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e235\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e11\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e2021\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eLI J\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e7\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e13\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e222\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e13\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e2019\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eLI X\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e7\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e16\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e1.167\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e278\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e16\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e2020\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eLIU Y\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e7\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e11\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e145\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e11\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e2019\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eZHANG X\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e7\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e17\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e301\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e18\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e2019\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003eHUANG Y\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e6\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e10\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e355\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c6\"\u003e\u003cp\u003e10\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c7\"\u003e\u003cp\u003e2020\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec11\" class=\"Section2\"\u003e\u003ch2\u003e3.6 Top most cited documents\u003c/h2\u003e\u003cp\u003eTable\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e presents the top ten most cited documents on the integration of AI in TNBC research. Keren et al. [\u003cspan citationid=\"CR32\" class=\"CitationRef\"\u003e32\u003c/span\u003e] leads as the most cited document, with 714 citations. This is followed by Braman et al. [\u003cspan citationid=\"CR33\" class=\"CitationRef\"\u003e33\u003c/span\u003e], He et al. [\u003cspan citationid=\"CR34\" class=\"CitationRef\"\u003e34\u003c/span\u003e], and Zou et al. [\u003cspan citationid=\"CR35\" class=\"CitationRef\"\u003e35\u003c/span\u003e] with 516, 399, and 277 citations, respectively. Others include Meyer et al. [\u003cspan citationid=\"CR36\" class=\"CitationRef\"\u003e36\u003c/span\u003e], Saha [\u003cspan citationid=\"CR37\" class=\"CitationRef\"\u003e37\u003c/span\u003e], Xiao et al. [\u003cspan citationid=\"CR38\" class=\"CitationRef\"\u003e38\u003c/span\u003e], Mostavi et al. [\u003cspan citationid=\"CR39\" class=\"CitationRef\"\u003e39\u003c/span\u003e], Wu and Hicks [\u003cspan citationid=\"CR40\" class=\"CitationRef\"\u003e40\u003c/span\u003e], and Cain et al. [\u003cspan citationid=\"CR41\" class=\"CitationRef\"\u003e41\u003c/span\u003e] with document citations of 232, 218, 213, 179, 174, and 148, respectively.\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab3\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 3\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eThe top ten most cited documents on the integration of AI in TNBC research\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"5\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eS/No\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eAuthor\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eTitle\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003eJournal\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c5\"\u003e\u003cp\u003eTotal Citations\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eKeren et al. [\u003cspan citationid=\"CR32\" class=\"CitationRef\"\u003e32\u003c/span\u003e]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eA structured tumor-immune microenvironment in triple negative breast cancer revealed by multiplexed ion beam imaging\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eCell\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e714\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eBraman et al. [\u003cspan citationid=\"CR33\" class=\"CitationRef\"\u003e33\u003c/span\u003e]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eIntratumoral and peritumoral radiomics for the pretreatment prediction of pathological complete response to neoadjuvant chemotherapy based on breast DCE-MRI\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eBreast cancer research\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e516\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eHe et al. [\u003cspan citationid=\"CR34\" class=\"CitationRef\"\u003e34\u003c/span\u003e]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eClassification of triple-negative breast cancers based on Immunogenomic profiling\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eJournal of Experimental \u0026amp; Clinical Cancer Research\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e399\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eZou et al. [\u003cspan citationid=\"CR35\" class=\"CitationRef\"\u003e35\u003c/span\u003e]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eLeveraging diverse cell-death patterns to predict the prognosis and drug sensitivity of triple-negative breast cancer patients after surgery\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eInternational journal of surgery\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e277\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e5\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eMeyer et al. [\u003cspan citationid=\"CR36\" class=\"CitationRef\"\u003e36\u003c/span\u003e]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eThe receptor AXL diversifies EGFR signaling and limits the response to EGFR-targeted inhibitors in triple-negative breast cancer cells\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eScience signalling\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e232\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e6\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eSaha [\u003cspan citationid=\"CR37\" class=\"CitationRef\"\u003e37\u003c/span\u003e]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eA machine learning approach to radiogenomics of breast cancer: A study of 922 subjects and 529 dce-mri features\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eBritish journal of cancer\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e218\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e7\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eXiao et al. [\u003cspan citationid=\"CR38\" class=\"CitationRef\"\u003e38\u003c/span\u003e]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eComprehensive metabolomics expands precision medicine for triple-negative breast cancer\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eCell research\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e213\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e8\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eMostavi et al. [\u003cspan citationid=\"CR39\" class=\"CitationRef\"\u003e39\u003c/span\u003e]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eConvolutional neural network models for cancer type prediction based on gene expression\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eBMC medical genomics\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e179\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e9\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eWu and Hicks [\u003cspan citationid=\"CR40\" class=\"CitationRef\"\u003e40\u003c/span\u003e]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eBreast cancer type classification using machine learning\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eJournal of personalized medicine\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e174\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e10\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c2\"\u003e\u003cp\u003eCain et al. [\u003cspan citationid=\"CR41\" class=\"CitationRef\"\u003e41\u003c/span\u003e]\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c3\"\u003e\u003cp\u003eMultivariate machine learning models for prediction of pathologic response to neoadjuvant therapy in breast cancer using MRI features: a study using an independent validation set\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c4\"\u003e\u003cp\u003eBreast cancer research and treatment\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c5\"\u003e\u003cp\u003e148\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003e\u003cb\u003eTC -Total citations, NP- Number of publications, PY_start- Publication year start\u003c/b\u003e\u003c/p\u003e\u003cp\u003e\u003cem\u003e3.7 Keywords co-occurrence network analysis\u003c/em\u003e\u003c/p\u003e\u003cp\u003eFollowing the analysis with VOSviewer, the network map of all keyword clusters is shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig5\" class=\"InternalRef\"\u003e6\u003c/span\u003eA. Different clusters could be identified from the network map, with different keywords shown according to the occurrence. Cluster 1, depicted in red, is made up of highly occurring keywords such as \u003cem\u003etriple negative breast cancer\u003c/em\u003e, \u003cem\u003emachine learning\u003c/em\u003e, \u003cem\u003egenetics\u003c/em\u003e, and \u003cem\u003egene expression\u003c/em\u003e. \u003cem\u003eBreast cancer, breast tumor, cohort analysis, human tissue, major clinical study\u003c/em\u003e, and \u003cem\u003epathology\u003c/em\u003e were among the most occurring keywords in cluster 2 (green). The third cluster, represented in blue, is composed of diverse keywords with \u003cem\u003edeep learning, diseases, algorithm, and artificial intelligence\u003c/em\u003e as the keywords with high frequency. \u003cem\u003eTumor associated leukocyte, tumor recurrence, tumor-infiltrating lymphocytes\u003c/em\u003e, and the \u003cem\u003eKaplan-Meier method\u003c/em\u003e make up the topmost occurring concepts in cluster 4, depicted in yellow. The fifth cluster (purple) has the following keywords in high occurrence, namely, \u003cem\u003escoring system, machine learning algorithm, classification\u003c/em\u003e, and \u003cem\u003eleast absolute shrinkage\u003c/em\u003e and \u003cem\u003eselection operator.\u003c/em\u003e Cluster 6 (turquoise) is made up of only two keywords: \u003cem\u003eearly detection of cancer\u003c/em\u003e and \u003cem\u003eearly cancer diagnosis.\u003c/em\u003e\u003c/p\u003e\u003cp\u003eFigure\u0026nbsp;\u003cspan refid=\"Fig5\" class=\"InternalRef\"\u003e6\u003c/span\u003eB presents the authors\u0026rsquo; keyword co-occurrence network. Different clusters could be identified from the network map, with different keywords shown according to the occurrence. Cluster 1, depicted in red, is made up of highly occurring keywords such as \u003cem\u003etriple negative breast cancer\u003c/em\u003e, \u003cem\u003emachine learning\u003c/em\u003e, \u003cem\u003ebiomarker\u003c/em\u003e, and \u003cem\u003eclassification\u003c/em\u003e. \u003cem\u003eBreast cancer, artificial intelligence, neoadjuvant chemotherapy\u003c/em\u003e, and \u003cem\u003epathological complete response\u003c/em\u003e were among the most occurring keywords in cluster 2 (green). The third cluster, represented in blue, is composed of several keywords, with \u003cem\u003edeep learning, prognosis, triple-negative breast cancer, and nuclei segmentation\u003c/em\u003e as the keywords with high frequency. \u003cem\u003eCancer, digital pathology, histopathology\u003c/em\u003e, and \u003cem\u003econvoluted neural networks\u003c/em\u003e make up the topmost occurring keywords in cluster 4, depicted in yellow. The fifth cluster (purple) has the following keywords in high occurrence, namely, \u003cem\u003ebreast neoplasms, magnetic resonance imaging, radiomics\u003c/em\u003e, and \u003cem\u003emolecular subtypes.\u003c/em\u003e Cluster 6 (turquoise) is made up of the following keywords: \u003cem\u003echemotherapy, immunotherapy, tumor micro-environment\u003c/em\u003e, and \u003cem\u003etriple negative breast cancer.\u003c/em\u003e Finally, cluster 7 (orange) is made up of only 2 keywords-\u003cem\u003emolecular subtype\u003c/em\u003e and \u003cem\u003eultrasound\u003c/em\u003e.