Artificial Intelligence in Immune Checkpoint Inhibitor Research: A Bibliometric Analysis of the Landscape

Artificial Intelligence in Immune Checkpoint Inhibitor Research: A Bibliometric Analysis of the Landscape | 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 Research Article Artificial Intelligence in Immune Checkpoint Inhibitor Research: A Bibliometric Analysis of the Landscape Jian Kang, Rui Tang, Dongqi Li, Li Ma, Zhiqiang Zhang This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8873872/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 This bibliometric analysis examines the transformative role of artificial intelligence (AI) in immune checkpoint inhibitor (ICI) research. Analyzing 597 publications from the Web of Science Core Collection (2016–2025), we reveal a dramatic rise in AI-related ICI studies, led by the USA and China. Key findings demonstrate AI's integration in predicting treatment response, optimizing dosing strategies, and managing immune-related adverse events. Through keyword co-occurrence and citation analyses, we identify critical AI applications including novel gene target discovery, drug structure design, and multimodal data fusion for personalized immunotherapy. While highlighting AI's potential to bridge preclinical research and clinical practice, we emphasize the need for interpretable models, robust validation, and ethical frameworks to ensure equitable clinical translation. This comprehensive overview provides valuable insights into research trends and future directions for AI-driven innovations in cancer immunotherapy. Artificial intelligence Immune checkpoint inhibitors bibliometric Figures Figure 1 Figure 2 Figure 3 Figure 4 Figure 5 Figure 6 Figure 7 Figure 8 Introduction Immune checkpoint inhibitors (ICIs) significantly improve patient prognoses by activating the immune system ( 1 – 3 ). However, their efficacy varies widely, while they may induce immune-related adverse events (irAEs), underscoring the critical need for precise dosing studies ( 4 – 9 ). Traditional immune biomarker detection methods are costly and their accuracy has been questioned ( 10 ). Meanwhile, these methods struggle to capture the heterogeneity and dynamic changes within the tumor microenvironment (TME) ( 10 – 12 ). Recently, artificial intelligence (AI) has emerged as a transformative tool to address these challenges ( 13 – 18 ). By integrating multi-omics data, spatial genomics analysis, and clinical outcomes, AI is increasingly unraveling the complex interplay between immune checkpoint inhibitor dosage, therapeutic efficacy, and toxicity ( 19 – 23 ). The advent of novel systemic treatments, particularly ICIs, has markedly expanded the therapeutic arsenal for solid tumors. However, their clinical application reveals considerable variability in patient outcomes, highlighting the urgent need for reliable predictors of response. In renal cell carcinoma, for instance, clinicopathological features such as sarcomatoid differentiation and International Metastatic RCC Database Consortium (IMDC) risk scores significantly influence survival in patients treated with first-line ICI–tyrosine kinase inhibitor combinations ( 24 , 25 ). Real-world data further underscore the differential effectiveness of immune-oncology combinations across risk strata, emphasizing the importance of risk-adapted therapeutic strategies ( 24 ). Beyond tumor-specific factors, systemic host conditions also modulate treatment efficacy. The interplay between cancer risk, chronic inflammation, and metabolic syndrome constitutes a complex axis that can impact immune responses and treatment outcomes ( 26 ). Additionally, patient-specific prognostic tools such as the cachexia index (CXI) have emerged as valuable biomarkers, reflecting the systemic metabolic and inflammatory burden that influences survival and potentially ICI responsiveness ( 27 ). In hepatocellular carcinoma, the combination of ICIs with antiangiogenic agents has become a first-line standard, yet challenges persist in identifying which patients will derive the greatest benefit, necessitating a deeper understanding of the underlying biological and clinical determinants ( 28 ). Cancer immunotherapy has advanced significantly with the introduction of new systemic treatments, such as immune checkpoint inhibitors. These treatments have revolutionized treatment options for cancers like gastric cancer, hepatocellular carcinoma, and renal cell carcinoma. However, challenges remain in optimizing therapeutic strategies and managing adverse events. Recent studies have highlighted the importance of understanding the DNA damage response alterations in gastric cancer, which could provide new targets for therapy ( 29 ). In hepatocellular carcinoma, immunotherapy faces challenges, including the identification of effective biomarkers and the overcoming of resistance mechanisms ( 30 ). Moreover, the associations between cancer risk, inflammation, and metabolic syndrome have been explored, emphasizing the need for a comprehensive approach to cancer treatment ( 26 ). The prognostic significance of the cachexia index in cancer patients has also been recognized, indicating its potential as a biomarker for treatment outcomes ( 27 ). Furthermore, real-world outcomes of patients with advanced renal cell carcinoma treated with immune-oncology combinations have varied according to risk groups. This finding highlights the importance of personalized treatment strategies ( 24 ). As the field of tumor immunotherapy rapidly expands, it has become imperative to conduct a comprehensive bibliometric analysis of ICIs-related and AI research. Bibliometrics offers a systematic approach to quantify and organize the exponential growth of publications on ICIs, providing a macroscopic perspective on research trends, hotspots, and future directions ( 31 – 36 ). Temporal analyses of publication volumes, geographic distributions, and institutional collaborations reveal research patterns, major contributors, and regional synergies ( 31 – 36 ). Such insights facilitate optimized global resource allocation, which minimizes redundancy, enhances research efficiency, and ultimately accelerates scientific progress. Furthermore, AI enables analysis of multidimensional data from scientific literature to explore ICIs mechanisms, dose-response relationships, and adverse event profiles in depth. For example, machine learning (ML) algorithms can model and predict the spatiotemporal dynamics of immune cells and cytokines within the TME, elucidate their correlation with ICIs dosage, and inform precise dosing strategies ( 15 , 19 , 37 – 43 ). These capabilities support clinical decision-making, dose optimization, and risk mitigation strategies ( 13 , 15 , 20 , 41 – 43 ). In conclusion, integrating AI into bibliometric analyses of ICIs research is a key advancement that supports precise dosing studies and enables personalized tumor immunotherapy. This interdisciplinary approach holds immense potential to improve clinical oncology outcomes by bridging translational gaps between preclinical discoveries and clinical applications. Methods Search Strategy We conducted a literature search in the Web of Science Core Collection (WoSCC) database ( https://www.webofscience.com/wos/woscc/basic-search ) on 30 May 2025. The search strategy followed the criteria outlined in Fig. 1 , restricting document types restricted to "articles" and "reviews". As a result, a total of 597 publications were selected for subsequent bibliometric analysis. Data Analysis VOSviewer (version 1.6.20) was utilized for bibliometric analysis, extracting key information from numerous ICIs-related publications ( 44 – 46 ). This software facilitated keyword co-occurrence analysis. The maps generated by VOSviewer used nodes to represent entities like keywords; the size of these nodes indicated the number of ICIs publications associated with each item, and the color signified the classification ( 44 – 46 ). CiteSpace (version 6.3.1), developed by Professor Chen, was another tool used for bibliometric analysis and visualization in immunosuppressant research ( 47 – 49 ). Specifically, it was used to analyze references with “ Citation Bursts ” to identify significant and influential publications in the field. The R package "bibliometrix" (version 4.3.0) was employed to analyze thematic evolution and to construct a global distribution network of ICIs publications ( 50 – 54 ). It comprehensively analyzed ICIs research across countries, institutions, publishers, and authors, offering insights into research output, impact, key players, collaborative networks, and publication trends. The quartile and impact factor of journals were obtained from the Journal Citation Reports 2024 and were used to assess the quality and influence of ICIs-related publications. Additionally, Microsoft Office Excel 2021 was used for quantitative analysis of ICIs publications, enabling researchers to organize, process, and analyze data efficiently. By applying AI techniques, researchers gained deeper insights into ICIs research trends, collaborations, and knowledge evolution, enabling a comprehensive understanding of the current status and future directions of AI-driven ICIs innovation. Quantitative Analysis of Publications Figure 2 presented a bar chart the annual publication trends of AI in ICIs from 2016 to 2025. In 2016, the number of publications was 1. By 2018, this number had gradually increased to approximately 8. The upward trend continued in 2021, with the number climbing to around 55. In 2024, publications increased to around 175. As of 2025, preliminary data showed the number of publications had reached 123, indicating ongoing growth. Each bar represented the number of publications for that year, with the y-axis showing publication counts and the x-axis indicating years from 2016 to 2025, collectively illustrating the continuous and remarkable growth in AI research on ICIs during this period. Country and Affiliations Analysis Figure 3 A showed the Country Collaboration Map for AI in ICIs research. The US had the most extensive research collaborations worldwide, followed by China, which also showed broad but comparatively fewer global partnerships. Figure 3 B, focusing on Corresponding Authors' Countries, showed that Chinese authors conducted more independent research, while US authors participated more in international collaborations. Moreover, the number of Chinese scholars had surpassed that of US scholars. Figure 4 A showed the top ten affiliations ranked by the number of publications in AI in ICIs research. Sun Yat-sen University ranked first with 77 articles, followed by Harvard University with 59, and Harvard Medical School affiliates with 47. Figure 4 B illustrated the publication trends over time for the top five affiliations. The chart clearly showed an increasing number of publications, with each color representing a different institution. This highlighted the dynamic and growing contributions of leading research centers in AI in ICIs. Sources and Cited Sources Figure 5 A presented the top ten most relevant sources in the field of AI applications in ICIs research. The top three sources were Frontiers in Immunology (51 articles), Cancers (44 articles), and Frontiers in Oncology (28 articles). These journals had published many studies, significantly contributing to the research field. Figure 5 B showed the top ten most locally cited sources. The top three in this category were The New England Journal of Medicine with 1,208 citations, Journal of Clinical Oncology with 991 citations, and Clinical Cancer Research with 916 citations. These sources were highly cited in the field, highlighting their influence and lasting contribution to advancing AI-related ICIs research. Authors and Co-authors Figure 6 A showed the top ten Most Relevant Authors in AI in ICIs research. The top three authors were Kim S, Li L, and Lee SH, with 13, 12, and 11 publications respectively. Park S and Wang Y each contributed 11 publications. Figure 6 B displayed the top ten Most Local Cited Authors. Park S was the most cited with 61, followed by Tian J with 55, and Kim S with 51 citations. Reference with Citation Bursts Figure 7 A presented a keyword visualization generated by VOSviewer, highlighting key themes in AI research within ICIs. The visualization underscored the interconnectedness and prominence of topics such as immune response prediction, patient stratification, and toxicity management. Figure 7 B, generated using the bibliometrix package, analyzed the frequency and distribution of keywords in the field. It revealed the prevalence of terms such as " cancer ", " expression ", and " survival ", offering insights into core concepts and current research focuses. Figure 7 C showed