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec12\" class=\"Section2\"\u003e\u003ch2\u003e3.8 Thematic evolution and trend topics\u003c/h2\u003e\u003cp\u003eThe thematic map of authors\u0026rsquo; keywords is presented in Fig.\u0026nbsp;\u003cspan refid=\"Fig6\" class=\"InternalRef\"\u003e7\u003c/span\u003eA, which is divided into four quadrants. The bottom left quadrant consists of emerging or declining themes, such as \u003cem\u003egraph neural network(s).\u003c/em\u003e Along the border between the bottom left (emerging or declining) and the top left (niche) quadrants, concepts like \u003cem\u003etnbc subtypes\u003c/em\u003e, \u003cem\u003eartificial intelligence (ai)\u003c/em\u003e, and \u003cem\u003edeep neural network\u003c/em\u003e are positioned, indicating their transition from one theme type to another. The basic themes in the bottom right quadrant include groupings such as \u003cem\u003emachine learning, triple-negative breast cancer, artificial intelligence\u003c/em\u003e; \u003cem\u003ebreast cancer, deep learning, radiomics\u003c/em\u003e; and \u003cem\u003enuclei segmentation, histopathology images, convolutional neural networks\u003c/em\u003e. At the top left, the niche themes comprise concepts like \u003cem\u003eclass, classifier evaluation\u003c/em\u003e, \u003cem\u003ediseases; breast cancer subtypes\u003c/em\u003e, \u003cem\u003edifferential gene expression, ensemble learning;\u003c/em\u003e and \u003cem\u003ecell segmentation, feature extraction\u003c/em\u003e in respective clusters. The top right quadrant contains the motor themes, with examples such as \u003cem\u003eattention mechanism, multi-omics data, graph convolutional network\u003c/em\u003e; and \u003cem\u003eimmune checkpoint inhibitor, machine learning algorithm, cancer-associated fibroblasts\u003c/em\u003e in unique clusters.\u003c/p\u003e\u003cp\u003eFigure\u0026nbsp;\u003cspan refid=\"Fig6\" class=\"InternalRef\"\u003e7\u003c/span\u003eB provides the thematic evolution based on the author\u0026rsquo;s keywords on the integration of AI in TNBC research. Between 2011 and 2017, \u003cem\u003ebreast cancer\u003c/em\u003e and \u003cem\u003emachine learning\u003c/em\u003e were the dominant themes. From the period of 2018 to 2022, \u003cem\u003ebioinformatics\u003c/em\u003e, \u003cem\u003ebiomarkers, breast cancer, computer-aided diagnosis, nuclei segmentation, precision medicine, segmentation, single-cell rna-seq, tnbc, triple negative breast cancer, tumor microenvironment\u003c/em\u003e became the most dominant themes. However, from 2023 up to the current period, the most dominant authors\u0026rsquo; keywords were \u003cem\u003ebreast cancer, computer-aided diagnosis, digital pathology, feature selection, histopathology, immune infiltration, machine learning, subtype, racial disparity, support vector machine, survival analysis and triple-negative breast cancer (tnbc)\u003c/em\u003e.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003cp\u003eFigure\u0026nbsp;\u003cspan refid=\"Fig7\" class=\"InternalRef\"\u003e8\u003c/span\u003e shows the trends in topic and research concepts based on the integration of AI in TNBC research. The size of the dot represented its frequency, while the horizontal line represented its period in years. The topics span different periods, with notable trends for each year indicated by the dot. From the figure, the trending topics between 2020 and 2022 included \u003cem\u003ebioinformatics, molecular subtypes, biomarker, digital pathology\u003c/em\u003e, and \u003cem\u003etriple negative breast cancer\u003c/em\u003e. However, from 2023 up to 2024, the trending topics are \u003cem\u003etriple-negative breast cancer, machine learning, breast cancer, tnbc, magnetic resonance imaging\u003c/em\u003e, and \u003cem\u003eartificial intelligence.\u003c/em\u003e\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec13\" class=\"Section2\"\u003e\u003ch2\u003e3.9 Countries and authors\u0026rsquo; collaboration network\u003c/h2\u003e\u003cp\u003eFrom Table\u0026nbsp;\u003cspan refid=\"Tab4\" class=\"InternalRef\"\u003e4\u003c/span\u003e, China, the United States, and India were the top 3 countries in terms of relevance estimated by the corresponding author\u0026rsquo;s country. Looking more closely at publication types, China, the USA, India, Korea, and Canada had more single-country publications (SCP) than multiple-country publications (MCP). In contrast, the UK, Georgia, Germany, France, and the Netherlands had more multiple-country publications (MCP) than single-country publications (SCP). Furthermore, while India, China, and Korea dominated in terms of a higher percentage of SCP in relation to total publications, the Netherlands led in having a higher MCP relative to total publications.\u003c/p\u003e\u003cp\u003e\u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab4\" border=\"1\"\u003e\u003ccaption language=\"En\"\u003e\u003cdiv class=\"CaptionNumber\"\u003eTable 4\u003c/div\u003e\u003cdiv class=\"CaptionContent\"\u003e\u003cp\u003eMost relevant countries of publications based on the corresponding author\u003c/p\u003e\u003c/div\u003e\u003c/caption\u003e\u003ccolgroup cols=\"6\"\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e\u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e\u003cdiv align=\"left\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e\u003cthead\u003e\u003ctr\u003e\u003cth align=\"left\" colname=\"c1\"\u003e\u003cp\u003eCountry\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c2\"\u003e\u003cp\u003eArticles\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c3\"\u003e\u003cp\u003eSCP\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c4\"\u003e\u003cp\u003eMCP\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c5\"\u003e\u003cp\u003e% SCP to total publications\u003c/p\u003e\u003c/th\u003e\u003cth align=\"left\" colname=\"c6\"\u003e\u003cp\u003e% MCP to total publications\u003c/p\u003e\u003c/th\u003e\u003c/tr\u003e\u003c/thead\u003e\u003ctbody\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eCHINA\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e173\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e151\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e22\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e87.3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e12.7\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eUSA\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e91\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e59\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e32\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e64.8\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e35.2\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eINDIA\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e29\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e28\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e96.6\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e3.4\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eKOREA\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e21\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e18\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e85.7\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e14.3\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eUNITED KINGDOM\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e11\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e7\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e36.4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e63.6\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eGEORGIA\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e10\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e6\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e40\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e60\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eGERMANY\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e10\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e7\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e30\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e70\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eFRANCE\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e9\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e5\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e44.4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e55.6\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eNETHERLANDS\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e7\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e1\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e6\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e14.3\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e85.7\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003ctr\u003e\u003ctd align=\"left\" colname=\"c1\"\u003e\u003cp\u003e\u003cb\u003eCANADA\u003c/b\u003e\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e\u003cp\u003e6\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e\u003cp\u003e4\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"char\" char=\".\" colname=\"c4\"\u003e\u003cp\u003e2\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c5\"\u003e\u003cp\u003e66.7\u003c/p\u003e\u003c/td\u003e\u003ctd align=\"left\" colname=\"c6\"\u003e\u003cp\u003e33.3\u003c/p\u003e\u003c/td\u003e\u003c/tr\u003e\u003c/tbody\u003e\u003c/colgroup\u003e\u003c/table\u003e\u003c/div\u003e\u003c/p\u003e\u003cp\u003eSix (6) clusters can be seen in the network of co-authorship country analysis presented in Fig.\u0026nbsp;\u003cspan refid=\"Fig8\" class=\"InternalRef\"\u003e9\u003c/span\u003eA. The largest cluster, which is cluster 1 depicted in red, is made up of countries like Australia, Belgium, India, the Netherlands, Poland, Saudi Arabia, and Sweden. Austria, France, Italy, Spain, the United Kingdom, and the United States make up cluster 2 depicted in green. While cluster 3 (blue) is made up of China and Taiwan, cluster 4 (yellow) comprises Iran and Canada. Both cluster 5 (purple) and cluster 6 (turquoise) are made up of two countries each-Norway and Brazil, and Germany and South Korea, respectively.\u003c/p\u003e\u003cp\u003eFigure\u0026nbsp;\u003cspan refid=\"Fig8\" class=\"InternalRef\"\u003e9\u003c/span\u003eB presents the authors\u0026rsquo; collaboration network. Three (3) clusters can be seen in the figure and are loosely connected together. Aneja R and Bhattarai S are present in cluster 1 (red). Cluster 2 (green) is the largest cluster and comprises authors such as Wang Y, Wang X, Zhang X, Zhang J, and Zhang Y. Lastly, cluster 3 (blue) has Yang W, Sun J, Chen H, Xu Z, and Valero V.\u003c/p\u003e\u003cp\u003e\u003c/p\u003e\u003c/div\u003e"},{"header":"4.0 Discussion","content":"\u003cdiv id=\"Sec15\" class=\"Section2\"\u003e\u003ch2\u003e4.1 Research growth\u003c/h2\u003e\u003cp\u003eAn in-depth bibliometric analysis was conducted on the research output on the integration of artificial intelligence in TNBC research from 2011 to 2025 using scientific literature records from the Scopus database. Particular emphasis was placed on the field's worldwide research trends, which included research hotspots, key contributors, conceptual development, and anticipated future research directions. The findings showed that knowledge in this area has advanced quickly during the period under review. The annual growth rate (38.02%) indicates that the body of knowledge is growing steadily with novel concepts, investigations, and deductions introduced annually. This further suggests that the discipline is dynamic. Similarly, the international co-authorship percentage (28.20%) highlights considerable global networking in generating scientific information on the integration of artificial intelligence in TNBC research. This indicates that international collaboration is responsible for approximately one-third of publications on the integration of AI in TNBC research, thereby increasing the diversity of viewpoints and expertise invested in its research. In line with best practices in bibliometrics, this study considered only original research articles and conference papers, given their importance in AI-related fields, as these represent validated, novel scientific contributions, while excluding reviews, editorials, and letters that primarily synthesize or comment on existing knowledge [\u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e, \u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e, \u003cspan citationid=\"CR42\" class=\"CitationRef\"\u003e42\u003c/span\u003e].\u003c/p\u003e\u003cp\u003eResults indicate that there has been growth in research interests on the integration of AI in TNBC research, leading to an annual increase in publications. This growth in research is similar to that reported by [\u003cspan citationid=\"CR43\" class=\"CitationRef\"\u003e43\u003c/span\u003e], who observed a general exponential rise in AI-related publications across scientific disciplines, and by [\u003cspan citationid=\"CR44\" class=\"CitationRef\"\u003e44\u003c/span\u003e], who highlighted an increasing trend of AI applications within breast cancer research. Likewise, recent bibliometric analyses in oncology, [\u003cspan citationid=\"CR45\" class=\"CitationRef\"\u003e45\u003c/span\u003e, \u003cspan citationid=\"CR46\" class=\"CitationRef\"\u003e46\u003c/span\u003e] also documented steady growth in the adoption of AI-driven methodologies, indicating that the surge observed in TNBC aligns with broader global trends in AI integration within medical research.\u003c/p\u003e\u003cp\u003eThe yearly average citations of scientific publications on AI integration in TNBC research (\u003cb\u003eFig.\u0026nbsp;2B\u003c/b\u003e) exhibited notable fluctuations, with peaks observed in 2013 and 2017. These increases are attributable to influential studies that shaped subsequent research directions and citation patterns. Since 2017, average annual citations have declined, likely due to citation dilution resulting from a rapid increase in publication volume, which disperses citations across more articles. Additional contributing factors include a time-lag effect, as recent publications have not yet accumulated substantial citations, and a shift in focus toward emerging subfields such as explainable AI, multi-omics integration, and deep learning within oncology. This trend is consistent with bibliometric analyses in related disciplines, which indicate that publication surges often correspond with temporary decreases in average annual citations [\u003cspan citationid=\"CR43\" class=\"CitationRef\"\u003e43\u003c/span\u003e, \u003cspan citationid=\"CR44\" class=\"CitationRef\"\u003e44\u003c/span\u003e, \u003cspan citationid=\"CR46\" class=\"CitationRef\"\u003e46\u003c/span\u003e, \u003cspan citationid=\"CR47\" class=\"CitationRef\"\u003e47\u003c/span\u003e].\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec16\" class=\"Section2\"\u003e\u003ch2\u003e4.2 Influential countries, affiliations and sources\u003c/h2\u003e\u003cp\u003eThe USA and China lead AI-integrated TNBC research due to large investments and structural advantages. The USA supports cancer research with significant funding for precision oncology and therapeutics, along with access to open resources such as TCGA and TCIA, which enable AI modeling. China takes advantage of its strong policy support, advanced digital infrastructures, and translational experience, resulting in high publication output [\u003cspan additionalcitationids=\"CR49\" citationid=\"CR48\" class=\"CitationRef\"\u003e48\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR50\" class=\"CitationRef\"\u003e50\u003c/span\u003e]. A bibliometric study on the tumor microenvironment in TNBC confirmed that the USA and China are the top contributors in terms of publication volume and citation impact [\u003cspan citationid=\"CR51\" class=\"CitationRef\"\u003e51\u003c/span\u003e]. Similarly, a bibliometric analysis of deep learning in cancer research found that China leads in publication volume, while the USA produces higher-impact, widely cited work due to global collaborations and research visibility [\u003cspan citationid=\"CR46\" class=\"CitationRef\"\u003e46\u003c/span\u003e]. The aggressive nature and lack of targeted therapies for TNBC make it a global research focus, giving both countries strong motivation to lead AI innovation in this area [\u003cspan citationid=\"CR52\" class=\"CitationRef\"\u003e52\u003c/span\u003e].\u003c/p\u003e\u003cp\u003eAffiliations are useful in bibliometric analyses for evaluating research trends and institutional output in a given body of knowledge. Authors usually conduct their research from institutions or organizations to which they are affiliated. The top 10 most relevant affiliations for AI in TNBC research are equally concentrated in the USA (50%) and China (50%) (Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e4\u003c/span\u003eA). These are the top two nations with high research output and citations on this topic (Fig.\u0026nbsp;\u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e3\u003c/span\u003eA and \u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e3\u003c/span\u003eB). Institutions from the USA include the University of Texas MD Anderson Cancer Center, Harvard Medical School, Mayo Clinic, Memorial Sloan Kettering Cancer Center, and Radboud University Medical Center. Together, they contributed 269 documents, representing 53.06% of the top ten affiliations' total publications. Similarly, Chinese institutions such as Fudan University, Harbin Medical University, Southern Medical University, Sun Yat-sen University Cancer Center, and Fudan University Shanghai contributed 238 documents, making up 46.94% of the total. This result highlights the geographic dominance of scientific leadership in this field. Both the USA and China have prioritized and invested heavily in artificial intelligence and oncology research. These investments have produced robust institutional frameworks, excellent access to comprehensive datasets, and funding structures that encourage interdisciplinary collaboration.\u003c/p\u003e\u003cp\u003eScientific information is usually published in journals and conference proceedings. These serve as primary channels of scholarly communication. From Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e4\u003c/span\u003eB, \u003cem\u003eCancers\u003c/em\u003e was the most relevant source for publishing research on the integration of AI in TNBC. This suggests that it is a prominent venue in this emerging field. It was followed by \u003cem\u003eScientific Reports\u003c/em\u003e, \u003cem\u003eFrontiers in Oncology\u003c/em\u003e, and \u003cem\u003eFrontiers in Immunology\u003c/em\u003e, indicating that much of this research appears in open-access sources. This maximizes research visibility and global reach. The presence of \u003cem\u003eFrontiers in Immunology\u003c/em\u003e highlights the significance of artificial intelligence in immuno-oncology. This focus is particularly relevant for TNBC, which lacks hormone receptors and depends on immune-based biomarkers and predictive modeling for diagnosis and treatment. Other journals, such as \u003cem\u003eBreast Cancer Research and Treatment\u003c/em\u003e, \u003cem\u003eComputers in Biology and Medicine, European Radiology, and Academic Radiology\u003c/em\u003e, show that research covers cancer-specific, imaging, and computational disciplines. This underlines the field's multidisciplinary scope. The inclusion of \u003cem\u003eNature Communications\u003c/em\u003e and the \u003cem\u003eInternational Journal of Molecular Sciences\u003c/em\u003e shows that AI in TNBC is gaining attention in high-impact, general science, and applied informatics journals further reflecting its growing scientific significance.\u003c/p\u003e\u003cp\u003eNinety per cent (90%) of the most relevant sources were also present as journals with the highest impact according to their h-impact measure, re-enforcing the fact that these journals not only publish high volumes but also carry significant scientific influence in this field. \u003cem\u003eAcademic Radiology\u003c/em\u003e did not make the list of the top 10 most impactful sources in which the integration of AI in TNBC research was published; instead, the \u003cem\u003eJournal of Magnetic Resonance Imaging\u003c/em\u003e (h-impact 5) appeared in its place. \u003cem\u003eCancers\u003c/em\u003e was also the most impactful journal in which AI in TNBC research was published, with an h-impact of 10. The inclusion of additional open-access journals, such as \u003cem\u003eScientific Reports, Frontiers in Oncology, and Frontiers in Immunology\u003c/em\u003e, supports the trend illustrated in Fig.\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e4\u003c/span\u003eB toward broader dissemination and accessibility of artificial intelligence (AI) integration in triple-negative breast cancer research. This trend is significant for the multidisciplinary nature of this field, which requires rapid information exchange and collaboration across disciplines. Other journals with comparatively high impact factors include \u003cem\u003eEuropean Radiology, Computers in Biology and Medicine, International Journal of Cancer Research, Nature Communications\u003c/em\u003e, and \u003cem\u003eBreast Cancer Research and Treatment\u003c/em\u003e. The prominence of specialized open-access oncology journals indicates that these publications are currently influencing the development of AI in TNBC research more substantially than traditional high-impact generalist journals.\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec17\" class=\"Section2\"\u003e\u003ch2\u003e4.3 Influential authors\u003c/h2\u003e\u003cp\u003eFigure\u0026nbsp;\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e5\u003c/span\u003eA provides a graphical summary of the most productive authors based on the number of published documents. Zhang J and Zhang Y each stood out as the leading authors, followed by Wang Y, Zhang X, Wang X, and Li X. When analyzing Fig.\u0026nbsp;\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e5\u003c/span\u003eA, it becomes evident that the leading authors in artificial intelligence (AI) integration in triple-negative breast cancer (TNBC) research are primarily affiliated with institutions in China. This concentration likely results from significant national investment in AI and oncology, as well as from access to extensive patient datasets and established collaborative networks among major Chinese cancer research centers such as Fudan University, Sun Yat-Sen University Cancer Center, Shanghai Jiao Tong University, and the Chinese Academy of Sciences. These findings indicate that the most productive authors are integrated within institutional clusters and collaborative research networks in China [\u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e, \u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e26\u003c/span\u003e, \u003cspan citationid=\"CR28\" class=\"CitationRef\"\u003e28\u003c/span\u003e].\u003c/p\u003e\u003cp\u003eAnalysis of the top authors' productivity period (Fig.\u0026nbsp;\u003cspan refid=\"Fig4\" class=\"InternalRef\"\u003e5\u003c/span\u003eB) indicates that all top 10 authors remain active in AI integration in TNBC research. Wang L has the longest publication span, beginning in 2017, followed by Wang X, who began publishing in 2018. A cluster of authors, including Wang S, Li J, Li Y, Zhang X, and Wang Y, commenced publishing in 2019. Zhang Y and Zhang J began their contributions in 2021, while Li X started in 2020. The publication period for these leading authors (2017\u0026ndash;2025) aligns with the observed growth in AI integration within TNBC research (\u003cb\u003eFig.\u0026nbsp;2A\u003c/b\u003e), which suggests that these individuals are among the foundational contributors to this field.\u003c/p\u003e\u003cp\u003eSeveral indicators are commonly used in bibliometrics to measure researchers\u0026rsquo; productivity and impact over time. The h-index, proposed by Hirsch [\u003cspan citationid=\"CR53\" class=\"CitationRef\"\u003e53\u003c/span\u003e], measures both the productivity and citation impact of a researcher. It balances quantity and quality by ignoring both lowly cited papers and the disproportionately high influence of a single publication. The g-index, introduced by Egghe [\u003cspan citationid=\"CR54\" class=\"CitationRef\"\u003e54\u003c/span\u003e], improves upon the h-index by giving more weight to highly cited publications. Thus, it recognizes the impact of exceptionally influential papers that the h-index might overlook. The m-index (or m-quotient) is derived by dividing the h-index by the number of years since the researcher\u0026rsquo;s first publication. It normalizes the h-index for academic age, allowing fairer comparisons between early-career and senior researchers [\u003cspan citationid=\"CR53\" class=\"CitationRef\"\u003e53\u003c/span\u003e]. Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e highlights the top 10 most impactful authors in the integration of AI in TNBC research based on h-index. Among them, Wang X emerged topmost with the highest h-index (10), total citations (TC\u0026thinsp;=\u0026thinsp;796), and an early research start year (2018), suggesting consistent productivity and citation visibility over time. Interestingly, despite starting more recently (2021), Zhang Y demonstrates the strongest research momentum, with the highest g-index (20) and m-index (1.8). This indicates rapid accumulation of both publications (NP\u0026thinsp;=\u0026thinsp;20) and citations (TC\u0026thinsp;=\u0026thinsp;764) within a short span, reflecting high-impact and possibly trend-setting work. Strong relative productivity adjusted for career length is also demonstrated by other authors, such as Lin Y (m-index\u0026thinsp;=\u0026thinsp;1.333) and Li H (m-index\u0026thinsp;=\u0026thinsp;1.4), indicating that their contributions are highly impactful given how recently they entered this field. Authors such as Li J and Liu Y, on the other hand, have lower m-indices (1.0) and moderate citation counts (TC\u0026thinsp;=\u0026thinsp;222 and 145, respectively), indicating a stable but slower impact compared to their colleagues. About 60% of the top 10 most impactful authors are also among the most productive authors, implying that they not only have high-volume publications, but these publications are equally impactful within this field. This result also corroborates the fact that the most impactful authors on the integration of AI in TNBC research are affiliated with institutions in China, aligning with broader trends where China and the USA lead in AI-driven oncology research output. The data also points to a relatively recent spike in research activity, with the majority of authors starting their contributions after 2018, highlighting the fact that AI applications in TNBC remain an emerging but rapidly expanding field.\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec18\" class=\"Section2\"\u003e\u003ch2\u003e4.4 Influential documents\u003c/h2\u003e\u003cp\u003eThe most cited studies that have influenced the use of artificial intelligence in triple-negative breast cancer research are shown in Table\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e. The main study topics and approaches that have garnered a lot of scholarly interest are highlighted in these citations. Published in \u003cem\u003eCell\u003c/em\u003e, [\u003cspan citationid=\"CR32\" class=\"CitationRef\"\u003e32\u003c/span\u003e] is the most cited publication. The tumor-immune microenvironment in TNBC was mapped using multiplexed ion beam imaging in this study, providing important information about immunological heterogeneity that supports existing AI-based predictive modeling. This shows how AI-driven spatial biology approaches have provided foundational knowledge for TNBC research. The second most influential study [\u003cspan citationid=\"CR33\" class=\"CitationRef\"\u003e33\u003c/span\u003e], was the first to use DCE-MRI data to predict therapy response using radiomics. The early focus on radiomics and imaging-based AI applications in TNBC prognosis and therapy response was also highlighted by [\u003cspan citationid=\"CR41\" class=\"CitationRef\"\u003e41\u003c/span\u003e], who validated multivariate machine learning MRI models. In terms of genomics, [\u003cspan citationid=\"CR34\" class=\"CitationRef\"\u003e34\u003c/span\u003e] used immunogenomic profiling to classify TNBC subtypes, while [\u003cspan citationid=\"CR39\" class=\"CitationRef\"\u003e39\u003c/span\u003e, \u003cspan citationid=\"CR40\" class=\"CitationRef\"\u003e40\u003c/span\u003e] showed the value of machine learning and convolutional neural networks in gene expression-based TNBC classification. The shift in AI applications from imaging to multi-omics and molecular data integration is highlighted by these contributions. Recent research shows that AI is becoming increasingly relevant in precision medicine, where metabolomics, cell-death signatures, and drug sensitivity prediction are being utilized for personalized therapy. Examples of these studies include [\u003cspan citationid=\"CR35\" class=\"CitationRef\"\u003e35\u003c/span\u003e, \u003cspan citationid=\"CR38\" class=\"CitationRef\"\u003e38\u003c/span\u003e]. Remarkably, despite being earlier, [\u003cspan citationid=\"CR36\" class=\"CitationRef\"\u003e36\u003c/span\u003e] was nonetheless highly referenced for detecting AXL-mediated EGFR resistance, which has influenced subsequent AI research on signaling circuit modelling. Finally, [\u003cspan citationid=\"CR37\" class=\"CitationRef\"\u003e37\u003c/span\u003e] made a substantial contribution as well by integrating machine learning and radiogenomics in a sizable dataset on breast cancer.\u003c/p\u003e\u003cp\u003eA comparison of Tables\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e and \u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e reveals that the most productive and impactful authors do not fully correspond with those responsible for the most cited publications. Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e identifies Wang X, Zhang Y, Lin Y, and Li H as the leading contributors, based on the h-index. However, these authors do not appear among the top ten most cited papers. Conversely, highly cited works [\u003cspan additionalcitationids=\"CR33\" citationid=\"CR32\" class=\"CitationRef\"\u003e32\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR34\" class=\"CitationRef\"\u003e34\u003c/span\u003e] dominate Table\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e but are not linked to the most recurrently productive authors in Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e. This pattern reveals a divergence between researchers who drive cumulative output in the integration of artificial intelligence in triple-negative breast cancer research and those who produce pioneering studies with significant citation impact. Table\u0026nbsp;\u003cspan refid=\"Tab2\" class=\"InternalRef\"\u003e2\u003c/span\u003e illustrates the sustained productivity and influence of specific authors, whereas Table\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e3\u003c/span\u003e highlights pivotal publications that have shifted research directions or introduced new methodologies. These complementary perspectives provide a comprehensive understanding of the development of AI in TNBC research, shaped by both consistent author productivity and milestone publications that serve as intellectual foundations.\u003c/p\u003e\u003cp\u003e\u003cem\u003e4.5 Keyword co-occurrence network\u003c/em\u003e\u003c/p\u003e\u003cp\u003eThe co-occurrence network of all keywords, shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig5\" class=\"InternalRef\"\u003e6\u003c/span\u003eA, outlines the thematic structure of research integrating artificial intelligence in TNBC. Node size reflects keyword frequency, and links represent co-occurrence relationships. The visualization highlights the multidisciplinary convergence of AI with molecular biology, clinical oncology, and imaging, underscoring its growing role in precision medicine for TNBC. Distinct clusters represent unique methodological and clinical research directions. Cluster 1 (red) focuses on biological and genomic aspects, including \u003cem\u003etriple negative breast cancer\u003c/em\u003e, \u003cem\u003emachine learning\u003c/em\u003e, \u003cem\u003egenetics\u003c/em\u003e, and \u003cem\u003egene expression\u003c/em\u003e, indicating a strong emphasis on omics-driven approaches. Cluster 2 (green) addresses clinical and translational topics, such as \u003cem\u003ebreast cancer\u003c/em\u003e, \u003cem\u003ebreast tumors\u003c/em\u003e, \u003cem\u003epathology\u003c/em\u003e, and \u003cem\u003ecohort analysis\u003c/em\u003e, highlighting the application of artificial intelligence in patient stratification and diagnosis. Cluster 3 (blue) centers on computational themes, including \u003cem\u003edeep learning\u003c/em\u003e, \u003cem\u003ealgorithm\u003c/em\u003e, and \u003cem\u003eartificial intelligence\u003c/em\u003e, underscoring the importance of advanced algorithms in oncology research. Cluster 4 (yellow) is associated with prognostic markers, such as \u003cem\u003etumor-infiltrating lymphocytes\u003c/em\u003e, \u003cem\u003etumor recurrence\u003c/em\u003e, and \u003cem\u003eKaplan-Meier analysis\u003c/em\u003e, linking artificial intelligence to survival outcome predictions. Cluster 5 (purple) highlights statistical and algorithmic methods, including \u003cem\u003eclassification\u003c/em\u003e and \u003cem\u003eleast absolute shrinkage and selection operator (LASSO)\u003c/em\u003e, while cluster 6 (turquoise) emphasizes early detection. These findings align with recent bibliometric reviews, which indicate that all-keyword mapping demonstrates a balanced interplay between artificial intelligence methodologies and clinical applications in oncology, and that TNBC research is emerging as a critical area [\u003cspan citationid=\"CR51\" class=\"CitationRef\"\u003e51\u003c/span\u003e, \u003cspan citationid=\"CR52\" class=\"CitationRef\"\u003e52\u003c/span\u003e, \u003cspan citationid=\"CR55\" class=\"CitationRef\"\u003e55\u003c/span\u003e].\u003c/p\u003e\u003cp\u003eOn the other hand, the authors\u0026rsquo; keywords co-occurrence network in Fig.\u0026nbsp;\u003cspan refid=\"Fig5\" class=\"InternalRef\"\u003e6\u003c/span\u003eB provides further insight into the intellectual structure of AI-driven TNBC research, capturing the self-defined priorities of contributing researchers. Cluster 1 (red) emphasizes methodological advances, including \u003cem\u003etriple-negative breast cancer\u003c/em\u003e, \u003cem\u003emachine learning\u003c/em\u003e, \u003cem\u003ebiomarker\u003c/em\u003e, and \u003cem\u003eclassification\u003c/em\u003e. These terms reflect the integration of AI into biomarker discovery and predictive modeling. Cluster 2 (green) addresses translational and therapeutic aspects, featuring \u003cem\u003eartificial intelligence\u003c/em\u003e, \u003cem\u003eneoadjuvant chemotherapy\u003c/em\u003e, and \u003cem\u003epathological complete response\u003c/em\u003e. This cluster demonstrates the expanding role of AI in treatment monitoring. Cluster 3 (blue) focuses on imaging and computational approaches, with \u003cem\u003edeep learning\u003c/em\u003e, \u003cem\u003eprognosis\u003c/em\u003e, and \u003cem\u003enuclei segmentation\u003c/em\u003e indicating an emphasis on automated histopathological analysis. Cluster 4 (yellow) consolidates concepts related to cancer diagnosis and digital pathology, signifying a transition toward AI-enhanced pathological workflows. Cluster 5 (purple) encompasses radiomics and imaging modalities, while cluster 6 (turquoise) connects therapeutic themes such as \u003cem\u003echemotherapy\u003c/em\u003e, \u003cem\u003eimmunotherapy\u003c/em\u003e, and \u003cem\u003etumor microenvironment\u003c/em\u003e, suggesting interaction between computational tools and immuno-oncology. Cluster 7 (orange), though the smallest, identifies emerging directions, including \u003cem\u003eultrasound\u003c/em\u003e and \u003cem\u003emolecular subtyping\u003c/em\u003e. The authors\u0026rsquo; keywords network indicates that researchers\u0026rsquo; selected keywords represent both established research areas and emerging frontiers. This complements the broader thematic scope presented by all keywords in Fig.\u0026nbsp;\u003cspan refid=\"Fig5\" class=\"InternalRef\"\u003e6\u003c/span\u003eA.\u003c/p\u003e\u003cp\u003eA comparative analysis of the co-occurrence networks in \u003cb\u003eFig.s 6A\u003c/b\u003e and \u003cb\u003e6B\u003c/b\u003e reveals both convergence and divergence in thematic focus when comparing all keywords with authors\u0026rsquo; keywords. The all-keywords map (Fig.\u0026nbsp;\u003cspan refid=\"Fig5\" class=\"InternalRef\"\u003e6\u003c/span\u003eA) displays a broader range of indexed terms. Its clusters include clinical and pathological aspects such as \u003cem\u003ebreast cancer\u003c/em\u003e, \u003cem\u003epathology\u003c/em\u003e, \u003cem\u003eand cohort analysis\u003c/em\u003e. Computational methodologies, including \u003cem\u003edeep learning\u003c/em\u003e, \u003cem\u003ealgorithm\u003c/em\u003e, and \u003cem\u003eartificial intelligence\u003c/em\u003e, are also prominent. In contrast, the authors\u0026rsquo; keywords map (Fig.\u0026nbsp;\u003cspan refid=\"Fig5\" class=\"InternalRef\"\u003e6\u003c/span\u003eB) reflects researchers\u0026rsquo; intentional framing of their studies. This map emphasizes translational and methodological priorities such as \u003cem\u003ebiomarker\u003c/em\u003e, \u003cem\u003eclassification\u003c/em\u003e, \u003cem\u003eneoadjuvant chemotherapy\u003c/em\u003e, \u003cem\u003eprognosis\u003c/em\u003e, and \u003cem\u003edigital pathology\u003c/em\u003e. Both maps identify \u003cem\u003etriple-negative breast cancer\u003c/em\u003e and \u003cem\u003eartificial intelligence\u003c/em\u003e or \u003cem\u003emachine learning\u003c/em\u003e techniques as central themes. However, the authors\u0026rsquo; network assigns greater importance to clinical applications such as \u003cem\u003epathological complete response\u003c/em\u003e, \u003cem\u003eimmunotherapy\u003c/em\u003e, and \u003cem\u003etumor microenvironment\u003c/em\u003e, as well as to precision tools such as \u003cem\u003eradiomics\u003c/em\u003e and \u003cem\u003enuclei segmentation\u003c/em\u003e. The all-keywords network, by comparison, encompasses a wider array of general oncology and methodological terms. This comparison suggests that database-driven indexing using all keywords provides a more comprehensive but less focused perspective. In contrast, author-specified keywords highlight the strategic priorities and emerging research frontiers identified by the scientific community [\u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e, \u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e, \u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e].