a keyword clustering map created by CiteSpace, highlighting application areas such as AI-driven treatment optimization and biomarker discovery. The clustering provided valuable insights into research themes focused on improving therapeutic outcomes and a better understanding of immune mechanisms. Together, these visualizations offered a clear overview of key topics and their relationships within AI applications in ICIs research. They highlighted the field’s dynamic and multifaceted nature. Discussion The integration of AI and bibliometrics in the study of ICIs represents a significant advancement in immunotherapy research. It provides a comprehensive framework to analyze the evolution, current trends, and future directions of ICIs research ( 22 , 55 – 59 ). Our bibliometric analysis unveils the rapid growth in publications related to AI applications in ICIs, highlighting the escalating interest and investment in this domain. This section further explores the implications of our findings, focusing on the specific applications of AI in ICIs research, including the identification of novel gene targets, cell receptor structures, design of new ICIs structures, simulation of ICIs experiments, monitoring of drug efficacy, and the application of multimodal fusion for personalized treatment in real-world settings. Figure 2 illustrates the rapid increase in publications over the past decade, which indicates growing enthusiasm and tangible progress in the field. This growth in research marks a fundamental shift in the approach to complex biological problems. AI has become an indispensable tool, enabling researchers to unravel the intricate mechanisms underlying ICIs and their interactions with the TME. The identification of novel gene targets and cell receptor structures, along with the design of new ICIs molecules, is an area where AI has shown particular promise. However, the rapid proliferation of AI applications calls for cautious optimism. While the quantitative growth is impressive, the qualitative impact, especially regarding clinical translation, remains uneven. Our analysis suggests that many studies remain in the preclinical or early clinical validation stage, which highlights a persistent gap between computational promise and therapeutic reality. This finding underscores the need for more robust, interdisciplinary collaboration that prioritizes clinical relevance alongside algorithmic innovation. This observation underscores the need for more robust, interdisciplinary collaboration that prioritizes clinical relevance alongside algorithmic innovation. The application of AI in ICIs is rapidly evolving. Various types of AI tools are being deployed to address different tasks ( 13 , 19 ). Convolutional neural networks (CNN) are commonly used for image analysis tasks, such as identifying tumor characteristics from radiological data ( 60 ). Graph-based models are useful for analyzing complex biological networks, including interactions between immune cells and cancer cells ( 61 , 62 ). Each AI tool has its own strengths and limitations, and the choice depends on the specific task. We believe that selecting AI methodologies should consider not only technical performance but also biological plausibility and clinical interpretability. For instance, while deep learning models often achieve high predictive accuracy, their “black-box” nature can reduce clinician trust and hinder their integration into routine practice. We advocate for a balanced approach that combines high-performance AI with explainable AI (XAI) techniques, ensuring that predictions are both accurate and interpretable—a crucial step toward building clinician confidence and facilitating real-world adoption. As depicted in Fig. 8 , AI has the potential to make significant contributions to six key areas of ICIs research. 1. Finding New Gene Targets AI technologies such as ML algorithms have shown great potential in identifying novel gene targets for immunotherapy ( 63 , 64 ). By analyzing complex, large-scale genomic and transcriptomic datasets, AI can uncover patterns and correlations that traditional methods often miss ( 65 – 67 ). This capability enables researchers to pinpoint genes differentially expressed in response to ICIs, which may serve as biomarkers for treatment response or resistance. For instance, AI enhances ICI response prediction in LUAD by analyzing IRGs, improving prognostic accuracy( 68 ). Analyzing multi-omics data shows that AI’s greatest strength is integrating different types of data( 69 ). These include genomic, transcriptomic, proteomic, and clinical data, which AI combines into a unified predictive framework( 69 ). Nevertheless, we have encountered challenges such as data heterogeneity and batch effects that can compromise the model’s generalizability( 70 ). Moving forward, we emphasize the importance of standardizing data collection protocols and incorporating domain knowledge to guide feature selection, in order to enhance the biological relevance and robustness of AI-driven target discovery. 2. Designing New ICIs plan Analyzing multi - omics data is essential for developing effective immunotherapies, through which novel biomarkers for predicting ICI responses can be identified by AI algorithms ( 55 , 71 , 72 ). Vast datasets will be analyzed by machine learning models( 61 ). Explainable AI will also be employed to have these models validated, ensuring scientific credibility( 73 ). Clinical trial design will be streamlined through this approach, allowing promising ICIs to be identified more rapidly. Ultimately, personalized and precise immunotherapy strategies are aimed to be delivered, improving patient outcomes in cancer treatment. 3. Designing New Structures AI is crucial for the rational design of new ICIs structures (74, 75). Using virtual screening and molecular docking simulations, AI algorithms can evaluate the binding affinity and specificity of potential drug candidates with their target receptors. These AI-driven methods significantly reduce the time and cost associated with traditional drug discovery processes. Moreover, AI-driven de novo drug design techniques can generate novel molecular structures with target properties, expanding the chemical space for ICIs development. 4. Simulating ICIs Experiments In silico simulations of ICIs experiments provide a powerful way to predict drug efficacy and toxicity before performing costly and time-consuming in vitro or in vivo studies. AI models can simulate drugs and their pharmacokinetic and pharmacodynamic profiles, which reveal details of absorption, distribution, metabolism, and excretion ( 62 , 74 – 77 ). Additionally, AI can model the complex interactions within the TME and predict how ICIs affect immune cell populations and cytokine levels. Such in silico simulations help optimize drug dosages and treatment regimens, thereby improving therapeutic outcomes. 5. Monitoring ICIs Drug Efficacy Monitoring of ICIs drug efficacy is essential. It helps adjust treatment strategies and minimize adverse events ( 13 , 14 , 55 – 58 , 78 – 80 ). AI technologies, such as wearable devices and mobile health applications, enable continuous monitoring of patient data, including vital signs, symptoms, and laboratory results( 81 ). ML algorithms analyze these data to detect early signs of treatment response or toxicity, enabling timely interventions( 82 ). Moreover, AI-driven imaging analysis techniques, such as radiomics, can non-invasively assess tumor burden and treatment response, providing valuable information for clinical decision-making( 83 ). 6. Multimodal Fusion of Real-World Complex Data for Individualized Treatment Integrating multimodal data—genomic, proteomic, imaging, and clinical—enables a more comprehensive understanding of patient heterogeneity and treatment response ( 55 , 71 ). AI algorithms excel at analyzing these complex datasets to identify meaningful patterns that guide personalized treatment strategies. By leveraging multimodal fusion techniques—methods that combine diverse data types—researchers can develop predictive models that account for individual patient characteristics, such as genetic makeup, tumor microenvironment, and comorbidities. This approach enables the creation of genuinely personalized immunotherapy regimens, optimizing therapeutic outcomes while minimizing adverse effects. We believe multimodal data fusion is the most promising and challenging frontier in AI-driven ICIs research. In our own work, we observed that integrating imaging with genomic data significantly improves prediction of treatment response compared to unimodal approaches. Nevertheless, major challenges remain, including data privacy concerns, interoperability of healthcare systems, and the need for scalable computational infrastructure. Addressing these challenges will require not only technological innovation but also policy support, and cross-sector collaboration. Identifying practice-changing studies in AI-driven ICIs research highlights AI’s transformative potential in oncology. Many studies have advanced scientific knowledge and brought tangible changes to clinical practice ( 18 – 20 ). These contributions highlight the importance of integrating AI into the development and application of ICIs, as this integration offers new tools for personalized treatment and improved patient outcomes. Future research should continue to build on these foundational studies. It should explore novel applications of AI and validate their impact in diverse clinical settings. From our standpoint, success for AI in ICIs should not be measured by the number of publications or algorithms developed. Instead, it should be judged by tangible improvements in patient survival and quality of life. Therefore, we urge the research community to prioritize clinically meaningful endpoints and engage clinicians early in the AI development process. Such partnerships can ensure that AI tools are designed with real-world utility in mind, ultimately accelerating their adoption and impact in oncology practice. Deploying AI models safely is a critical issue in the field of ICIs. Ethical concerns arise when AI models are applied in clinical settings because they significantly impact patient care. Ensuring model transparency is essential because it helps clinicians and researchers understand how AI models make decisions. Additionally, tackling dataset biases is crucial so that AI models remain fair and generalizable across diverse populations. Strategies to address these challenges include rigorously validating AI models, training them on diverse and representative datasets, and implementing ethical guidelines for AI use in healthcare. AI has great potential to bridge the gap between preclinical research and clinical application, which is a critical need in immunotherapy ( 20 , 59 , 74 ). Efficiently translating lab findings into clinical practice is essential. AI-driven approaches can streamline this process. They help translate promising discoveries into tangible benefits for patients. However, integrating AI into clinical practice requires technical advancements. It also demands a shift in mindset among clinicians and researchers. Robust validation and regulatory frameworks must be established to ensure AI-driven tools are reliable, accurate, and safe. Conclusion In conclusion, we are optimistic about the future of AI in ICIs. However, we remain mindful of the work ahead. Bibliometric trends show that the field is rapidly expanding, but true transformation depends on our ability to overcome the translational, ethical, and practical challenges mentioned earlier. As researchers and clinicians, we have a responsibility to steer AI development toward equitable, interpretable, and clinically impactful solutions, ensuring that the promise of AI translates into better outcomes for every patient facing cancer. Declarations Funds This study was supported by the scientific research of the Heilongjiang Provincial Health Commission [grant number 20240404050045]. Authors’ contributions J.K. designed the study, drafted the initial manuscript, and created all original illustrations. R. T., D. L., and L. M. reviewed the manuscript and improved English. All data processing, statistical analyses, and interpretative synthesis of results were conducted by J.K. using validated methodological frameworks. Z. Z. provided critical review and substantive revisions to the manuscript regarding intellectual content. All authors finalized the manuscript, approved its submission, and take responsibility for the integrity of the work as presented. Consent for publication Not applicable. Availability of data and materials The original contributions of this study are included in the article and supplementary material at http://www.webofscience.com/wos/woscc/basic-search. Further inquiries can be directed to the corresponding authors. Competing interests There is no competing interests. Ethical approval Not applicable. Consent for publication Not applicable. Consent to publish Not applicable. References Dall'Olio FG, Marabelle A, Caramella C, Garcia C, Aldea M, Chaput N, et al. Tumour burden and efficacy of immune-checkpoint inhibitors. Nat Rev Clin Oncol. 