\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec19\" class=\"Section2\"\u003e\u003ch2\u003e4.6 Thematic evolution and trending topics\u003c/h2\u003e\u003cp\u003eThe thematic map (Fig.\u0026nbsp;\u003cspan refid=\"Fig6\" class=\"InternalRef\"\u003e7\u003c/span\u003eA) illustrates the progression of artificial intelligence integration in triple-negative breast cancer research by organizing authors\u0026rsquo; keywords into four quadrants according to relevance and development. Basic themes, including m\u003cem\u003eachine learning, deep learning, radiomics, artificial intelligence\u003c/em\u003e, and \u003cem\u003etriple-negative breast cancer\u003c/em\u003e, underscore the foundational role of these concepts in the field. These keywords highlight the increasing application of computational models for image analysis, biomarker identification, and predictive modeling. Their classification as basic themes suggest ongoing refinement and methodological advancement. In contrast, motor themes such as \u003cem\u003eattention mechanisms, multi-omics data integration, graph convolutional networks\u003c/em\u003e, and \u003cem\u003eimmune checkpoint inhibitors\u003c/em\u003e indicate a shift toward more complex and biologically informed AI methodologies. This development demonstrates a growing emphasis on advanced algorithms to address TNBC\u0026rsquo;s molecular heterogeneity and its interactions with the tumor microenvironment. Niche themes, such as \u003cem\u003ebreast cancer subtype classification, differential gene expression\u003c/em\u003e, and \u003cem\u003eensemble learning\u003c/em\u003e, provide specialized but less central contributions. Emerging or declining themes (low centrality and low density), including \u003cem\u003egraph neural network(s)\u003c/em\u003e may represent either early-stage innovations or concepts encountering barriers to broader adoption. Themes such as \u003cem\u003edeep neural network, artificial intelligence (ai)\u003c/em\u003e, and \u003cem\u003etnbc subtype\u003c/em\u003e are currently between the niche and emerging or declining themes. They are specialized yet not fully part of mainstream TNBC research. Their low centrality indicates limited engagement with the wider oncology community, while rising internal density suggests active work by specialized groups. This stage signifies that clinical success and broader adoption could render these themes central to the field. If they are not well-integrated, they may remain peripheral or decline. Strategic investment and collaboration across domains are needed to reach their potential. In general, the thematic mapping reveals a transition from foundational AI applications in TNBC to more sophisticated, integrative strategies that advance precision oncology.\u003c/p\u003e\u003cp\u003eThe thematic evolution of authors\u0026rsquo; keywords in the integration of AI in TNBC research from 2011 to 2025, as shown in Fig.\u0026nbsp;\u003cspan refid=\"Fig6\" class=\"InternalRef\"\u003e7\u003c/span\u003eB, demonstrates a progressive shift in research priorities. Between 2011 and 2017, the research mainly focused on broad topics such as \u003cem\u003ebreast cancer\u003c/em\u003e and \u003cem\u003emachine learning\u003c/em\u003e. From 2018 to 2022, research broadened to strategies for understanding tumor biology and image analysis. This is evidenced by keywords like \u003cem\u003esingle-cell rna-seq\u003c/em\u003e, \u003cem\u003etumor microenvironment\u003c/em\u003e, and \u003cem\u003enuclei segmentation\u003c/em\u003e. During this period, research on TNBC also became increasingly specialized. Between 2023 and 2025, the focus is projected to move toward radiomics, diagnosis, and prognosis prediction. The appearance of keywords such as \u003cem\u003ecomputer-aided diagnosis\u003c/em\u003e, \u003cem\u003edigital pathology\u003c/em\u003e, \u003cem\u003efeature selection\u003c/em\u003e, and \u003cem\u003esurvival analysis\u003c/em\u003e suggests a shift toward improving diagnostic tools and methods. This aims for better patient outcomes. Throughout the period, breast cancer has remained a central theme. The increased use of computational tools underscores the interdisciplinary nature of contemporary oncological research.\u003c/p\u003e\u003cp\u003eFigure\u0026nbsp;\u003cspan refid=\"Fig7\" class=\"InternalRef\"\u003e8\u003c/span\u003e presents the temporal emergence and frequency of trend topics related to the integration of AI in TNBC research; the analysis utilized the authors\u0026rsquo; keywords. This figure demonstrates a marked increase in the use of terms such as \u003cem\u003ebioinformatics\u003c/em\u003e, \u003cem\u003emolecular subtypes\u003c/em\u003e, \u003cem\u003ebiomarker\u003c/em\u003e, \u003cem\u003edigital pathology, and triple-negative breast cancer\u003c/em\u003e from 2020 to 2022, indicating increased adoption of computational tools and representing key areas where AI is transforming TNBC research, enabling advanced data analysis, precise disease classification, biomarker discovery, and enhanced diagnostic imaging. However, by 2023, topics such as \u003cem\u003etriple-negative breast cancer\u003c/em\u003e, \u003cem\u003emachine learning\u003c/em\u003e, and \u003cem\u003ebreast cancer\u003c/em\u003e dominated this research landscape, signaling a strong convergence of oncology and artificial intelligence in scholarly focus. By 2024, \u003cem\u003etnbc\u003c/em\u003e, \u003cem\u003emagnetic resonance imaging\u003c/em\u003e, and \u003cem\u003eartificial intelligence\u003c/em\u003e emerged as the most frequently discussed topics, reflecting a sharp focus on data-driven diagnostics and precision imaging in TNBC research. The rising frequency of these terms over time highlights the expanding influence of AI in improving diagnostic accuracy, personalizing treatment, and increasing research efficiency in TNBC. This development is consistent with broader bibliometric analyses that demonstrate the interdisciplinary convergence of oncology, data science, and medical imaging [\u003cspan citationid=\"CR28\" class=\"CitationRef\"\u003e28\u003c/span\u003e, \u003cspan citationid=\"CR56\" class=\"CitationRef\"\u003e56\u003c/span\u003e, \u003cspan citationid=\"CR57\" class=\"CitationRef\"\u003e57\u003c/span\u003e].\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec20\" class=\"Section2\"\u003e\u003ch2\u003e4.7 Countries and authors\u0026rsquo; collaboration\u003c/h2\u003e\u003cp\u003eThe nation of the corresponding author provides insight into leadership and teamwork within the international research environment. China and the United States are the leading countries for corresponding authors (Table\u0026nbsp;\u003cspan refid=\"Tab4\" class=\"InternalRef\"\u003e4\u003c/span\u003e), which is consistent with their status as the most cited and productive nations (\u003cb\u003eFig.s 3B and 3A\u003c/b\u003e). Articles are classified as either single-country publications (SCP), where all authors are from the same nation and intra-country collaboration is indicated, or multiple-country publications (MCP), which involve contributors from different nations and represent inter-country collaboration [\u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e]. Countries in Asia and North America, such as China, the USA, India, Korea, and Canada, produce more SCPs than MCPs, indicating a stronger focus on domestic research. This pattern suggests that these research powerhouses depend primarily on established domestic infrastructure, funding, and networks to advance AI integration in TNBC research, while international collaboration remains secondary. In contrast, European countries, including the UK, Georgia, Germany, France, and the Netherlands, rely more extensively on international partnerships, consistent with evidence that transnational collaboration is more prevalent in regions with supportive cross-border policies [\u003cspan citationid=\"CR58\" class=\"CitationRef\"\u003e58\u003c/span\u003e, \u003cspan citationid=\"CR59\" class=\"CitationRef\"\u003e59\u003c/span\u003e]. Although the USA has more SCPs than MCPs, it has a high proportion of internationally co-authored work, highlighting its central role in global research networks. India, despite its relatively high output, relies predominantly on domestic collaborations, indicating limited international integration. The Netherlands exhibits a notably high MCP rate compared to its SCP rate. These differences underscore the strategic value of international collaboration in enhancing the integration of AI in TNBC research beyond mere publication volume.\u003c/p\u003e\u003cp\u003eFigure\u0026nbsp;\u003cspan refid=\"Fig8\" class=\"InternalRef\"\u003e9\u003c/span\u003eA identifies six co-authorship clusters in the integration of AI in TNBC research. Cluster 1, in red, includes Australia, Belgium, India, the Netherlands, Poland, Saudi Arabia, and Sweden, and demonstrates growing regional collaborations between emerging and established research nations. This agrees with previous studies that showed that India and the Netherlands are increasing their contributions to AI-enabled oncology research [\u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e25\u003c/span\u003e, \u003cspan citationid=\"CR60\" class=\"CitationRef\"\u003e60\u003c/span\u003e]. Cluster 2, in green, comprises Austria, France, Italy, Spain, the United Kingdom, and the United States, forming the primary hub of research activity. The United States leads in citation impact and is second only to China in terms of publication volume and serves as a central mediator for international collaboration, particularly with European countries [\u003cspan citationid=\"CR58\" class=\"CitationRef\"\u003e58\u003c/span\u003e, \u003cspan citationid=\"CR59\" class=\"CitationRef\"\u003e59\u003c/span\u003e]. Cluster 3, in blue, consists of China and Taiwan, reflecting China's prominent role in breast cancer immunology and AI research, supported by strong institutional partnerships that enhance regional research output [\u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e25\u003c/span\u003e, \u003cspan citationid=\"CR60\" class=\"CitationRef\"\u003e60\u003c/span\u003e]. The remaining clusters, cluster 4 (Iran and Canada), cluster 5 (Norway and Brazil), and cluster 6 (Germany and South Korea), represent bilateral or specialized collaborations that supplement the global research network. These patterns align with broader trends in international scientific collaboration, where geographic proximity, policy frameworks, and institutional capacity influence the structure and intensity of co-authorship networks [\u003cspan citationid=\"CR58\" class=\"CitationRef\"\u003e58\u003c/span\u003e, \u003cspan citationid=\"CR59\" class=\"CitationRef\"\u003e59\u003c/span\u003e].\u003c/p\u003e\u003cp\u003eFigure\u0026nbsp;\u003cspan refid=\"Fig8\" class=\"InternalRef\"\u003e9\u003c/span\u003eB presents the authors\u0026rsquo; collaboration network, revealing three distinct and loosely connected co-authorship clusters. Cluster 1 (red) is the smallest and comprises Aneja R and Bhattarai S, demonstrating an active partnership with limited integration into the wider research community, a pattern consistent with peripheral dyadic collaborations in AI-cancer research [\u003cspan citationid=\"CR61\" class=\"CitationRef\"\u003e61\u003c/span\u003e]. Cluster 2 (green) is the largest and most central, led by prolific authors including Wang Y, Wang X, Zhang X, Zhang J, and Zhang Y. This cluster highlights the substantial contributions of authors with primary affiliation to Chinese-based institutions, who are among the most productive in the integration of AI in TNBC research and frequently engage in high-volume, intra-country collaborations [\u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e26\u003c/span\u003e, \u003cspan citationid=\"CR46\" class=\"CitationRef\"\u003e46\u003c/span\u003e]. Cluster 3 (blue) consists of Yang W, Sun J, Chen H, Xu Z, and Valero V, forming a subgroup with strong internal collaboration but weaker connections to the central green cluster. Collaborations between research clusters remain fragmented, with limited cross-linkages between Western and Asian scholars. This fragmentation is consistent with bibliometric evidence showing that research on AI integration in biomedical science is concentrated in regional hubs, including the United States, China, and Europe, with trans-regional co-authorship relatively uncommon [\u003cspan citationid=\"CR62\" class=\"CitationRef\"\u003e62\u003c/span\u003e, \u003cspan citationid=\"CR63\" class=\"CitationRef\"\u003e63\u003c/span\u003e]. Increasing inter-cluster collaborations could promote knowledge exchange, methodological diversity, and broader global research impact [\u003cspan citationid=\"CR57\" class=\"CitationRef\"\u003e57\u003c/span\u003e].