2022;19(2):75–90. Kubli SP, Berger T, Araujo DV, Siu LL, Mak TW. Beyond immune checkpoint blockade: emerging immunological strategies. Nat Rev Drug Discov. 2021;20(12):899–919. Wei J, Li W, Zhang P, Guo F, Liu M. Current trends in sensitizing immune checkpoint inhibitors for cancer treatment. Mol Cancer. 2024;23(1):279. Carlino MS, Larkin J, Long GV. Immune checkpoint inhibitors in melanoma. Lancet. 2021;398(10304):1002–14. Geisler AN, Phillips GS, Barrios DM, Wu J, Leung DYM, Moy AP, et al. Immune checkpoint inhibitor-related dermatologic adverse events. J Am Acad Dermatol. 2020;83(5):1255–68. Okiyama N, Tanaka R. Immune-related adverse events in various organs caused by immune checkpoint inhibitors. Allergol Int. 2022;71(2):169–78. Poto R, Troiani T, Criscuolo G, Marone G, Ciardiello F, Tocchetti CG, et al. Holistic Approach to Immune Checkpoint Inhibitor-Related Adverse Events. Front Immunol. 2022;13:804597. Wan G, Chen W, Khattab S, Roster K, Nguyen N, Yan B, et al. Multi-organ immune-related adverse events from immune checkpoint inhibitors and their downstream implications: a retrospective multicohort study. Lancet Oncol. 2024;25(8):1053–69. Yin Q, Wu L, Han L, Zheng X, Tong R, Li L, et al. Immune-related adverse events of immune checkpoint inhibitors: a review. Front Immunol. 2023;14:1167975. Hu B, Yin G, Zhu J, Bai Y, Sun X. Continuous prediction for tumor mutation burden based on transcriptional data in gastrointestinal cancers. BMC Med Inf Decis Mak. 2024;24(1):384. Chen Z, Chen X, Ju L, Li Y, Li W, Pang H. Establishing a predictive model for tumor mutation burden status based on (18)F-FDG PET/CT and clinical features of non-small cell lung cancer patients. Transl Lung Cancer Res. 2024;13(9):2269–81. Sun C, Luo T, Liu Z, Ge J, Shao L, Liu X, et al. Tumor Mutation Burden-Related Histopathologic Features for Predicting Overall Survival in Gliomas Using Graph Deep Learning. Am J Pathol. 2023;193(12):2111–21. Dacic S, Travis WD, Giltnane JM, Kos F, Abel J, Hilz S, et al. Artificial Intelligence-Powered Assessment of Pathologic Response to Neoadjuvant Atezolizumab in Patients With NSCLC: Results From the LCMC3 Study. J Thorac Oncol. 2024;19(5):719–31. Emens LA, Romero PJ, Anderson AC, Bruno TC, Capitini CM, Collyar D et al. Challenges and opportunities in cancer immunotherapy: a Society for Immunotherapy of Cancer (SITC) strategic vision. J Immunother Cancer. 2024;12(6). Gong L, Gong J, Sun X, Yu L, Liao B, Chen X, et al. Identification and prediction of immune checkpoint inhibitors-related pneumonitis by machine learning. Front Immunol. 2023;14:1138489. Guo X, Chen S, Wang X, Liu X. Immune-related pulmonary toxicities of checkpoint inhibitors in non-small cell lung cancer: Diagnosis, mechanism, and treatment strategies. Front Immunol. 2023;14:1138483. Huemer F, Leisch M, Geisberger R, Melchardt T, Rinnerthaler G, Zaborsky N et al. Combination Strategies for Immune-Checkpoint Blockade and Response Prediction by Artificial Intelligence. Int J Mol Sci. 2020;21(8). Jiang Y, Zhang Z, Wang W, Huang W, Chen C, Xi S, et al. Biology-guided deep learning predicts prognosis and cancer immunotherapy response. Nat Commun. 2023;14(1):5135. Kim H, Kim S, Choi S, Park C, Park S, Pereira S, et al. Clinical Validation of Artificial Intelligence-Powered PD-L1 Tumor Proportion Score Interpretation for Immune Checkpoint Inhibitor Response Prediction in Non-Small Cell Lung Cancer. JCO Precis Oncol. 2024;8:e2300556. Zeng Q, Klein C, Caruso S, Maille P, Allende DS, Mínguez B, et al. Artificial intelligence-based pathology as a biomarker of sensitivity to atezolizumab-bevacizumab in patients with hepatocellular carcinoma: a multicentre retrospective study. Lancet Oncol. 2023;24(12):1411–22. Zhao J, Sun Z, Yu Y, Yuan Z, Lin Y, Tan Y et al. Radiomic and clinical data integration using machine learning predict the efficacy of anti-PD-1 antibodies-based combinational treatment in advanced breast cancer: a multicentered study. J Immunother Cancer. 2023;11(5). Zhao Z, Xu K, Jiang Y, Xu X, Liu Y. The role of artificial intelligence in immune checkpoint inhibitor research: A bibliometric analysis. Hum Vaccin Immunother. 2024;20(1):2429893. Zheng MM, Li JY, Guo HJ, Zhang J, Wang LS, Jiang KF, et al. IMPDH inhibitors upregulate PD-L1 in cancer cells without impairing immune checkpoint inhibitor efficacy. Acta Pharmacol Sin. 2025;46(4):1058–67. Santoni M, Buti S, Myint ZW, Maruzzo M, Iacovelli R, Pichler M, et al. Real-world Outcome of Patients with Advanced Renal Cell Carcinoma and Intermediate- or Poor-risk International Metastatic Renal Cell Carcinoma Database Consortium Criteria Treated by Immune-oncology Combinations: Differential Effectiveness by Risk Group? Eur Urol Oncol. 2024;7(1):102–11. Rizzo A, Mollica V, Santoni M, Ricci AD, Rosellini M, Marchetti A, et al. Impact of Clinicopathological Features on Survival in Patients Treated with First-line Immune Checkpoint Inhibitors Plus Tyrosine Kinase Inhibitors for Renal Cell Carcinoma: A Meta-analysis of Randomized Clinical Trials. Eur Urol Focus. 2022;8(2):514–21. Vitale E, Rizzo A, Santa K, Jirillo E. Associations between Cancer Risk. Inflamm Metabolic Syndrome: Scoping Rev Biology (Basel). 2024;13(5). Bas O, Sahin TK, Karahan L, Rizzo A, Guven DC. Prognostic significance of the cachexia index (CXI) in patients with cancer: A systematic review and meta-analysis. Clin Nutr ESPEN. 2025;68:240–7. Rizzo A, Ricci AD, Gadaleta-Caldarola G, Brandi G. First-line immune checkpoint inhibitor-based combinations in unresectable hepatocellular carcinoma: current management and future challenges. Expert Rev Gastroenterol Hepatol. 2021;15(11):1245–51. Ricci AD, Rizzo A, Brandi G. DNA damage response alterations in gastric cancer: knocking down a new wall. Future Oncol. 2021;17(8):865–8. Rizzo A, Ricci AD. Challenges and Future Trends of Hepatocellular Carcinoma Immunotherapy. Int J Mol Sci. 2022;23(19). He C, Zhang J, Zhang R, Liu L, Luo J, Zhang W, et al. Bibliometrics Analysis and Knowledge Mapping of Fragment-Based Drug Design Research: Trends from 2015 to 2024. Drug Des Devel Ther. 2025;19:4245–62. Qu F, Wang G, Wen P, Liu X, Zeng X. Knowledge mapping of immunotherapy for breast cancer: A bibliometric analysis from 2013 to 2022. Hum Vaccin Immunother. 2024;20(1):2335728. Stelmach V, Stavrou G, Theodorou I, Semertzidou E, Tzikos G, Menni AE et al. Postbiotics: Mapp Trend Nutrients. 2024;16(18). Wang C, Liu L, Bai X. Global Trends in Oliceridine (TRV130) Research from 2013 to 2024: A Bibliometrics and Knowledge Graph Analysis. Drug Des Devel Ther. 2024;18:4681–92. Wu T, Wu Y, Nie K, Yan J, Chen Y, Wang S, et al. Bibliometric analysis and global trends in uterus transplantation. Int J Surg. 2024;110(8):4932–46. Zhu X, Lv M, Cheng T, Zhou Y, Yuan G, Chu Y, et al. Bibliometric analysis of atrial fibrillation and ion channels. Heart Rhythm. 2024;21(7):1161–9. Jin W, Luo Q. When artificial intelligence meets PD-1/PD-L1 inhibitors: Population screening, response prediction and efficacy evaluation. Comput Biol Med. 2022;145:105499. Kinget L, Naulaerts S, Govaerts J, Vanmeerbeek I, Sprooten J, Laureano RS, et al. A spatial architecture-embedding HLA signature to predict clinical response to immunotherapy in renal cell carcinoma. Nat Med. 2024;30(6):1667–79. Kong J, Ha D, Lee J, Kim I, Park M, Im SH, et al. Network-based machine learning approach to predict immunotherapy response in cancer patients. Nat Commun. 2022;13(1):3703. Lin A, Jiang A, Huang L, Li Y, Zhang C, Zhu L, et al. From chaos to order: optimizing fecal microbiota transplantation for enhanced immune checkpoint inhibitors efficacy. Gut Microbes. 2025;17(1):2452277. Liu C, Xie J, Lin B, Tian W, Wu Y, Xin S, et al. Pan-Cancer Single-Cell and Spatial-Resolved Profiling Reveals the Immunosuppressive Role of APOE+ Macrophages in Immune Checkpoint Inhibitor Therapy. Adv Sci (Weinh). 2024;11(23):e2401061. Lopci E. Immunotherapy Monitoring with Immune Checkpoint Inhibitors Based on [(18)F]FDG PET/CT in Metastatic Melanomas and Lung Cancer. J Clin Med. 2021;10:21. Menche C, Schuhwerk H, Armstark I, Gupta P, Fuchs K, van Roey R, et al. ZEB1-mediated fibroblast polarization controls inflammation and sensitivity to immunotherapy in colorectal cancer. EMBO Rep. 2024;25(8):3406–31. He J, Cui H, Jiang G, Fang L, Hao J. Knowledge mapping of trained immunity/innate immune memory: Insights from two decades of studies. Hum Vaccin Immunother. 2024;20(1):2415823. Yu L, Xu C, Zhang M, Zhou Y, Hu Z, Li L, et al. Top 100 cited research on COVID-19 vaccines: A bibliometric analysis and evidence mapping. Hum Vaccin Immunother. 2024;20(1):2370605. Zhao Z, Hu B, Xu K, Jiang Y, Xu X, Liu Y. A quantitative analysis of artificial intelligence research in cervical cancer: a bibliometric approach utilizing CiteSpace and VOSviewer. Front Oncol. 2024;14:1431142. Cai H, Du R, Zhang J, Wang X, Li W, Yang K, et al. Knowledge domain and trends in treatment-resistant schizophrenia (TRS) research based on CiteSpace bibliometrics analysis. Front Pharmacol. 2024;15:1478625. Lai Y, Jiang J, Zhang H, Gong K. Bibliometric Analysis of Curcumin Based on CiteSpace: Landscapes, Hotspots, and Frontiers. Drug Des Devel Ther. 2024;18:5743–58. Zhang L, Cui S, Xi X, Bi H, Huang B. Research hotspots and frontiers of essential tremor from 2013 to 2023: a visualization analysis based on CiteSpace. Front Aging Neurosci. 2024;16:1380851. Niu J, Deng R, Dong Z, Yang X, Xing Z, Yu Y, et al. Mapping the landscape of AI and ML in vaccine innovation: A bibliometric study. Hum Vaccin Immunother. 2025;21(1):2501358. Yang X, Kang J, Xing Z, Sun Y, Liu Z, Li N, et al. Bibliometric analysis of RNA vaccines for cancer. Hum Vaccin Immunother. 2023;19(2):2231333. Lai B, Jiang H, Gao Y, Zhou X. Research trends and hotspots of myositis ossificans: a bibliometric analysis from 1993 to 2022. EFORT Open Rev. 2024;9(7):589–99. Peng T, Yang Y, Ma J, Xu P, Xie X, Hu N, et al. Dementia and metabolic syndrome: a bibliometric analysis. Front Aging Neurosci. 2024;16:1400589. Yang C, Liu H, Feng X, Shi H, Jiang Y, Li J, et al. Research hotspots and frontiers of neoadjuvant therapy in triple-negative breast cancer: a bibliometric analysis of publications between 2002 and 2023. Int J Surg. 2024;110(8):4976–92. Bang YH, Lee CK, Bang K, Kim HD, Kim KP, Jeong JH, et al. Artificial Intelligence-Powered Spatial Analysis of Tumor-Infiltrating Lymphocytes as a Potential Biomarker for Immune Checkpoint Inhibitors in Patients with Biliary Tract Cancer. Clin Cancer Res. 2024;30(20):4635–43. Bareche Y, Kelly D, Abbas-Aghababazadeh F, Nakano M, Esfahani PN, Tkachuk D, et al. Leveraging big data of immune checkpoint blockade response identifies novel potential targets. Ann Oncol. 2022;33(12):1304–17. Chang TG, Cao Y, Sfreddo HJ, Dhruba SR, Lee SH, Valero C, et al. LORIS robustly predicts patient outcomes with immune checkpoint blockade therapy using common clinical, pathologic and genomic features. Nat Cancer. 2024;5(8):1158–75. Chen P, Zhang J, Wu J. Artificial Intelligence in Digital Pathology to Advance Cancer Immunotherapy. 21 Century Pathol. 2022;2(3). Jiang L, Wang J, Wang Y, Yang H, Kong L, Wu Z, et al. Bibliometric and LDA analysis of acute rejection in liver transplantation: Emerging trends, immunotherapy challenges, and the role of artificial intelligence. Cell Transpl. 2025;34:9636897251325628. Mu W, Jiang L, Shi Y, Tunali I, Gray JE, Katsoulakis E et al. Non-invasive measurement of PD-L1 status and prediction of immunotherapy response using deep learning of PET/CT images. J Immunother Cancer. 2021;9(6). Prelaj A, Miskovic V, Zanitti M, Trovo F, Genova C, Viscardi G, et al. Artificial intelligence for predictive biomarker discovery in immuno-oncology: a systematic review. Ann Oncol. 2024;35(1):29–65. Fraunhoffer N, Hammel P, Conroy T, Nicolle R, Bachet JB, Harlé A, et al. Development and validation of AI-assisted transcriptomic signatures to personalize adjuvant chemotherapy in patients with pancreatic ductal adenocarcinoma. Ann Oncol. 2024;35(9):780–91. Fomin V, So WV, Barbieri RA, Hiller-Bittrolff K, Koletou E, Tu T et al. Machine learning identifies clinical tumor mutation landscape pathways of resistance to checkpoint inhibitor therapy in NSCLC. J Immunother Cancer. 2025;13(3). Ljubimov VA, Sun T, Wang J, Li L, Wang PZ, Ljubimov AV, et al. Blood-brain barrier crossing biopolymer targeting c-Myc and anti-PD-1 activate primary brain lymphoma immunity: Artificial intelligence analysis. J Control Release. 2025;381:113611. Cannarozzi AL, Latiano A, Massimino L, Bossa F, Giuliani F, Riva M, et al. Inflammatory bowel disease genomics, transcriptomics, proteomics and metagenomics meet artificial intelligence. United Eur Gastroenterol J. 2024;12(10):1461–80. Chen B, Sun X, Huang H, Feng C, Chen W, Wu D. An integrated machine learning framework for developing and validating a diagnostic model of major depressive disorder based on interstitial cystitis-related genes. J Affect Disord. 2024;359:22–32. Hoang DT, Dinstag G, Shulman ED, Hermida LC, Ben-Zvi DS, Elis E, et al. A deep-learning framework to predict cancer treatment response from histopathology images through imputed transcriptomics. Nat Cancer. 2024;5(9):1305–17. Wang M, Wang Y, Li Y, Zhang C, Li C, Bi N. Interpretable artificial intelligence based on immunoregulation-related genes predicts prognosis and immunotherapy response in lung adenocarcinoma. Front Bioinform. 2025;5:1613761. He X, Liu X, Zuo F, Shi H, Jing J. Artificial intelligence-based multi-omics analysis fuels cancer precision medicine. Semin Cancer Biol. 2023;88:187–200. Li J, Li L, You P, Wei Y, Xu B. Towards artificial intelligence to multi-omics characterization of tumor heterogeneity in esophageal cancer. Semin Cancer Biol. 2023;91:35–49. Boretti A. Improving chimeric antigen receptor T-cell therapies by using artificial intelligence and internet of things technologies: A narrative review. Eur J Pharmacol. 2024;974:176618. Jumper J, Evans R, Pritzel A, Green T, Figurnov M, Ronneberger O, et al. Highly accurate protein structure prediction with AlphaFold. Nature. 2021;596(7873):583–9. Ahluwalia VS, Parikh RB. Explainable Machine Learning to Predict Treatment Response in Advanced Non-Small Cell Lung Cancer. JCO Clin Cancer Inf. 2025;9:e2400157. Caballero Mateos AM, de la Cañadas GA, Gros B. Paradigm Shift in Inflammatory Bowel Disease Management: Precision Medicine, Artificial Intelligence, and Emerging Therapies. J Clin Med. 2025;14(5). He YJ, Liu PL, Wei T, Liu T, Li YF, Yang J, et al. Artificial intelligence in kidney transplantation: a 30-year bibliometric analysis of research trends, innovations, and future directions. Ren Fail. 2025;47(1):2458754. Kim J, Lee BJ, Moon S, Lee H, Lee J, Kim BS, et al. Strategies to Overcome Hurdles in Cancer Immunotherapy. Biomater Res. 2024;28:0080. Vivas AJ, Boumediene S, Tobón GJ. Predicting autoimmune diseases: A comprehensive review of classic biomarkers and advances in artificial intelligence. Autoimmun Rev. 2024;23(9):103611. Chen Z, Chen Y, Sun Y, Tang L, Zhang L, Hu Y, et al. Predicting gastric cancer response to anti-HER2 therapy or anti-HER2 combined immunotherapy based on multi-modal data. Signal Transduct Target Ther. 2024;9(1):222. Cheng Z, Du Y, Yu L, Yuan Z, Tian J. Application of Noninvasive Imaging to Combined Immune Checkpoint Inhibitors for Breast Cancer: Facts and Future. Mol Imaging Biol. 2022;24(2):264–79. Ciccolini J, Benzekry S, Barlesi F. Deciphering the response and resistance to immune-checkpoint inhibitors in lung cancer with artificial intelligence-based analysis: when PIONeeR meets QUANTIC. Br J Cancer. 2020;123(3):337–8. Lee S, Chu Y, Ryu J, Park YJ, Yang S, Koh SB. Artificial Intelligence for Detection of Cardiovascular-Related Diseases from Wearable Devices: A Systematic Review and Meta-Analysis. Yonsei Med J. 2022;63(Suppl):S93–107. Zuo D, Yang L, Jin Y, Qi H, Liu Y, Ren L. Machine learning-based models for the prediction of breast cancer recurrence risk. BMC Med Inf Decis Mak. 2023;23(1):276. Bijlsma S, Maal T, Rubbert C, Mannil M, Meijer A, van der Kolk A, et al. AI radiomics predicts spatial glioma recurrence on preoperative MRI: a systematic review. Eur J Radiol. 2025;193:112412. Additional Declarations No competing interests reported. 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-8873872","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":602425621,"identity":"22a1586e-f5aa-4038-9268-ef75a5ff9372","order_by":0,"name":"Jian Kang","email":"","orcid":"","institution":"Second Hospital of Anhui Medical University","correspondingAuthor":false,"prefix":"","firstName":"Jian","middleName":"","lastName":"Kang","suffix":""},{"id":602425622,"identity":"29bdd4c9-9e11-4ce6-b5b7-01e1185cca82","order_by":1,"name":"Rui Tang","email":"","orcid":"","institution":"Heilongjiang Provincial Hospital","correspondingAuthor":false,"prefix":"","firstName":"Rui","middleName":"","lastName":"Tang","suffix":""},{"id":602425623,"identity":"90b36c61-9268-4fa2-80b9-2217f5783524","order_by":2,"name":"Dongqi Li","email":"","orcid":"","institution":"Heilongjiang Provincial Hospital","correspondingAuthor":false,"prefix":"","firstName":"Dongqi","middleName":"","lastName":"Li","suffix":""},{"id":602425624,"identity":"173d23df-0201-4437-a858-5222cf880073","order_by":3,"name":"Li Ma","email":"","orcid":"","institution":"Heilongjiang Nursing College","correspondingAuthor":false,"prefix":"","firstName":"Li","middleName":"","lastName":"Ma","suffix":""},{"id":602425625,"identity":"a4a8a427-1363-4460-a02c-15b763438d8d","order_by":4,"name":"Zhiqiang Zhang","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABGklEQVRIie3RsUrEMBjA8ZTIdw7f2TVF6TMECoei3D2IS0PAyarg4uBQEepSbj7RhxAcxC0lUBcfoHLCnQhODp1uPE0LN6bcKJj/0rTkx9cQQlyuvxhVRMUIOLq5mptX1X5knQRiT9U7WyFHzdcmtJgchBFnck3iA3KNxwPxFHwCI5fvh1zRYopkeGIjQdaQ1yPxfCcNKb+SBwVyH4k8txE+y7nu56VIp6clI6ANwcE2EiVSCxmVZkp/+SPSN22mLBviLzoJN2cpJggRrygwL2unQCdhJZypGiEMckl3xVgntxqivXsurcTP6GPdXKXf015VL3Qyfrn+qL4vhlZCyCZfrTZY3Dxo+8PW/abefLWiddc+l8vl+r/9AgMyXDY9F6c3AAAAAElFTkSuQmCC","orcid":"","institution":"Second Hospital of Anhui Medical University","correspondingAuthor":true,"prefix":"","firstName":"Zhiqiang","middleName":"","lastName":"Zhang","suffix":""}],"badges":[],"createdAt":"2026-02-13 16:23:11","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8873872/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8873872/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":104252089,"identity":"27c13ee4-5ed4-4bb5-8105-6e508adc21d0","added_by":"auto","created_at":"2026-03-09 16:17:13","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":877067,"visible":true,"origin":"","legend":"\u003cp\u003eTitle: Flowchart of the search strategy in screening articles\u003c/p\u003e\n\u003cp\u003eLegend: The figure showed the articles were selected.\u003c/p\u003e","description":"","filename":"image1.png","url":"https://assets-eu.researchsquare.com/files/rs-8873872/v1/813071c7ad51379d02cd76c8.png"},{"id":104252102,"identity":"4388ef1e-f0a7-4993-b537-437634b981ca","added_by":"auto","created_at":"2026-03-09 16:17:16","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":542364,"visible":true,"origin":"","legend":"\u003cp\u003eTitle: Annual output of research of AI in Immune checkpoint inhibitors\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eLegend: \u003c/strong\u003eThis figure illustrates the annual output of research articles on AI in the field of Immune checkpoint inhibitors.\u003c/p\u003e","description":"","filename":"image2.png","url":"https://assets-eu.researchsquare.com/files/rs-8873872/v1/b8b4e02d922268549c3ae22f.png"},{"id":104252277,"identity":"9ea6dead-cf6c-4309-8f6b-288a6ace9e00","added_by":"auto","created_at":"2026-03-09 16:17:46","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":122306,"visible":true,"origin":"","legend":"\u003cp\u003eTitle: Country Collaboration Map and Corresponding Author’s Countries\u003c/p\u003e\n\u003cp\u003eLegend: This figure presents a map visualizing international collaborations and highlights the countries of corresponding authors, offering insights into the geographical distribution and collaborative patterns of research in this field.\u003c/p\u003e","description":"","filename":"image3.png","url":"https://assets-eu.researchsquare.com/files/rs-8873872/v1/59655de31d79847abe984acf.png"},{"id":104252175,"identity":"a637d3b0-a2c8-4f1c-be35-67bc3903ed33","added_by":"auto","created_at":"2026-03-09 16:17:29","extension":"png","order_by":4,"title":"Figure 4","display":"","copyAsset":false,"role":"figure","size":78303,"visible":true,"origin":"","legend":"\u003cp\u003eTitle: Top Relevant Affiliations and Their Production in AI in ICIs Research\u003c/p\u003e\n\u003cp\u003eLegends Figure 4A: Displays the top ten most relevant institutions engaged in AI research related to immune checkpoint inhibitors (ICIs).\u003c/p\u003e\n\u003cp\u003eFigure 4B: Shows the research output of the top five institutions over time, illustrating their contributions and productivity in this domain.\u003c/p\u003e","description":"","filename":"image4.png","url":"https://assets-eu.researchsquare.com/files/rs-8873872/v1/4393206d755fc64a4fc6636b.png"},{"id":104252037,"identity":"25f58877-ac89-4ed9-8b00-cd146e4386bb","added_by":"auto","created_at":"2026-03-09 16:16:55","extension":"png","order_by":5,"title":"Figure 5","display":"","copyAsset":false,"role":"figure","size":545088,"visible":true,"origin":"","legend":"\u003cp\u003eTitle: Key Research Sources in AI in ICIs Research\u003c/p\u003e\n\u003cp\u003eLegend: Figure 5A: Identifies the ten most significant sources of information in the field of AI applied to ICIs research.\u003c/p\u003e\n\u003cp\u003eFigure 5B: Lists the ten most frequently cited sources within the local research context, indicating their influence and impact on the field.\u003c/p\u003e","description":"","filename":"image5.png","url":"https://assets-eu.researchsquare.com/files/rs-8873872/v1/217518659e8054fb62b9fe40.png"},{"id":104252030,"identity":"6b3f95e2-b2df-4fb6-8085-b6d9d8b84205","added_by":"auto","created_at":"2026-03-09 16:16:48","extension":"png","order_by":6,"title":"Figure 6","display":"","copyAsset":false,"role":"figure","size":381175,"visible":true,"origin":"","legend":"\u003cp\u003eTitle: Most Relevant and Locally Cited Authors in AI in ICIs Research\u003c/p\u003e\n\u003cp\u003eLegend:\u003c/p\u003e\n\u003cp\u003eFigure 6A : Highlights the ten most influential authors in the field of AI research related to ICIs.\u003c/p\u003e\n\u003cp\u003eFigure 6B: Showcases the ten most cited authors within the local research community, recognizing their scholarly contributions.\u003c/p\u003e","description":"","filename":"image6.png","url":"https://assets-eu.researchsquare.com/files/rs-8873872/v1/9214ffe8d218786d0c5b0319.png"},{"id":104252176,"identity":"6dea5bae-01a3-4a2b-83c1-ab01660f43e3","added_by":"auto","created_at":"2026-03-09 16:17:30","extension":"png","order_by":7,"title":"Figure 7","display":"","copyAsset":false,"role":"figure","size":540491,"visible":true,"origin":"","legend":"\u003cp\u003eKeyword Analysis and Clustering in AI in ICIs Research\u003c/p\u003e\n\u003cp\u003eLegend:\u003c/p\u003e\n\u003cp\u003eFigure 7A: Provides a keyword visualization generated by VOSviewer, offering a graphical representation of the most important terms and their relationships in the research field.\u003c/p\u003e\n\u003cp\u003eFigure 7B: Displays the frequency and distribution of keywords analyzed by the bibliometrix package, providing quantitative insights into keyword usage.\u003c/p\u003e\n\u003cp\u003eFigure 7C: Presents a keyword clustering map generated by CiteSpace, revealing thematic groups and research fronts within the field of AI applied to ICIs.\u003c/p\u003e","description":"","filename":"image7.png","url":"https://assets-eu.researchsquare.com/files/rs-8873872/v1/cb8171c06279c0b28b5f1197.png"},{"id":104252036,"identity":"4f166bf2-6ce6-4221-a1e2-0bf57c627e3b","added_by":"auto","created_at":"2026-03-09 16:16:55","extension":"jpeg","order_by":8,"title":"Figure 8","display":"","copyAsset":false,"role":"figure","size":163297,"visible":true,"origin":"","legend":"\u003cp\u003e\u003cstrong\u003eTitle:\u003c/strong\u003e The Six Key Applications of AI in ICIs Research\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eLegend:\u003c/strong\u003e It illustrates the six key applications of AI in ICIs research, including identifying novel gene targets, discovering new cell receptor structures, designing new immune checkpoint inhibitor structures, simulating immune checkpoint inhibitor experiments, monitoring the effects of immune checkpoint inhibitor drugs, and fusing multimodal real-world complex data for individualized patient treatment.\u003c/p\u003e","description":"","filename":"image8.jpeg","url":"https://assets-eu.researchsquare.com/files/rs-8873872/v1/ce5ccc6c2d7b1e13b659acb7.jpeg"},{"id":105369733,"identity":"4e74e8b6-bfa9-4165-9297-ca2140569bed","added_by":"auto","created_at":"2026-03-25 09:14:23","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":3815451,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8873872/v1/34ceb6f4-a7a6-4750-ae6e-02c5e5a53c18.