\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec21\" class=\"Section2\"\u003e\u003ch2\u003e4.8 Emerging trends analysis\u003c/h2\u003e\u003cp\u003eThe integration of artificial intelligence into triple-negative breast cancer research has accelerated, reshaping oncological investigation and clinical practice. This section examines emerging trends identified through bibliometric mapping. Analysis of the keyword co-occurrence network, topic trends, thematic map, and thematic evolution reveals key developments in this research field.\u003c/p\u003e\u003cdiv id=\"Sec22\" class=\"Section3\"\u003e\u003ch2\u003e4.8.1 Digital Pathology and Radiomics\u003c/h2\u003e\u003cp\u003eAdvanced imaging and digital pathology represent foundational yet evolving elements in triple-negative breast cancer research. Thematic evolution analysis indicates that \u003cem\u003edigital pathology\u003c/em\u003e, \u003cem\u003efeature selection\u003c/em\u003e, and \u003cem\u003ehistopathology\u003c/em\u003e have emerged as significant themes since 2023 (Fig.\u0026nbsp;\u003cspan refid=\"Fig6\" class=\"InternalRef\"\u003e7\u003c/span\u003eB). Trend topics data demonstrate a growing adoption of \u003cem\u003edigital pathology\u003c/em\u003e and \u003cem\u003emagnetic resonance imaging\u003c/em\u003e (Fig.\u0026nbsp;\u003cspan refid=\"Fig7\" class=\"InternalRef\"\u003e8\u003c/span\u003e). Furthermore, thematic mapping identifies \u003cem\u003ehistopathology images\u003c/em\u003e, \u003cem\u003enuclei segmentation\u003c/em\u003e, and \u003cem\u003eradiomics\u003c/em\u003e as basic themes, suggesting they are highly relevant but not yet fully developed (Fig.\u0026nbsp;\u003cspan refid=\"Fig6\" class=\"InternalRef\"\u003e7\u003c/span\u003eA). AI-enhanced imaging supports precise tumor delineation, automated feature extraction, and longitudinal monitoring of treatment response. Digital pathology platforms utilizing convolutional neural networks (CNNs) enable reproducible, high-throughput histological assessments. Radiomics, which transforms medical images into quantitative data, is increasingly used to predict treatment outcomes and identify phenotypic biomarkers. As these technologies mature and further integrate with artificial intelligence, they are likely to become central to innovation in TNBC diagnostics and to advance personalized, data-driven clinical decision-making for patients with TNBC.\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec23\" class=\"Section3\"\u003e\u003ch2\u003e4.8.2 Biomarker discovery and predictive modeling\u003c/h2\u003e\u003cp\u003eDue to the absence of ER, PR, and HER2 receptors, research is currently being intensified to identify therapeutic targets for improved prognosis. Biomarker discovery has become a central focus in triple-negative breast cancer research, particularly as artificial intelligence methods increasingly identify clinically relevant molecular indicators. Thematic evolution indicates \u003cem\u003ebiomarker\u003c/em\u003e and \u003cem\u003efeature selection\u003c/em\u003e as key themes around 2018 to 2022 and 2023 to 2025, respectively (Fig.\u0026nbsp;\u003cspan refid=\"Fig6\" class=\"InternalRef\"\u003e7\u003c/span\u003eB). This is supported by the trends\u0026rsquo; topic analysis, which showed \u003cem\u003ebiomarker\u003c/em\u003e as the most frequent term in 2022 (Fig.\u0026nbsp;\u003cspan refid=\"Fig7\" class=\"InternalRef\"\u003e8\u003c/span\u003e). Artificial intelligence models are applied to genomic, proteomic, and radiomic datasets to identify biomarkers associated with TNBC aggressiveness, drug resistance, and survival outcomes. Feature selection methods isolate the most predictive variables, thereby improving model interpretability and clinical applicability. These predictive models facilitate risk stratification and inform personalized treatment planning, which can enhance therapeutic efficacy and minimize adverse effects. The continued expansion of data-driven biomarker research is anticipated to advance precision oncology and translational clinical applications.\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec24\" class=\"Section3\"\u003e\u003ch2\u003e4.8.3 Varied artificial intelligence algorithms\u003c/h2\u003e\u003cp\u003eArtificial intelligence is becoming increasingly influential in triple-negative breast cancer research, facilitating high-throughput data analysis, predictive modeling, and automated diagnostics. Thematic evolution analyses reveal a notable increase in the use of terms such as \u003cem\u003emachine learning\u003c/em\u003e and \u003cem\u003esupport vector\u003c/em\u003e machine from 2023 to 2025, with trend frequency data highlighting the prominence of \u003cem\u003emachine learning\u003c/em\u003e in 2023 and \u003cem\u003eartificial intelligence\u003c/em\u003e in 2024 (Fig.\u0026nbsp;\u003cspan refid=\"Fig6\" class=\"InternalRef\"\u003e7\u003c/span\u003eB, \u003cspan refid=\"Fig7\" class=\"InternalRef\"\u003e8\u003c/span\u003e). \u003cem\u003eDeep neural networks\u003c/em\u003e and \u003cem\u003eartificial intelligence\u003c/em\u003e are positioned between niche and emerging or declining themes, while \u003cem\u003egraph neural network(s\u003c/em\u003e) are categorized within the emerging or declining quadrant of the thematic map (Fig.\u0026nbsp;\u003cspan refid=\"Fig6\" class=\"InternalRef\"\u003e7\u003c/span\u003eA). This placement suggests that, although interest in these technologies is growing, their integration into mainstream TNBC workflows remains limited. Furthermore, \u003cem\u003edeep learning\u003c/em\u003e, \u003cem\u003emachine learning\u003c/em\u003e, \u003cem\u003eartificial intelligence, convolutional neural networks\u003c/em\u003e are placed in the basic theme quadrant indicating that these themes are fundamental, widely connected to other themes in this field but are still evolving. Machine learning (ML) and deep learning (DL) methods are increasingly applied to histopathological image segmentation, biomarker identification, and clinical decision support, resulting in improved diagnostic accuracy and efficiency. As computational oncology advances, AI is anticipated to transition from a peripheral innovation to a central component of TNBC research, reflecting a broader shift toward data-driven medicine. The application of ML and DL algorithms enables the identification of complex patterns in genomic and imaging data, ultimately contributing to earlier detection and more personalized treatment strategies that improve patient outcomes.\u003c/p\u003e\u003c/div\u003e\u003c/div\u003e\n\u003ch3\u003e4. 9 Future research directions\u003c/h3\u003e\n\u003cdiv id=\"Sec26\" class=\"Section3\"\u003e\u003cdiv class=\"Heading\"\u003e4.9.1 Clinical translation of AI models\u003c/div\u003e\u003cp\u003eThe thematic map (Fig.\u0026nbsp;\u003cspan refid=\"Fig6\" class=\"InternalRef\"\u003e7\u003c/span\u003eA) identifies \u003cem\u003eartificial intelligence\u003c/em\u003e and \u003cem\u003edeep neural networks\u003c/em\u003e as emerging technologies that are increasing in relevance yet remain insufficiently integrated into clinical workflows. Subsequent research should focus on developing explainable AI models that are validated and implemented in practical oncology environments. Key priorities include ensuring regulatory compliance, enhancing clinical interpretability, and facilitating integration with electronic health records to promote usability and trust among oncologists [\u003cspan citationid=\"CR64\" class=\"CitationRef\"\u003e64\u003c/span\u003e].\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec27\" class=\"Section3\"\u003e\u003cdiv class=\"Heading\"\u003e4.9.2 Multi-omics integration for personalized therapy\u003c/div\u003e\u003cp\u003eThe increasing use of \u003cem\u003emulti-omics data\u003c/em\u003e and \u003cem\u003efeature selection\u003c/em\u003e, as demonstrated in the thematic map (motor theme) and thematic evolution (2023 to 2023), respectively, reflects a transition toward systems-level analysis (Fig.\u0026nbsp;\u003cspan refid=\"Fig6\" class=\"InternalRef\"\u003e7\u003c/span\u003eA, B). Future research on triple-negative breast cancer should investigate the application of artificial intelligence to integrate genomic, transcriptomic, proteomic, and epigenomic data for the development of dynamic, patient-specific treatment algorithms. This approach aims to advance precision medicine from static molecular profiling to adaptive, real-time therapeutic guidance [\u003cspan citationid=\"CR65\" class=\"CitationRef\"\u003e65\u003c/span\u003e, \u003cspan citationid=\"CR66\" class=\"CitationRef\"\u003e66\u003c/span\u003e].\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec28\" class=\"Section3\"\u003e\u003cdiv class=\"Heading\"\u003e4.9.3 Non-invasive diagnostics and liquid biopsy\u003c/div\u003e\u003cp\u003eWhile currently peripheral in the thematic map (Fig.\u0026nbsp;\u003cspan refid=\"Fig6\" class=\"InternalRef\"\u003e7\u003c/span\u003eA), \u003cem\u003ebiomarker\u003c/em\u003e and \u003cem\u003efeature selection\u003c/em\u003e research is increasingly focused on non-invasive diagnostics. Artificial intelligence is expected to significantly advance the analysis of circulating tumor DNA (ctDNA), exosomes, and other liquid biopsy components, facilitating early detection and real-time monitoring of TNBC without the need for tissue samples [\u003cspan citationid=\"CR67\" class=\"CitationRef\"\u003e67\u003c/span\u003e].\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec29\" class=\"Section3\"\u003e\u003cdiv class=\"Heading\"\u003e4.9.4 Immuno-oncology and tumor microenvironment modeling\u003c/div\u003e\u003cp\u003eThematic clustering focused on \u003cem\u003eimmune checkpoint inhibitors\u003c/em\u003e and \u003cem\u003ecancer-associated fibroblasts\u003c/em\u003e \u003cb\u003e(\u003c/b\u003eFig.\u0026nbsp;\u003cspan refid=\"Fig6\" class=\"InternalRef\"\u003e7\u003c/span\u003eA\u003cb\u003e)\u003c/b\u003e indicates increasing scholarly attention to the tumor microenvironment. Future research is expected to employ artificial intelligence to model immune interactions, predict responses to immunotherapies, and identify novel immune biomarkers. These advancements are anticipated to facilitate the development of personalized immuno-oncology strategies specifically adapted to the unique immune landscape of triple-negative breast cancer [\u003cspan citationid=\"CR68\" class=\"CitationRef\"\u003e68\u003c/span\u003e].\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec30\" class=\"Section3\"\u003e\u003cdiv class=\"Heading\"\u003e4.9.5 Increased and sustained collaboration between authors\u003c/div\u003e\u003cp\u003eIncreased and sustained collaboration between authors is essential for advancing AI integration in TNBC research. Currently, co-authorship networks are split by region and institution. Figure\u0026nbsp;\u003cspan refid=\"Fig8\" class=\"InternalRef\"\u003e9\u003c/span\u003eB shows three weakly linked groups. Cluster 1 (red) represents a peripheral partnership between Aneja R and Bhattarai S. Cluster 2 (green) comprises Chinese-based authors, such as Wang Y and Zhang Y, who collaborate primarily within their own country. Cluster 3 (blue) has Western researchers such as Yang W and Valero V (both affiliated with the University of Texas MD Anderson Cancer Center), who work closely together but rarely with members of other clusters. This divide matches other trends that show research clusters stay regional, with few global co-authorships in AI integration in the biosciences [\u003cspan citationid=\"CR62\" class=\"CitationRef\"\u003e62\u003c/span\u003e, \u003cspan citationid=\"CR63\" class=\"CitationRef\"\u003e63\u003c/span\u003e]. This limits both methodological diversity and worldwide impact. Promoting links between groups through international consortia, data sharing, and targeted funding can close these gaps, encourage knowledge exchange, and facilitate innovation. Such efforts also address the isolation of some collaborations [\u003cspan citationid=\"CR69\" class=\"CitationRef\"\u003e69\u003c/span\u003e, \u003cspan citationid=\"CR70\" class=\"CitationRef\"\u003e70\u003c/span\u003e]. Given the status of TNBC as a global health scourge, increased and sustained national and international collaborations will be required in this field to address this threat.\u003c/p\u003e\u003c/div\u003e\u003cdiv id=\"Sec31\" class=\"Section2\"\u003e\u003ch2\u003e4.10 Limitations\u003c/h2\u003e\u003cp\u003eThis study offers important insights into the integration of artificial intelligence in triple-negative breast cancer research on a global scale. Nevertheless, certain limitations should be acknowledged. The exclusive use of the Scopus database, while recognized for its reliability, resulted in the exclusion of other major databases such as Web of Science, Google Scholar, Dimensions, and Lens. This restriction may have limited the comprehensiveness of the literature reviewed. The study also included only publications up to July 19th of the current year, when documents were retrieved. Research and citation counts may have increased since then, possibly affecting the results. Future research should address these shortcomings. Despite these limitations, the study remains valid and useful, offering valuable insights into current and future directions for AI integration in TNBC research.\u003c/p\u003e\u003c/div\u003e"},{"header":"5.0 Conclusion","content":"\u003cp\u003eBibliometric analysis was employed to examine the yearly publications, prolific authors, prominent journals, contributing nations, popular keywords, general progress, and evolution in artificial intelligence integration in TNBC research from 2011 to 2025. This paper is the first to analyze the topic using a bibliometric approach based on the Scopus database, offering a comprehensive assessment of research output, including analysis of authors, sources, documents, themes, trends, and future priorities. The publications analyzed in this study were contributed by 2,781 authors affiliated with diverse institutions across the globe. With the annual rise of 38.02%, the body of knowledge is growing steadily. Furthermore, the international co-authorship percentage (28.20%) highlights significant networking in generating scientific information on artificial intelligence integration in triple-negative breast cancer research, albeit in isolated clusters. China and the United States were the most productive and most cited countries, respectively, with the USA leading in global collaboration per published document. The University of Texas MD Anderson Cancer Center was the most relevant affiliation. \u003cem\u003eCancers\u003c/em\u003e was the most productive and impactful source. Zhang J was the most productive author, while Wang X emerged as the most impactful author in the field. \u003cem\u003eBiomarker, radiomics\u003c/em\u003e and \u003cem\u003efeature selection\u003c/em\u003e were some of the emerging trends in this field. Future research should address clinical translation of AI models, multi-omics for personalized therapy, non-invasive diagnostics and liquid biopsy, immuno-oncology and tumor microenvironment, along with an increased and sustained collaboration between authors to shape the research landscape on AI integration into TNBC research.\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003eAcknowledgements\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eNot applicable\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eAuthors' contributions\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConceptualization\u003c/strong\u003e: Israel Ogwuche Ogra, Jeremiah Zaphnathpaaneah Adaji; \u003cstrong\u003eMethodology\u003c/strong\u003e: Israel Ogwuche Ogra, Jeremiah Zaphnathpaaneah Adaji, Emohchonne Utos Jonathan, Faustina Ntim Opoku; \u003cstrong\u003eFormal analysis and investigation:\u003c/strong\u003e Jeremiah Zaphnathpaaneah Adaji; Precious Ezinne Nebo, Evelyn Omolola Ajibua, Eneh Philip; \u003cstrong\u003eData curation:\u0026nbsp;\u003c/strong\u003eJeremiah Zaphnathpaaneah Adaji, Shadrack Dangabar Apollos, Daniel Gbenga Adekanmi, Daniel Thakuma Tizhe; \u003cstrong\u003eWriting - original draft preparation:\u003c/strong\u003e Jeremiah Zaphnathpaaneah Adaji; Israel Ogwuche Ogra; \u003cstrong\u003eWriting - review and editing:\u003c/strong\u003e Israel Ogwuche Ogra, Uche Samuel Ndidi, Umezuruike Linus Opara; \u003cstrong\u003eProject administration:\u003c/strong\u003e Israel Ogwuche Ogra, Hadiza Joy Umar, David John Burman Ladan, Kodjovi Sossou; \u003cstrong\u003eSupervision\u003c/strong\u003e: Uche Samuel Ndidi, Umezuruike Linus Opara.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eFunding\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eNo funding was received for this research.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eData availability\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eData is provided within the manuscript or supplementary information files.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eCompeting interests\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe authors have no conflict of interest to declare that are relevant to the content of this article.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eEthical approval and consent to participate\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eNo aspect of our research required formal ethical approval or usage of participants.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eClinical trial number\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eNot applicable.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eConsent for publication\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe authors agree on the transfer of the copyright to the Publisher on acceptance of this manuscript for publication.\u0026nbsp;\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\n\u003cli\u003eDent R, Trudeau M, Pritchard KI, Hanna WM, Kahn HK, Sawka CA, et al. Triple-negative breast cancer: clinical features and patterns of recurrence. Clin Cancer Res. 2007;13(15):4429\u0026ndash;34. https://doi.org/10.1158/1078-0432.CCR-06-3045.\u003c/li\u003e\n\u003cli\u003eElsawaf Z, Sinn HP. Triple-negative breast cancer: clinical and histological correlations. Breast Care. 2011;6(4):273\u0026ndash;8. https://doi.org/10.1159/000331643.\u003c/li\u003e\n\u003cli\u003eCarey LA, Dees EC, Sawyer L, Gatti L, Moore DT, Collichio F, et al. The triple negative paradox: primary tumor chemosensitivity of breast cancer subtypes. Clin Cancer Res. 2007;13(8):2329\u0026ndash;34. https://doi.org/10.1158/1078-0432.CCR-06-1109.\u003c/li\u003e\n\u003cli\u003eAmerican Cancer Society. Triple-negative Breast Cancer | Details, Diagnosis, and Signs. American Cancer Society; 2023. https://www.cancer.org/cancer/types/breast-cancer/about/types-of-breast-cancer/triple-negative.html. Accessed 20 August 2025\u003c/li\u003e\n\u003cli\u003eMediratta K, El-Sahli S, D\u0026rsquo;Costa V, Wang L. Current progresses and challenges of immunotherapy in triple-negative breast cancer. Cancers. 2020;12(12):3529. https://doi.org/10.3390/cancers12123529.\u003c/li\u003e\n\u003cli\u003eWu Q, Siddharth S, Sharma D. Triple negative breast cancer: a mountain yet to be scaled despite the triumphs. Cancers. 2021;13(15):3697. https://doi.org/10.3390/cancers13153697.\u003c/li\u003e\n\u003cli\u003eBayard S, Martini R, Chen Y, Jenkins B, Elhussin I, Cheng E, et al. Abstract PO-139: BRCA sequence variants in breast cancer patients with African ancestry. Cancer Epidemiol Biomarkers Prev. 2022;31(1 Suppl):PO-139.\u003c/li\u003e\n\u003cli\u003eYao S, Wei L, Hu Q, Liu S, Manojlovic Z, Fiorica PN, et al. Mutational landscape of triple-negative breast cancer in African American women. Nat Genet. 2025;1(1). https://doi.org/10.1038/s41588-025-02322-y.\u003c/li\u003e\n\u003cli\u003eLeon-Ferre RA, Goetz MP. Advances in systemic therapies for triple negative breast cancer. BMJ. 2023;381:p1173. https://doi.org/10.1136/bmj-2022-071674 .\u003c/li\u003e\n\u003cli\u003eAsleh K, Riaz N, Nielsen TO. Heterogeneity of triple negative breast cancer: current advances in subtyping and treatment implications. J Exp Clin Cancer Res. 2022;41(1):265. https://doi.org/10.1186/s13046-022-02476-1.\u003c/li\u003e\n\u003cli\u003eMarra A, Trapani D, Viale G, Criscitiello C, Curigliano G. Practical classification of triple-negative breast cancer: intratumoral heterogeneity, mechanisms of drug resistance, and novel therapies. NPJ Breast Cancer. 2020;6:54. https://doi.org/10.1038/s41523-020-00197-2.\u003c/li\u003e\n\u003cli\u003eRussell SJ, Norvig P. Artificial Intelligence: A Modern Approach. Prentice Hall; 1995.\u003c/li\u003e\n\u003cli\u003eTopol E. Deep Medicine: How Artificial Intelligence Can Make Healthcare Human Again. Hachette UK; 2019.\u003c/li\u003e\n\u003cli\u003eGuo J, Hu J, Zheng Y, Zhao S, Ma J. Artificial intelligence: opportunities and challenges in the clinical applications of triple-negative breast cancer. Br J Cancer. 2023;128(12):2141\u0026ndash;9. https://doi.org/10.1038/s41416-023-02215-z.\u003c/li\u003e\n\u003cli\u003eOcana A, Pandiella A, Privat C, Bravo I, Luengo-Oroz M, Amir E, et al. Integrating artificial intelligence in drug discovery and early drug development: a transformative approach. Biomark Res. 2025;13(1):45. https://doi.org/10.1186/s40364-025-00758-2.\u003c/li\u003e\n\u003cli\u003eRajput HPS, Lodhi S. AI in drug repurposing. Int J Pharm Sci. 2025;3(5):2098\u0026ndash;103. https://doi.org/10.5281/zenodo.15396590.\u003c/li\u003e\n\u003cli\u003eWan Y, Shen Y, Wang J, Zhang T, Fu X. Knowledge mapping of ultrasound technology and triple-negative breast cancer: a visual and bibliometric analysis. Discov Oncol. 2025;16(1):1248. https://doi.org/10.1007/s12672-025-03063-4.\u003c/li\u003e\n\u003cli\u003eDonthu N, Kumar S, Mukherjee D, Pandey N, Lim WM. How to conduct a bibliometric analysis: an overview and guidelines. J Bus Res. 2021;133:285\u0026ndash;96. https://doi.org/10.1016/j.jbusres.2021.04.070.\u003c/li\u003e\n\u003cli\u003eAria M, Cuccurullo C. bibliometrix: An R-tool for comprehensive science mapping analysis. J Informetr. 2017;11(4):959\u0026ndash;75. https://doi.org/10.1016/j.joi.2017.08.007.\u003c/li\u003e\n\u003cli\u003eChen C. CiteSpace II: detecting and visualizing emerging trends and transient patterns in scientific literature. J Am Soc Inf Sci Technol. 2006;57(3):359\u0026ndash;77. https://doi.org/10.1002/asi.20317.\u003c/li\u003e\n\u003cli\u003evan Eck N, Waltman L. Software survey: VOSviewer, a computer program for bibliometric mapping. Scientometrics. 2010;84(2):523\u0026ndash;38. https://doi.org/10.1007/s11192-009-0146-3.\u003c/li\u003e\n\u003cli\u003eSyed AH, Khan T. Evolution of research trends in artificial intelligence for breast cancer diagnosis and prognosis over the past two decades: a bibliometric analysis. Front Oncol. 2022;12:854927. https://doi.org/10.3389/fonc.2022.854927.\u003c/li\u003e\n\u003cli\u003eSingh S, Healy NA. The top 100 most-cited articles on artificial intelligence in breast radiology: a bibliometric analysis. Insights Imaging. 2024;15(1):297. https://doi.org/10.1186/s13244-024-01869-4.\u003c/li\u003e\n\u003cli\u003eHou C, Huang T, Hu K, Ye Z, Guo J, Zhou H. Artificial intelligence-assisted multimodal imaging for the clinical applications of breast cancer: a bibliometric analysis. Discov Oncol. 2025;16(1):537. https://doi.org/10.1007/s12672-025-02329-1.\u003c/li\u003e\n\u003cli\u003eWu X, Xia Y, Lou X, Huang K, Wu L, Gao C. Decoding breast cancer imaging trends: the role of AI and radiomics through bibliometric insights. Breast Cancer Res. 2025;27(1):29. https://doi.org/10.1186/s13058-025-01983-1.\u003c/li\u003e\n\u003cli\u003eLi S, Zhang N, Zhang H, Zhou R, Li Z, Yang X, et al. Artificial intelligence learning landscape of triple-negative breast cancer uncovers new opportunities for enhancing outcomes and immunotherapy responses. J Big Data. 2023;10(1):132. https://doi.org/10.1186/s40537-023-00809-1.\u003c/li\u003e\n\u003cli\u003eWang X, Li X, Dong T, Yu W, Jia Z, Hou Y, et al. Global biomarker trends in triple-negative breast cancer research: a bibliometric analysis. Int J Surg. 2024;110(12):7962\u0026ndash;83. https://doi.org/10.1097/JS9.0000000000001799.\u003c/li\u003e\n\u003cli\u003eWang K, Zheng C, Xue L, Deng D, Zeng L, Li M, et al. A bibliometric analysis of 16,826 triple-negative breast cancer publications using multiple machine learning algorithms: progress in the past 17 years. Front Med. 2023;10:999312. https://doi.org/10.3389/fmed.2023.999312.\u003c/li\u003e\n\u003cli\u003eBurnham JF. Scopus database: a review. Biomed Digit Libr. 2006;3(1):1. https://doi.org/10.1186/1742-5581-3-1.\u003c/li\u003e\n\u003cli\u003eGrant MJ. Keywords and their role in information retrieval. Health Inf Libr J. 2010;27(3):173\u0026ndash;5. https://doi.org/10.1111/j.1471-1842.2010.00904.x.\u003c/li\u003e\n\u003cli\u003eAlzate-Granados JP, Ni\u0026ntilde;o LF. Prediction of overall and relapse-free survival in triple-negative breast cancer patients through machine learning-based clustering on clinical data. Clin Breast Cancer. 2025. https://doi.org/10.1016/j.clbc.2025.07.027.\u003c/li\u003e\n\u003cli\u003eKeren L, Bosse M, Marquez D, Angoshtari R, Jain S, Varma S, et al. A structured tumor-immune microenvironment in triple negative breast cancer revealed by multiplexed ion beam imaging. Cell. 2018;174(6):1373\u0026ndash;87. https://doi.org/10.1016/j.cell.2018.08.039.