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Artificial Intelligence in Immune Checkpoint Inhibitor Research: A Bibliometric Analysis of the Landscape","fulltext":[{"header":"Introduction","content":"\u003cp\u003eImmune checkpoint inhibitors (ICIs) significantly improve patient prognoses by activating the immune system (\u003cspan additionalcitationids=\"CR2\" citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e). However, their efficacy varies widely, while they may induce immune-related adverse events (irAEs), underscoring the critical need for precise dosing studies (\u003cspan additionalcitationids=\"CR5 CR6 CR7 CR8\" citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e). Traditional immune biomarker detection methods are costly and their accuracy has been questioned (\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e). Meanwhile, these methods struggle to capture the heterogeneity and dynamic changes within the tumor microenvironment (TME) (\u003cspan additionalcitationids=\"CR11\" citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e). Recently, artificial intelligence (AI) has emerged as a transformative tool to address these challenges (\u003cspan additionalcitationids=\"CR14 CR15 CR16 CR17\" citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e). By integrating multi-omics data, spatial genomics analysis, and clinical outcomes, AI is increasingly unraveling the complex interplay between immune checkpoint inhibitor dosage, therapeutic efficacy, and toxicity (\u003cspan additionalcitationids=\"CR20 CR21 CR22\" citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e23\u003c/span\u003e).\u003c/p\u003e \u003cp\u003eThe advent of novel systemic treatments, particularly ICIs, has markedly expanded the therapeutic arsenal for solid tumors. However, their clinical application reveals considerable variability in patient outcomes, highlighting the urgent need for reliable predictors of response. In renal cell carcinoma, for instance, clinicopathological features such as sarcomatoid differentiation and International Metastatic RCC Database Consortium (IMDC) risk scores significantly influence survival in patients treated with first-line ICI\u0026ndash;tyrosine kinase inhibitor combinations (\u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e24\u003c/span\u003e, \u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e25\u003c/span\u003e). Real-world data further underscore the differential effectiveness of immune-oncology combinations across risk strata, emphasizing the importance of risk-adapted therapeutic strategies (\u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e24\u003c/span\u003e). Beyond tumor-specific factors, systemic host conditions also modulate treatment efficacy. The interplay between cancer risk, chronic inflammation, and metabolic syndrome constitutes a complex axis that can impact immune responses and treatment outcomes (\u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e26\u003c/span\u003e). Additionally, patient-specific prognostic tools such as the cachexia index (CXI) have emerged as valuable biomarkers, reflecting the systemic metabolic and inflammatory burden that influences survival and potentially ICI responsiveness (\u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e27\u003c/span\u003e). In hepatocellular carcinoma, the combination of ICIs with antiangiogenic agents has become a first-line standard, yet challenges persist in identifying which patients will derive the greatest benefit, necessitating a deeper understanding of the underlying biological and clinical determinants (\u003cspan citationid=\"CR28\" class=\"CitationRef\"\u003e28\u003c/span\u003e).\u003c/p\u003e \u003cp\u003eCancer immunotherapy has advanced significantly with the introduction of new systemic treatments, such as immune checkpoint inhibitors. These treatments have revolutionized treatment options for cancers like gastric cancer, hepatocellular carcinoma, and renal cell carcinoma. However, challenges remain in optimizing therapeutic strategies and managing adverse events.\u003c/p\u003e \u003cp\u003eRecent studies have highlighted the importance of understanding the DNA damage response alterations in gastric cancer, which could provide new targets for therapy (\u003cspan citationid=\"CR29\" class=\"CitationRef\"\u003e29\u003c/span\u003e). In hepatocellular carcinoma, immunotherapy faces challenges, including the identification of effective biomarkers and the overcoming of resistance mechanisms (\u003cspan citationid=\"CR30\" class=\"CitationRef\"\u003e30\u003c/span\u003e). Moreover, the associations between cancer risk, inflammation, and metabolic syndrome have been explored, emphasizing the need for a comprehensive approach to cancer treatment (\u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e26\u003c/span\u003e). The prognostic significance of the cachexia index in cancer patients has also been recognized, indicating its potential as a biomarker for treatment outcomes (\u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e27\u003c/span\u003e). Furthermore, real-world outcomes of patients with advanced renal cell carcinoma treated with immune-oncology combinations have varied according to risk groups. This finding highlights the importance of personalized treatment strategies (\u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e24\u003c/span\u003e).\u003c/p\u003e \u003cp\u003eAs the field of tumor immunotherapy rapidly expands, it has become imperative to conduct a comprehensive bibliometric analysis of ICIs-related and AI research. Bibliometrics offers a systematic approach to quantify and organize the exponential growth of publications on ICIs, providing a macroscopic perspective on research trends, hotspots, and future directions (\u003cspan additionalcitationids=\"CR32 CR33 CR34 CR35\" citationid=\"CR31\" class=\"CitationRef\"\u003e31\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR36\" class=\"CitationRef\"\u003e36\u003c/span\u003e). Temporal analyses of publication volumes, geographic distributions, and institutional collaborations reveal research patterns, major contributors, and regional synergies (\u003cspan additionalcitationids=\"CR32 CR33 CR34 CR35\" citationid=\"CR31\" class=\"CitationRef\"\u003e31\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR36\" class=\"CitationRef\"\u003e36\u003c/span\u003e). Such insights facilitate optimized global resource allocation, which minimizes redundancy, enhances research efficiency, and ultimately accelerates scientific progress.\u003c/p\u003e \u003cp\u003eFurthermore, AI enables analysis of multidimensional data from scientific literature to explore ICIs mechanisms, dose-response relationships, and adverse event profiles in depth. For example, machine learning (ML) algorithms can model and predict the spatiotemporal dynamics of immune cells and cytokines within the TME, elucidate their correlation with ICIs dosage, and inform precise dosing strategies (\u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e, \u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e, \u003cspan additionalcitationids=\"CR38 CR39 CR40 CR41 CR42\" citationid=\"CR37\" class=\"CitationRef\"\u003e37\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR43\" class=\"CitationRef\"\u003e43\u003c/span\u003e). These capabilities support clinical decision-making, dose optimization, and risk mitigation strategies (\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e, \u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e, \u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e, \u003cspan additionalcitationids=\"CR42\" citationid=\"CR41\" class=\"CitationRef\"\u003e41\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR43\" class=\"CitationRef\"\u003e43\u003c/span\u003e).\u003c/p\u003e \u003cp\u003eIn conclusion, integrating AI into bibliometric analyses of ICIs research is a key advancement that supports precise dosing studies and enables personalized tumor immunotherapy. This interdisciplinary approach holds immense potential to improve clinical oncology outcomes by bridging translational gaps between preclinical discoveries and clinical applications.\u003c/p\u003e"},{"header":"Methods","content":"\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e \u003ch2\u003eSearch Strategy\u003c/h2\u003e \u003cp\u003eWe conducted a literature search in the Web of Science Core Collection (WoSCC) database (\u003cspan class=\"ExternalRef\"\u003e\u003cspan class=\"RefSource\"\u003ehttps://www.webofscience.com/wos/woscc/basic-search\u003c/span\u003e\u003cspan address=\"https://www.webofscience.com/wos/woscc/basic-search\" targettype=\"URL\" class=\"RefTarget\"\u003e\u003c/span\u003e\u003c/span\u003e) on 30 May 2025. The search strategy followed the criteria outlined in Fig.\u0026nbsp;\u003cspan refid=\"Fig1\" class=\"InternalRef\"\u003e1\u003c/span\u003e, restricting document types restricted to \"articles\" and \"reviews\". As a result, a total of 597 publications were selected for subsequent bibliometric analysis.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec4\" class=\"Section2\"\u003e \u003ch2\u003eData Analysis\u003c/h2\u003e \u003cp\u003eVOSviewer (version 1.6.20) was utilized for bibliometric analysis, extracting key information from numerous ICIs-related publications (\u003cspan additionalcitationids=\"CR45\" citationid=\"CR44\" class=\"CitationRef\"\u003e44\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR46\" class=\"CitationRef\"\u003e46\u003c/span\u003e). This software facilitated keyword co-occurrence analysis. The maps generated by VOSviewer used nodes to represent entities like keywords; the size of these nodes indicated the number of ICIs publications associated with each item, and the color signified the classification (\u003cspan additionalcitationids=\"CR45\" citationid=\"CR44\" class=\"CitationRef\"\u003e44\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR46\" class=\"CitationRef\"\u003e46\u003c/span\u003e).\u003c/p\u003e \u003cp\u003eCiteSpace (version 6.3.1), developed by Professor Chen, was another tool used for bibliometric analysis and visualization in immunosuppressant research (\u003cspan additionalcitationids=\"CR48\" citationid=\"CR47\" class=\"CitationRef\"\u003e47\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR49\" class=\"CitationRef\"\u003e49\u003c/span\u003e). Specifically, it was used to analyze references with \u0026ldquo;\u003cb\u003eCitation Bursts\u003c/b\u003e\u0026rdquo; to identify significant and influential publications in the field.\u003c/p\u003e \u003cp\u003eThe R package \"bibliometrix\" (version 4.3.0) was employed to analyze thematic evolution and to construct a global distribution network of ICIs publications (\u003cspan additionalcitationids=\"CR51 CR52 CR53\" citationid=\"CR50\" class=\"CitationRef\"\u003e50\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR54\" class=\"CitationRef\"\u003e54\u003c/span\u003e). It comprehensively analyzed ICIs research across countries, institutions, publishers, and authors, offering insights into research output, impact, key players, collaborative networks, and publication trends. The quartile and impact factor of journals were obtained from the Journal Citation Reports 2024 and were used to assess the quality and influence of ICIs-related publications.\u003c/p\u003e \u003cp\u003eAdditionally, Microsoft Office Excel 2021 was used for quantitative analysis of ICIs publications, enabling researchers to organize, process, and analyze data efficiently. By applying AI techniques, researchers gained deeper insights into ICIs research trends, collaborations, and knowledge evolution, enabling a comprehensive understanding of the current status and future directions of AI-driven ICIs innovation.\u003c/p\u003e \u003c/div\u003e\n\u003ch3\u003eQuantitative Analysis of Publications\u003c/h3\u003e\n\u003cp\u003eFigure \u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003e presented a bar chart the annual publication trends of AI in ICIs from 2016 to 2025. In 2016, the number of publications was 1. By 2018, this number had gradually increased to approximately 8. The upward trend continued in 2021, with the number climbing to around 55. In 2024, publications increased to around 175. As of 2025, preliminary data showed the number of publications had reached 123, indicating ongoing growth. Each bar represented the number of publications for that year, with the y-axis showing publication counts and the x-axis indicating years from 2016 to 2025, collectively illustrating the continuous and remarkable growth in AI research on ICIs during this period.\u003c/p\u003e\n\u003ch3\u003eCountry and Affiliations Analysis\u003c/h3\u003e\n\u003cp\u003eFigure \u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003eA showed the Country Collaboration Map for AI in ICIs research. The US had the most extensive research collaborations worldwide, followed by China, which also showed broad but comparatively fewer global partnerships. Figure\u0026nbsp;\u003cspan refid=\"Fig3\" class=\"InternalRef\"\u003e3\u003c/span\u003eB, focusing on Corresponding Authors' Countries, showed that Chinese authors conducted more independent research, while US authors participated more in international collaborations. Moreover, the number of Chinese scholars had surpassed that of US scholars.\u003c/p\u003e \u003cp\u003eFigure \u003cspan refid=\"Fig5\" class=\"InternalRef\"\u003e4\u003c/span\u003eA showed the top ten affiliations ranked by the number of publications in AI in ICIs research. Sun Yat-sen University ranked first with 77 articles, followed by Harvard University with 59, and Harvard Medical School affiliates with 47. Figure\u0026nbsp;\u003cspan refid=\"Fig5\" class=\"InternalRef\"\u003e4\u003c/span\u003eB illustrated the publication trends over time for the top five affiliations. The chart clearly showed an increasing number of publications, with each color representing a different institution. This highlighted the dynamic and growing contributions of leading research centers in AI in ICIs.\u003c/p\u003e\n\u003ch3\u003eSources and Cited Sources\u003c/h3\u003e\n\u003cp\u003eFigure \u003cspan refid=\"Fig7\" class=\"InternalRef\"\u003e5\u003c/span\u003eA presented the top ten most relevant sources in the field of AI applications in ICIs research. The top three sources were \u003cem\u003eFrontiers in Immunology\u003c/em\u003e (51 articles), \u003cem\u003eCancers\u003c/em\u003e (44 articles), and \u003cem\u003eFrontiers in Oncology\u003c/em\u003e (28 articles). These journals had published many studies, significantly contributing to the research field.\u003c/p\u003e \u003cp\u003eFigure \u003cspan refid=\"Fig7\" class=\"InternalRef\"\u003e5\u003c/span\u003eB showed the top ten most locally cited sources. The top three in this category were The New England Journal of Medicine with 1,208 citations, Journal of Clinical Oncology with 991 citations, and Clinical Cancer Research with 916 citations. These sources were highly cited in the field, highlighting their influence and lasting contribution to advancing AI-related ICIs research.\u003c/p\u003e \u003cdiv id=\"Sec8\" class=\"Section2\"\u003e \u003ch2\u003eAuthors and Co-authors\u003c/h2\u003e \u003cp\u003eFigure \u003cspan refid=\"Fig10\" class=\"InternalRef\"\u003e6\u003c/span\u003eA showed the top ten Most Relevant Authors in AI in ICIs research. The top three authors were Kim S, Li L, and Lee SH, with 13, 12, and 11 publications respectively. Park S and Wang Y each contributed 11 publications. Figure\u0026nbsp;\u003cspan refid=\"Fig10\" class=\"InternalRef\"\u003e6\u003c/span\u003eB displayed the top ten Most Local Cited Authors. Park S was the most cited with 61, followed by Tian J with 55, and Kim S with 51 citations.\u003c/p\u003e \u003cp\u003e \u003cb\u003eReference with Citation Bursts\u003c/b\u003e \u003c/p\u003e \u003cp\u003eFigure \u003cspan refid=\"Fig14\" class=\"InternalRef\"\u003e7\u003c/span\u003eA presented a keyword visualization generated by VOSviewer, highlighting key themes in AI research within ICIs. The visualization underscored the interconnectedness and prominence of topics such as immune response prediction, patient stratification, and toxicity management.\u003c/p\u003e \u003cp\u003eFigure \u003cspan refid=\"Fig14\" class=\"InternalRef\"\u003e7\u003c/span\u003eB, generated using the bibliometrix package, analyzed the frequency and distribution of keywords in the field. It revealed the prevalence of terms such as \"\u003cb\u003ecancer\u003c/b\u003e\", \"\u003cb\u003eexpression\u003c/b\u003e\", and \"\u003cb\u003esurvival\u003c/b\u003e\", offering insights into core concepts and current research focuses.\u003c/p\u003e \u003cp\u003eFigure \u003cspan refid=\"Fig14\" class=\"InternalRef\"\u003e7\u003c/span\u003eC showed a keyword clustering map created by CiteSpace, highlighting application areas such as AI-driven treatment optimization and biomarker discovery. The clustering provided valuable insights into research themes focused on improving therapeutic outcomes and a better understanding of immune mechanisms. Together, these visualizations offered a clear overview of key topics and their relationships within AI applications in ICIs research. They highlighted the field\u0026rsquo;s dynamic and multifaceted nature.\u003c/p\u003e \u003c/div\u003e"},{"header":"Discussion","content":"\u003cp\u003eThe integration of AI and bibliometrics in the study of ICIs represents a significant advancement in immunotherapy research. It provides a comprehensive framework to analyze the evolution, current trends, and future directions of ICIs research (\u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e, \u003cspan additionalcitationids=\"CR56 CR57 CR58\" citationid=\"CR55\" class=\"CitationRef\"\u003e55\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR59\" class=\"CitationRef\"\u003e59\u003c/span\u003e). Our bibliometric analysis unveils the rapid growth in publications related to AI applications in ICIs, highlighting the escalating interest and investment in this domain. This section further explores the implications of our findings, focusing on the specific applications of AI in ICIs research, including the identification of novel gene targets, cell receptor structures, design of new ICIs structures, simulation of ICIs experiments, monitoring of drug efficacy, and the application of multimodal fusion for personalized treatment in real-world settings.\u003c/p\u003e \u003cp\u003eFigure \u003cspan refid=\"Fig2\" class=\"InternalRef\"\u003e2\u003c/span\u003e illustrates the rapid increase in publications over the past decade, which indicates growing enthusiasm and tangible progress in the field. This growth in research marks a fundamental shift in the approach to complex biological problems. AI has become an indispensable tool, enabling researchers to unravel the intricate mechanisms underlying ICIs and their interactions with the TME. The identification of novel gene targets and cell receptor structures, along with the design of new ICIs molecules, is an area where AI has shown particular promise.\u003c/p\u003e \u003cp\u003eHowever, the rapid proliferation of AI applications calls for cautious optimism. While the quantitative growth is impressive, the qualitative impact, especially regarding clinical translation, remains uneven. Our analysis suggests that many studies remain in the preclinical or early clinical validation stage, which highlights a persistent gap between computational promise and therapeutic reality. This finding underscores the need for more robust, interdisciplinary collaboration that prioritizes clinical relevance alongside algorithmic innovation. This observation underscores the need for more robust, interdisciplinary collaboration that prioritizes clinical relevance alongside algorithmic innovation.\u003c/p\u003e \u003cp\u003eThe application of AI in ICIs is rapidly evolving. Various types of AI tools are being deployed to address different tasks (\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e, \u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e). Convolutional neural networks (CNN) are commonly used for image analysis tasks, such as identifying tumor characteristics from radiological data (\u003cspan citationid=\"CR60\" class=\"CitationRef\"\u003e60\u003c/span\u003e). Graph-based models are useful for analyzing complex biological networks, including interactions between immune cells and cancer cells (\u003cspan citationid=\"CR61\" class=\"CitationRef\"\u003e61\u003c/span\u003e, \u003cspan citationid=\"CR62\" class=\"CitationRef\"\u003e62\u003c/span\u003e). Each AI tool has its own strengths and limitations, and the choice depends on the specific task.\u003c/p\u003e \u003cp\u003eWe believe that selecting AI methodologies should consider not only technical performance but also biological plausibility and clinical interpretability. For instance, while deep learning models often achieve high predictive accuracy, their \u0026ldquo;black-box\u0026rdquo; nature can reduce clinician trust and hinder their integration into routine practice. We advocate for a balanced approach that combines high-performance AI with explainable AI (XAI) techniques, ensuring that predictions are both accurate and interpretable\u0026mdash;a crucial step toward building clinician confidence and facilitating real-world adoption.\u003c/p\u003e \u003cp\u003eAs depicted in Fig.\u0026nbsp;\u003cspan refid=\"Fig15\" class=\"InternalRef\"\u003e8\u003c/span\u003e, AI has the potential to make significant contributions to six key areas of ICIs research.\u003c/p\u003e \u003cp\u003e \u003cb\u003e1. Finding New Gene Targets\u003c/b\u003e \u003c/p\u003e \u003cp\u003eAI technologies such as ML algorithms have shown great potential in identifying novel gene targets for immunotherapy (\u003cspan citationid=\"CR63\" class=\"CitationRef\"\u003e63\u003c/span\u003e, \u003cspan citationid=\"CR64\" class=\"CitationRef\"\u003e64\u003c/span\u003e). By analyzing complex, large-scale genomic and transcriptomic datasets, AI can uncover patterns and correlations that traditional methods often miss (\u003cspan additionalcitationids=\"CR66\" citationid=\"CR65\" class=\"CitationRef\"\u003e65\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR67\" class=\"CitationRef\"\u003e67\u003c/span\u003e). This capability enables researchers to pinpoint genes differentially expressed in response to ICIs, which may serve as biomarkers for treatment response or resistance. For instance, AI enhances ICI response prediction in LUAD by analyzing IRGs, improving prognostic accuracy(\u003cspan citationid=\"CR68\" class=\"CitationRef\"\u003e68\u003c/span\u003e).\u003c/p\u003e \u003cp\u003eAnalyzing multi-omics data shows that AI\u0026rsquo;s greatest strength is integrating different types of data(\u003cspan citationid=\"CR69\" class=\"CitationRef\"\u003e69\u003c/span\u003e). These include genomic, transcriptomic, proteomic, and clinical data, which AI combines into a unified predictive framework(\u003cspan citationid=\"CR69\" class=\"CitationRef\"\u003e69\u003c/span\u003e). Nevertheless, we have encountered challenges such as data heterogeneity and batch effects that can compromise the model\u0026rsquo;s generalizability(\u003cspan citationid=\"CR70\" class=\"CitationRef\"\u003e70\u003c/span\u003e). Moving forward, we emphasize the importance of standardizing data collection protocols and incorporating domain knowledge to guide feature selection, in order to enhance the biological relevance and robustness of AI-driven target discovery.\u003c/p\u003e \u003cp\u003e \u003cb\u003e2. Designing New ICIs plan\u003c/b\u003e \u003c/p\u003e \u003cp\u003eAnalyzing multi - omics data is essential for developing effective immunotherapies, through which novel biomarkers for predicting ICI responses can be identified by AI algorithms (\u003cspan citationid=\"CR55\" class=\"CitationRef\"\u003e55\u003c/span\u003e, \u003cspan citationid=\"CR71\" class=\"CitationRef\"\u003e71\u003c/span\u003e, \u003cspan citationid=\"CR72\" class=\"CitationRef\"\u003e72\u003c/span\u003e). Vast datasets will be analyzed by machine learning models(\u003cspan citationid=\"CR61\" class=\"CitationRef\"\u003e61\u003c/span\u003e). Explainable AI will also be employed to have these models validated, ensuring scientific credibility(\u003cspan citationid=\"CR73\" class=\"CitationRef\"\u003e73\u003c/span\u003e). Clinical trial design will be streamlined through this approach, allowing promising ICIs to be identified more rapidly. Ultimately, personalized and precise immunotherapy strategies are aimed to be delivered, improving patient outcomes in cancer treatment.\u003c/p\u003e \u003cp\u003e \u003cb\u003e3. Designing New Structures\u003c/b\u003e \u003c/p\u003e \u003cp\u003eAI is crucial for the rational design of new ICIs structures (74, 75). Using virtual screening and molecular docking simulations, AI algorithms can evaluate the binding affinity and specificity of potential drug candidates with their target receptors. These AI-driven methods significantly reduce the time and cost associated with traditional drug discovery processes. Moreover, AI-driven de novo drug design techniques can generate novel molecular structures with target properties, expanding the chemical space for ICIs development.