\u003c/li\u003e\n\u003cli\u003eBraman NM, Etesami M, Prasanna P, Dubchuk C, Gilmore H, Tiwari P, et al. Intratumoral and peritumoral radiomics for the pretreatment prediction of pathological complete response to neoadjuvant chemotherapy based on breast DCE-MRI. Breast Cancer Res. 2017;19(1):57. https://doi.org/10.1186/s13058-017-0846-1.\u003c/li\u003e\n\u003cli\u003eHe Y, Jiang Z, Chen C, Wang X. Classification of triple-negative breast cancers based on immunogenomic profiling. J Exp Clin Cancer Res. 2018;37(1):327. https://doi.org/10.1186/s13046-018-1002-1.\u003c/li\u003e\n\u003cli\u003eZou Y, Xie J, Zheng S, Liu W, Tang Y, Tian W, et al. Leveraging diverse cell-death patterns to predict the prognosis and drug sensitivity of triple-negative breast cancer patients after surgery. Int J Surg. 2022;107:106936. https://doi.org/10.1016/j.ijsu.2022.106936.\u003c/li\u003e\n\u003cli\u003eMeyer AS, Miller MA, Gertler FB, Lauffenburger DA. The receptor AXL diversifies EGFR signaling and limits the response to EGFR-targeted inhibitors in triple-negative breast cancer cells. Sci Signal. 2013;6(287):ra66. https://doi.org/10.1126/scisignal.2004155.\u003c/li\u003e\n\u003cli\u003eSaha A, Harowicz MR, Grimm LJ, Kim CE, Ghate SV, Walsh R, et al. A machine learning approach to radiogenomics of breast cancer: a study of 922 subjects and 529 DCE-MRI features. Br J Cancer. 2018;119(4):508\u0026ndash;16. https://doi.org/10.1038/s41416-018-0185-8.\u003c/li\u003e\n\u003cli\u003eXiao Y, Ma D, Yang YS, Yang Y, Ding JH, Gong Y, et al. Comprehensive metabolomics expands precision medicine for triple-negative breast cancer. Cell Res. 2022;32(5):477\u0026ndash;90. https://doi.org/10.1038/s41422-022-00614-0.\u003c/li\u003e\n\u003cli\u003eMostavi M, Chiu YC, Huang Y, Chen Y. Convolutional neural network models for cancer type prediction based on gene expression. BMC Med Genomics. 2020;13(Suppl 5):44. https://doi.org/10.1186/s12920-020-0712-5.\u003c/li\u003e\n\u003cli\u003eWu J, Hicks C. Breast cancer type classification using machine learning. J Pers Med. 2021;11(2):61. https://doi.org/10.3390/jpm11020061.\u003c/li\u003e\n\u003cli\u003eCain EH, Saha A, Harowicz MR, Marks JR, Marcom PK, Mazurowski MA. Multivariate machine learning models for prediction of pathologic response to neoadjuvant therapy in breast cancer using MRI features: a study using an independent validation set. Breast Cancer Res Treat. 2019;173(2):455\u0026ndash;63. https://doi.org/10.1007/s10549-018-4990-9.\u003c/li\u003e\n\u003cli\u003eZupic I, Čater T. Bibliometric methods in management and organization. Organ Res Methods. 2015;18(3):429\u0026ndash;72. https://doi.org/10.1177/1094428114562629.\u003c/li\u003e\n\u003cli\u003eDuede E, Dolan W, Bauer A, Foster I, Lakhani K. Oil \u0026amp; water? Diffusion of AI within and across scientific fields. arXiv preprint. 2024;arXiv:2405.15828. https://doi.org/10.48550/arXiv.2405.15828.\u003c/li\u003e\n\u003cli\u003eWang X, Ahmad I, Javeed D, Zaidi SA, Alotaibi FM, Ghoneim ME, et al. Intelligent hybrid deep learning model for breast cancer detection. Electronics. 2022;11(17):2767. https://doi.org/10.3390/electronics11172767.\u003c/li\u003e\n\u003cli\u003eDong H, Wang X, Zheng Y, Li J, Liu Z, Wang A, et al. Mapping the rapid growth of multi-omics in tumor immunotherapy: bibliometric evidence of technology convergence and paradigm shifts. Hum Vaccin Immunother. 2025;21(1):2493539. https://doi.org/10.1080/21645515.2025.2493539.\u003c/li\u003e\n\u003cli\u003eWang R, Huang S, Wang P, Shi X, Li S, Ye Y, et al. Bibliometric analysis of the application of deep learning in cancer from 2015 to 2023. Cancer Imaging. 2024;24(1):85. https://doi.org/10.1186/s40644-024-00737-0.\u003c/li\u003e\n\u003cli\u003eHajkowicz S, Sanderson C, Karimi S, Bratanova A, Naughtin C. Artificial intelligence adoption in the physical sciences, natural sciences, life sciences, social sciences and the arts and humanities: a bibliometric analysis of research publications from 1960\u0026ndash;2021. arXiv preprint. 2023;arXiv:2306.09145. https://doi.org/10.48550/arXiv.2306.09145.\u003c/li\u003e\n\u003cli\u003eGuo Q, Geng C, Yao N, Zhao L. Can digital infrastructure enhance economic efficiency? Evidence from China. Qual Quant. 2024;58(2):1729\u0026ndash;52. https://doi.org/10.1007/s11135-023-01710-y.\u003c/li\u003e\n\u003cli\u003eRoberts H, Cowls J, Hine E, Morley J, Wang V, Taddeo M, et al. Governing artificial intelligence in China and the European Union: comparing aims and promoting ethical outcomes. Inf Soc. 2023;39(2):79\u0026ndash;97. https://doi.org/10.1080/01972243.2022.2124565.\u003c/li\u003e\n\u003cli\u003eWebster G, Creemers R, Kania E, Triolo P. Full translation: China\u0026rsquo;s \u0026ldquo;new generation artificial intelligence development plan\u0026rdquo; (2017). DigiChina, Stanford University; 2017. https://digichina.stanford.edu/work/full-translation-chinas-new-generation-artificial-intelligence-development-plan-2017/. Accessed 15 September 2025.\u003c/li\u003e\n\u003cli\u003eLi P, Li J, Tong X, Xiao Z, Diao W, Zhong C, et al. Global research trends and prospects related to tumor microenvironment within triple-negative breast cancer: a bibliometric analysis. Front Immunol. 2023;14:1261290. https://doi.org/10.3389/fimmu.2023.1261290.\u003c/li\u003e\n\u003cli\u003eXiong N, Wu H, Yu Z. Advancements and challenges in triple-negative breast cancer: a comprehensive review of therapeutic and diagnostic strategies. Front Oncol. 2024;14:1405491. https://doi.org/10.3389/fonc.2024.1405491.\u003c/li\u003e\n\u003cli\u003eHirsch JE. An index to quantify an individual\u0026rsquo;s scientific research output. Proc Natl Acad Sci U S A. 2005;102(46):16569\u0026ndash;72. https://doi.org/10.1073/pnas.0507655102.\u003c/li\u003e\n\u003cli\u003eEgghe L. Theory and practise of the g-index. Scientometrics. 2006;69(1):131\u0026ndash;52. doi:10.1007/s11192-006-0144-7.\u003c/li\u003e\n\u003cli\u003eEkinci B, Tekedere H. Bibliometric analysis of research on artificial intelligence applications in breast cancer diagnosis. Technol Health Care. 2025;09287329251362602. https://doi.org/10.3233/THC-240037.\u003c/li\u003e\n\u003cli\u003eBhalla K, Xiao Q, Luna JM, Podany E, Ahmad T, Ademuyiwa FO, et al. Radiologic imaging biomarkers in triple-negative breast cancer: a literature review about the role of artificial intelligence and the way forward. BJR Artif Intell. 2024;1(1):ubae016. https://doi.org/10.1093/bjrai/ubae016.\u003c/li\u003e\n\u003cli\u003eWang SH, Chen G, Zhong X, Lin T, Shen Y, Fan X, et al. Global development of artificial intelligence in cancer field: a bibliometric analysis range from 1983 to 2022. Front Oncol. 2023;13:1215729. https://doi.org/10.3389/fonc.2023.1215729.\u003c/li\u003e\n\u003cli\u003eKwiek M. International research collaboration and international research orientation: comparative findings about European academics. J Stud Int Educ. 2018;22(2):136\u0026ndash;60. https://doi.org/10.1177/1028315317747084.\u003c/li\u003e\n\u003cli\u003eWagner CS, Park HW, Leydesdorff L. The continuing growth of global cooperation networks in research: a conundrum for national governments. PLoS One. 2015;10(7):e0131816. https://doi.org/10.1371/journal.pone.0131816.\u003c/li\u003e\n\u003cli\u003eSingh A, Singh A, Bhattacharya S. Research trends on AI in breast cancer diagnosis, and treatment over two decades. Discov Oncol. 2024;15(1):772. https://doi.org/10.1007/s12672-024-01671-0.\u003c/li\u003e\n\u003cli\u003eLin L, Liang L, Wang M, Huang R, Gong M, Song G, et al. A bibliometric analysis of worldwide cancer research using machine learning methods. Cancer Innov. 2023;2(3):219\u0026ndash;32. https://doi.org/10.1002/cai2.68.\u003c/li\u003e\n\u003cli\u003eKo\u0026ccedil;ak M, Ak\u0026ccedil;alı Z. The published role of artificial intelligence in drug discovery and development: a bibliometric and social network analysis from 1990 to 2023. J Cheminform. 2025;17(1):71. https://doi.org/10.1186/s13321-025-00988-4.\u003c/li\u003e\n\u003cli\u003eXu Q, Feng X, Qin S, Hong Y, Cui R, Liang J, et al. Research on therapeutic clinical trials including immunotherapy in triple-negative breast cancer: a bibliometric analysis. Front Oncol. 2024;14:1423924. https://doi.org/10.3389/fonc.2024.1423924.\u003c/li\u003e\n\u003cli\u003eLiao J, Li X, Gan Y, Han S, Rong P, Wang W, et al. Artificial intelligence assists precision medicine in cancer treatment. Front Oncol. 2023;12:998222. https://doi.org 10.3389/fonc.2022.998222.\u003c/li\u003e\n\u003cli\u003eYang S, Wang Z, Wang C, Li C, Wang B. Comparative evaluation of machine learning models for subtyping triple-negative breast cancer: a deep learning-based multi-omics data integration approach. J Cancer. 2024;15(12):3943\u0026ndash;54. https://doi.org/10.7150/jca.93215.\u003c/li\u003e\n\u003cli\u003eZhang N, Zhang Y, Yang RF, Chu HQ, Rehman A, Yang LY, et al. Multi-omics integration uncovers key transcriptional regulators in triple-negative breast cancer spatial heterogeneity. Front Genet. 2025;16:1614254. https://doi.org/10.3389/fgene.2025.1614254.\u003c/li\u003e\n\u003cli\u003eSheng J, Zong X. Liquid biopsy in TNBC: significance in diagnostics, prediction, and treatment monitoring. Front Oncol. 2025;15:1607960. https://doi.org/10.3389/fonc.2025.1607960.\u003c/li\u003e\n\u003cli\u003eGuo Z, Zhu Z, Lin X, Wang S, Wen Y, Wang L, et al. Tumor microenvironment and immunotherapy for triple-negative breast cancer. Biomark Res. 2024;12(1):166. https://doi.org/10.1186/s40364-024-00714-6.\u003c/li\u003e\n\u003cli\u003eLiang H, Yin G, Feng D, Chen H, Liu X, Li J. Research trends on nanomaterials in triple-negative breast cancer (TNBC): a bibliometric analysis from 2010 to 2024. Drug Deliv Transl Res. 2024;1\u0026ndash;6. https://doi.org/10.1007/s13346-024-01704-9.\u003c/li\u003e\n\u003cli\u003eNdidi US, Ogra IO, Jonathan EU, Iroha OK. Drug repurposing in cancer research: a bibliometric analysis. Discov Oncol. 2025;16:1796. https://doi.org/10.1007/s12672-025-02895-4.\u003c/li\u003e\n\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Triple-negative breast cancer, machine learning, bibliometrics, emerging trends, Scopus","lastPublishedDoi":"10.21203/rs.3.rs-7830165/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7830165/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eTriple-negative breast cancer (TNBC) is defined by the absence of estrogen and progesterone receptors and low expression of the human epidermal growth factor receptor 2 (HER2) protein, which limits the efficacy of available treatment strategies. Recent advances in data science have spurred the application of artificial intelligence (AI) in TNBC research, leading to notable progress. The purpose of this study was to evaluate the current landscape, primary research areas, and emerging trends in AI integration in TNBC research. The analysis aimed to provide a comprehensive overview of research progress and to identify future research directions. Using the Bibliometrix R package and VOSviewer, 461 documents indexed in the Scopus database from 2011 to 2025 were examined. Results indicate rapid expansion in this research field, with an annual growth rate of 38.02%. China and the United States of America emerged as the leading contributors, with the USA leading in global collaboration. The journal \u003cem\u003eCancers\u003c/em\u003ehad the highest number of publications and the greatest impact in this field. The University of Texas MD Anderson Cancer Center was the most relevant affiliation, while Zhang J and Wang X emerged as the most productive and impactful authors, respectively. \u003cem\u003eBiomarkers\u003c/em\u003e, \u003cem\u003eradiomics\u003c/em\u003e, and \u003cem\u003efeature selection\u003c/em\u003e were among the top emerging trends in this field. Identified future research directions include clinical translation of AI models, multi-omics for personalized therapy, non-invasive diagnostics, liquid biopsy, and the tumor microenvironment. Increased and sustained collaboration among authors is needed to shape the research landscape on AI integration into TNBC research.\u003c/p\u003e","manuscriptTitle":"Integration of Artificial Intelligence in Triple-Negative Breast Cancer Research: A Bibliometric and Emerging Trends Analysis","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-10-15 08:20:29","doi":"10.21203/rs.3.rs-7830165/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"fde26caf-4603-4416-9689-399987c055fc","owner":[],"postedDate":"October 15th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2025-10-27T13:49:17+00:00","versionOfRecord":[],"versionCreatedAt":"2025-10-15 08:20:29","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7830165","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7830165","identity":"rs-7830165","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}