\u003c/p\u003e \u003cp\u003e \u003cb\u003e4. Simulating ICIs Experiments\u003c/b\u003e \u003c/p\u003e \u003cp\u003eIn silico simulations of ICIs experiments provide a powerful way to predict drug efficacy and toxicity before performing costly and time-consuming in vitro or in vivo studies. AI models can simulate drugs and their pharmacokinetic and pharmacodynamic profiles, which reveal details of absorption, distribution, metabolism, and excretion (\u003cspan citationid=\"CR62\" class=\"CitationRef\"\u003e62\u003c/span\u003e, \u003cspan additionalcitationids=\"CR75 CR76\" citationid=\"CR74\" class=\"CitationRef\"\u003e74\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR77\" class=\"CitationRef\"\u003e77\u003c/span\u003e). Additionally, AI can model the complex interactions within the TME and predict how ICIs affect immune cell populations and cytokine levels. Such in silico simulations help optimize drug dosages and treatment regimens, thereby improving therapeutic outcomes.\u003c/p\u003e \u003cp\u003e \u003cb\u003e5. Monitoring ICIs Drug Efficacy\u003c/b\u003e \u003c/p\u003e \u003cp\u003eMonitoring of ICIs drug efficacy is essential. It helps adjust treatment strategies and minimize adverse events (\u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e, \u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e, \u003cspan additionalcitationids=\"CR56 CR57\" citationid=\"CR55\" class=\"CitationRef\"\u003e55\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR58\" class=\"CitationRef\"\u003e58\u003c/span\u003e, \u003cspan additionalcitationids=\"CR79\" citationid=\"CR78\" class=\"CitationRef\"\u003e78\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR80\" class=\"CitationRef\"\u003e80\u003c/span\u003e). AI technologies, such as wearable devices and mobile health applications, enable continuous monitoring of patient data, including vital signs, symptoms, and laboratory results(\u003cspan citationid=\"CR81\" class=\"CitationRef\"\u003e81\u003c/span\u003e). ML algorithms analyze these data to detect early signs of treatment response or toxicity, enabling timely interventions(\u003cspan citationid=\"CR82\" class=\"CitationRef\"\u003e82\u003c/span\u003e). Moreover, AI-driven imaging analysis techniques, such as radiomics, can non-invasively assess tumor burden and treatment response, providing valuable information for clinical decision-making(\u003cspan citationid=\"CR83\" class=\"CitationRef\"\u003e83\u003c/span\u003e).\u003c/p\u003e \u003cp\u003e \u003cb\u003e6. Multimodal Fusion of Real-World Complex Data for Individualized Treatment\u003c/b\u003e \u003c/p\u003e \u003cp\u003eIntegrating multimodal data\u0026mdash;genomic, proteomic, imaging, and clinical\u0026mdash;enables a more comprehensive understanding of patient heterogeneity and treatment response (\u003cspan citationid=\"CR55\" class=\"CitationRef\"\u003e55\u003c/span\u003e, \u003cspan citationid=\"CR71\" class=\"CitationRef\"\u003e71\u003c/span\u003e). AI algorithms excel at analyzing these complex datasets to identify meaningful patterns that guide personalized treatment strategies. By leveraging multimodal fusion techniques\u0026mdash;methods that combine diverse data types\u0026mdash;researchers can develop predictive models that account for individual patient characteristics, such as genetic makeup, tumor microenvironment, and comorbidities. This approach enables the creation of genuinely personalized immunotherapy regimens, optimizing therapeutic outcomes while minimizing adverse effects.\u003c/p\u003e \u003cp\u003eWe believe multimodal data fusion is the most promising and challenging frontier in AI-driven ICIs research. In our own work, we observed that integrating imaging with genomic data significantly improves prediction of treatment response compared to unimodal approaches. Nevertheless, major challenges remain, including data privacy concerns, interoperability of healthcare systems, and the need for scalable computational infrastructure. Addressing these challenges will require not only technological innovation but also policy support, and cross-sector collaboration.\u003c/p\u003e \u003cp\u003eIdentifying practice-changing studies in AI-driven ICIs research highlights AI\u0026rsquo;s transformative potential in oncology. Many studies have advanced scientific knowledge and brought tangible changes to clinical practice (\u003cspan additionalcitationids=\"CR19\" citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e). These contributions highlight the importance of integrating AI into the development and application of ICIs, as this integration offers new tools for personalized treatment and improved patient outcomes. Future research should continue to build on these foundational studies. It should explore novel applications of AI and validate their impact in diverse clinical settings.\u003c/p\u003e \u003cp\u003eFrom our standpoint, success for AI in ICIs should not be measured by the number of publications or algorithms developed. Instead, it should be judged by tangible improvements in patient survival and quality of life. Therefore, we urge the research community to prioritize clinically meaningful endpoints and engage clinicians early in the AI development process. Such partnerships can ensure that AI tools are designed with real-world utility in mind, ultimately accelerating their adoption and impact in oncology practice.\u003c/p\u003e \u003cp\u003eDeploying AI models safely is a critical issue in the field of ICIs. Ethical concerns arise when AI models are applied in clinical settings because they significantly impact patient care. Ensuring model transparency is essential because it helps clinicians and researchers understand how AI models make decisions. Additionally, tackling dataset biases is crucial so that AI models remain fair and generalizable across diverse populations. Strategies to address these challenges include rigorously validating AI models, training them on diverse and representative datasets, and implementing ethical guidelines for AI use in healthcare.\u003c/p\u003e \u003cp\u003eAI has great potential to bridge the gap between preclinical research and clinical application, which is a critical need in immunotherapy (\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e, \u003cspan citationid=\"CR59\" class=\"CitationRef\"\u003e59\u003c/span\u003e, \u003cspan citationid=\"CR74\" class=\"CitationRef\"\u003e74\u003c/span\u003e). Efficiently translating lab findings into clinical practice is essential. AI-driven approaches can streamline this process. They help translate promising discoveries into tangible benefits for patients. However, integrating AI into clinical practice requires technical advancements. It also demands a shift in mindset among clinicians and researchers. Robust validation and regulatory frameworks must be established to ensure AI-driven tools are reliable, accurate, and safe.\u003c/p\u003e"},{"header":"Conclusion","content":"\u003cp\u003eIn conclusion, we are optimistic about the future of AI in ICIs. However, we remain mindful of the work ahead. Bibliometric trends show that the field is rapidly expanding, but true transformation depends on our ability to overcome the translational, ethical, and practical challenges mentioned earlier. As researchers and clinicians, we have a responsibility to steer AI development toward equitable, interpretable, and clinically impactful solutions, ensuring that the promise of AI translates into better outcomes for every patient facing cancer.\u003c/p\u003e"},{"header":"Declarations","content":"\u003cp\u003e\u003cstrong\u003e\u003cem\u003eFunds\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThis study was supported by the scientific research of the Heilongjiang Provincial Health Commission [grant number 20240404050045].\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003eAuthors\u0026rsquo; contributions\u0026nbsp;\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eJ.K. designed the study, drafted the initial manuscript, and created all original illustrations.\u003c/p\u003e\n\u003cp\u003eR. T., D. L., and L. M. reviewed the manuscript and improved English.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eAll data processing, statistical analyses, and interpretative synthesis of results were conducted by J.K. using validated methodological frameworks.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eZ. Z. provided critical review and substantive revisions to the manuscript regarding intellectual content.\u003c/p\u003e\n\u003cp\u003eAll authors finalized the manuscript, approved its submission, and take responsibility for the integrity of the work as presented.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003eConsent for publication\u0026nbsp;\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eNot applicable.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003eAvailability of data and materials\u003c/em\u003e\u003c/strong\u003e\u003cstrong\u003e\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe original contributions of this study are included in the article and supplementary material at http://www.webofscience.com/wos/woscc/basic-search. Further inquiries can be directed to the corresponding authors.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003eCompeting interests\u0026nbsp;\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThere is no competing interests.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003eEthical approval\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eNot applicable.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003eConsent for publication\u0026nbsp;\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eNot applicable.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e\u003cem\u003eConsent to publish\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eNot applicable.\u0026nbsp;\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eDall'Olio FG, Marabelle A, Caramella C, Garcia C, Aldea M, Chaput N, et al. Tumour burden and efficacy of immune-checkpoint inhibitors. Nat Rev Clin Oncol. 2022;19(2):75\u0026ndash;90.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKubli SP, Berger T, Araujo DV, Siu LL, Mak TW. Beyond immune checkpoint blockade: emerging immunological strategies. Nat Rev Drug Discov. 2021;20(12):899\u0026ndash;919.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWei J, Li W, Zhang P, Guo F, Liu M. Current trends in sensitizing immune checkpoint inhibitors for cancer treatment. Mol Cancer. 2024;23(1):279.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eCarlino MS, Larkin J, Long GV. Immune checkpoint inhibitors in melanoma. Lancet. 2021;398(10304):1002\u0026ndash;14.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGeisler AN, Phillips GS, Barrios DM, Wu J, Leung DYM, Moy AP, et al. Immune checkpoint inhibitor-related dermatologic adverse events. J Am Acad Dermatol. 2020;83(5):1255\u0026ndash;68.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eOkiyama N, Tanaka R. Immune-related adverse events in various organs caused by immune checkpoint inhibitors. Allergol Int. 2022;71(2):169\u0026ndash;78.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePoto R, Troiani T, Criscuolo G, Marone G, Ciardiello F, Tocchetti CG, et al. Holistic Approach to Immune Checkpoint Inhibitor-Related Adverse Events. Front Immunol. 2022;13:804597.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWan G, Chen W, Khattab S, Roster K, Nguyen N, Yan B, et al. Multi-organ immune-related adverse events from immune checkpoint inhibitors and their downstream implications: a retrospective multicohort study. Lancet Oncol. 2024;25(8):1053\u0026ndash;69.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eYin Q, Wu L, Han L, Zheng X, Tong R, Li L, et al. Immune-related adverse events of immune checkpoint inhibitors: a review. Front Immunol. 2023;14:1167975.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHu B, Yin G, Zhu J, Bai Y, Sun X. Continuous prediction for tumor mutation burden based on transcriptional data in gastrointestinal cancers. BMC Med Inf Decis Mak. 2024;24(1):384.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChen Z, Chen X, Ju L, Li Y, Li W, Pang H. Establishing a predictive model for tumor mutation burden status based on (18)F-FDG PET/CT and clinical features of non-small cell lung cancer patients. Transl Lung Cancer Res. 2024;13(9):2269\u0026ndash;81.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSun C, Luo T, Liu Z, Ge J, Shao L, Liu X, et al. Tumor Mutation Burden-Related Histopathologic Features for Predicting Overall Survival in Gliomas Using Graph Deep Learning. Am J Pathol. 2023;193(12):2111\u0026ndash;21.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDacic S, Travis WD, Giltnane JM, Kos F, Abel J, Hilz S, et al. Artificial Intelligence-Powered Assessment of Pathologic Response to Neoadjuvant Atezolizumab in Patients With NSCLC: Results From the LCMC3 Study. J Thorac Oncol. 2024;19(5):719\u0026ndash;31.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eEmens LA, Romero PJ, Anderson AC, Bruno TC, Capitini CM, Collyar D et al. Challenges and opportunities in cancer immunotherapy: a Society for Immunotherapy of Cancer (SITC) strategic vision. J Immunother Cancer. 2024;12(6).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGong L, Gong J, Sun X, Yu L, Liao B, Chen X, et al. Identification and prediction of immune checkpoint inhibitors-related pneumonitis by machine learning. Front Immunol. 2023;14:1138489.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGuo X, Chen S, Wang X, Liu X. Immune-related pulmonary toxicities of checkpoint inhibitors in non-small cell lung cancer: Diagnosis, mechanism, and treatment strategies. Front Immunol. 2023;14:1138483.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHuemer F, Leisch M, Geisberger R, Melchardt T, Rinnerthaler G, Zaborsky N et al. Combination Strategies for Immune-Checkpoint Blockade and Response Prediction by Artificial Intelligence. Int J Mol Sci. 2020;21(8).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eJiang Y, Zhang Z, Wang W, Huang W, Chen C, Xi S, et al. Biology-guided deep learning predicts prognosis and cancer immunotherapy response. Nat Commun. 2023;14(1):5135.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKim H, Kim S, Choi S, Park C, Park S, Pereira S, et al. Clinical Validation of Artificial Intelligence-Powered PD-L1 Tumor Proportion Score Interpretation for Immune Checkpoint Inhibitor Response Prediction in Non-Small Cell Lung Cancer. JCO Precis Oncol. 2024;8:e2300556.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZeng Q, Klein C, Caruso S, Maille P, Allende DS, M\u0026iacute;nguez B, et al. Artificial intelligence-based pathology as a biomarker of sensitivity to atezolizumab-bevacizumab in patients with hepatocellular carcinoma: a multicentre retrospective study. Lancet Oncol. 2023;24(12):1411\u0026ndash;22.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZhao J, Sun Z, Yu Y, Yuan Z, Lin Y, Tan Y et al. Radiomic and clinical data integration using machine learning predict the efficacy of anti-PD-1 antibodies-based combinational treatment in advanced breast cancer: a multicentered study. J Immunother Cancer. 2023;11(5).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZhao Z, Xu K, Jiang Y, Xu X, Liu Y. The role of artificial intelligence in immune checkpoint inhibitor research: A bibliometric analysis. Hum Vaccin Immunother. 2024;20(1):2429893.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZheng MM, Li JY, Guo HJ, Zhang J, Wang LS, Jiang KF, et al. IMPDH inhibitors upregulate PD-L1 in cancer cells without impairing immune checkpoint inhibitor efficacy. Acta Pharmacol Sin. 2025;46(4):1058\u0026ndash;67.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSantoni M, Buti S, Myint ZW, Maruzzo M, Iacovelli R, Pichler M, et al. Real-world Outcome of Patients with Advanced Renal Cell Carcinoma and Intermediate- or Poor-risk International Metastatic Renal Cell Carcinoma Database Consortium Criteria Treated by Immune-oncology Combinations: Differential Effectiveness by Risk Group? Eur Urol Oncol. 2024;7(1):102\u0026ndash;11.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRizzo A, Mollica V, Santoni M, Ricci AD, Rosellini M, Marchetti A, et al. Impact of Clinicopathological Features on Survival in Patients Treated with First-line Immune Checkpoint Inhibitors Plus Tyrosine Kinase Inhibitors for Renal Cell Carcinoma: A Meta-analysis of Randomized Clinical Trials. Eur Urol Focus. 2022;8(2):514\u0026ndash;21.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eVitale E, Rizzo A, Santa K, Jirillo E. Associations between Cancer Risk. Inflamm Metabolic Syndrome: Scoping Rev Biology (Basel). 2024;13(5).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBas O, Sahin TK, Karahan L, Rizzo A, Guven DC. Prognostic significance of the cachexia index (CXI) in patients with cancer: A systematic review and meta-analysis. Clin Nutr ESPEN. 2025;68:240\u0026ndash;7.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRizzo A, Ricci AD, Gadaleta-Caldarola G, Brandi G. First-line immune checkpoint inhibitor-based combinations in unresectable hepatocellular carcinoma: current management and future challenges. Expert Rev Gastroenterol Hepatol. 2021;15(11):1245\u0026ndash;51.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRicci AD, Rizzo A, Brandi G. DNA damage response alterations in gastric cancer: knocking down a new wall. Future Oncol. 2021;17(8):865\u0026ndash;8.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRizzo A, Ricci AD. Challenges and Future Trends of Hepatocellular Carcinoma Immunotherapy. Int J Mol Sci. 2022;23(19).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHe C, Zhang J, Zhang R, Liu L, Luo J, Zhang W, et al. Bibliometrics Analysis and Knowledge Mapping of Fragment-Based Drug Design Research: Trends from 2015 to 2024. Drug Des Devel Ther. 2025;19:4245\u0026ndash;62.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eQu F, Wang G, Wen P, Liu X, Zeng X. Knowledge mapping of immunotherapy for breast cancer: A bibliometric analysis from 2013 to 2022. Hum Vaccin Immunother. 2024;20(1):2335728.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eStelmach V, Stavrou G, Theodorou I, Semertzidou E, Tzikos G, Menni AE et al. Postbiotics: Mapp Trend Nutrients. 2024;16(18).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWang C, Liu L, Bai X. Global Trends in Oliceridine (TRV130) Research from 2013 to 2024: A Bibliometrics and Knowledge Graph Analysis. Drug Des Devel Ther. 2024;18:4681\u0026ndash;92.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWu T, Wu Y, Nie K, Yan J, Chen Y, Wang S, et al. Bibliometric analysis and global trends in uterus transplantation. Int J Surg. 2024;110(8):4932\u0026ndash;46.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZhu X, Lv M, Cheng T, Zhou Y, Yuan G, Chu Y, et al. Bibliometric analysis of atrial fibrillation and ion channels. Heart Rhythm. 2024;21(7):1161\u0026ndash;9.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eJin W, Luo Q. When artificial intelligence meets PD-1/PD-L1 inhibitors: Population screening, response prediction and efficacy evaluation. Comput Biol Med. 2022;145:105499.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKinget L, Naulaerts S, Govaerts J, Vanmeerbeek I, Sprooten J, Laureano RS, et al. A spatial architecture-embedding HLA signature to predict clinical response to immunotherapy in renal cell carcinoma. Nat Med. 2024;30(6):1667\u0026ndash;79.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKong J, Ha D, Lee J, Kim I, Park M, Im SH, et al. Network-based machine learning approach to predict immunotherapy response in cancer patients. Nat Commun. 2022;13(1):3703.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLin A, Jiang A, Huang L, Li Y, Zhang C, Zhu L, et al. From chaos to order: optimizing fecal microbiota transplantation for enhanced immune checkpoint inhibitors efficacy. Gut Microbes. 2025;17(1):2452277.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLiu C, Xie J, Lin B, Tian W, Wu Y, Xin S, et al. Pan-Cancer Single-Cell and Spatial-Resolved Profiling Reveals the Immunosuppressive Role of APOE+ Macrophages in Immune Checkpoint Inhibitor Therapy. Adv Sci (Weinh). 2024;11(23):e2401061.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLopci E. Immunotherapy Monitoring with Immune Checkpoint Inhibitors Based on [(18)F]FDG PET/CT in Metastatic Melanomas and Lung Cancer. J Clin Med. 2021;10:21.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMenche C, Schuhwerk H, Armstark I, Gupta P, Fuchs K, van Roey R, et al. ZEB1-mediated fibroblast polarization controls inflammation and sensitivity to immunotherapy in colorectal cancer. EMBO Rep. 2024;25(8):3406\u0026ndash;31.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHe J, Cui H, Jiang G, Fang L, Hao J. Knowledge mapping of trained immunity/innate immune memory: Insights from two decades of studies. Hum Vaccin Immunother. 2024;20(1):2415823.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eYu L, Xu C, Zhang M, Zhou Y, Hu Z, Li L, et al. Top 100 cited research on COVID-19 vaccines: A bibliometric analysis and evidence mapping. Hum Vaccin Immunother. 2024;20(1):2370605.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZhao Z, Hu B, Xu K, Jiang Y, Xu X, Liu Y. A quantitative analysis of artificial intelligence research in cervical cancer: a bibliometric approach utilizing CiteSpace and VOSviewer. Front Oncol. 2024;14:1431142.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eCai H, Du R, Zhang J, Wang X, Li W, Yang K, et al. Knowledge domain and trends in treatment-resistant schizophrenia (TRS) research based on CiteSpace bibliometrics analysis. Front Pharmacol. 2024;15:1478625.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLai Y, Jiang J, Zhang H, Gong K. Bibliometric Analysis of Curcumin Based on CiteSpace: Landscapes, Hotspots, and Frontiers. Drug Des Devel Ther. 2024;18:5743\u0026ndash;58.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZhang L, Cui S, Xi X, Bi H, Huang B. Research hotspots and frontiers of essential tremor from 2013 to 2023: a visualization analysis based on CiteSpace. Front Aging Neurosci. 2024;16:1380851.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eNiu J, Deng R, Dong Z, Yang X, Xing Z, Yu Y, et al. Mapping the landscape of AI and ML in vaccine innovation: A bibliometric study. Hum Vaccin Immunother. 2025;21(1):2501358.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eYang X, Kang J, Xing Z, Sun Y, Liu Z, Li N, et al. Bibliometric analysis of RNA vaccines for cancer. Hum Vaccin Immunother. 2023;19(2):2231333.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLai B, Jiang H, Gao Y, Zhou X. Research trends and hotspots of myositis ossificans: a bibliometric analysis from 1993 to 2022. EFORT Open Rev. 2024;9(7):589\u0026ndash;99.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePeng T, Yang Y, Ma J, Xu P, Xie X, Hu N, et al. Dementia and metabolic syndrome: a bibliometric analysis. Front Aging Neurosci. 2024;16:1400589.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eYang C, Liu H, Feng X, Shi H, Jiang Y, Li J, et al. Research hotspots and frontiers of neoadjuvant therapy in triple-negative breast cancer: a bibliometric analysis of publications between 2002 and 2023. Int J Surg. 2024;110(8):4976\u0026ndash;92.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBang YH, Lee CK, Bang K, Kim HD, Kim KP, Jeong JH, et al. Artificial Intelligence-Powered Spatial Analysis of Tumor-Infiltrating Lymphocytes as a Potential Biomarker for Immune Checkpoint Inhibitors in Patients with Biliary Tract Cancer. Clin Cancer Res. 2024;30(20):4635\u0026ndash;43.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBareche Y, Kelly D, Abbas-Aghababazadeh F, Nakano M, Esfahani PN, Tkachuk D, et al. Leveraging big data of immune checkpoint blockade response identifies novel potential targets. Ann Oncol. 2022;33(12):1304\u0026ndash;17.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChang TG, Cao Y, Sfreddo HJ, Dhruba SR, Lee SH, Valero C, et al. LORIS robustly predicts patient outcomes with immune checkpoint blockade therapy using common clinical, pathologic and genomic features. Nat Cancer. 2024;5(8):1158\u0026ndash;75.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChen P, Zhang J, Wu J. Artificial Intelligence in Digital Pathology to Advance Cancer Immunotherapy. 21 Century Pathol. 2022;2(3).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eJiang L, Wang J, Wang Y, Yang H, Kong L, Wu Z, et al. Bibliometric and LDA analysis of acute rejection in liver transplantation: Emerging trends, immunotherapy challenges, and the role of artificial intelligence. Cell Transpl. 2025;34:9636897251325628.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMu W, Jiang L, Shi Y, Tunali I, Gray JE, Katsoulakis E et al. Non-invasive measurement of PD-L1 status and prediction of immunotherapy response using deep learning of PET/CT images. J Immunother Cancer. 2021;9(6).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePrelaj A, Miskovic V, Zanitti M, Trovo F, Genova C, Viscardi G, et al. Artificial intelligence for predictive biomarker discovery in immuno-oncology: a systematic review. Ann Oncol. 2024;35(1):29\u0026ndash;65.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eFraunhoffer N, Hammel P, Conroy T, Nicolle R, Bachet JB, Harl\u0026eacute; A, et al. Development and validation of AI-assisted transcriptomic signatures to personalize adjuvant chemotherapy in patients with pancreatic ductal adenocarcinoma. Ann Oncol. 2024;35(9):780\u0026ndash;91.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eFomin V, So WV, Barbieri RA, Hiller-Bittrolff K, Koletou E, Tu T et al. Machine learning identifies clinical tumor mutation landscape pathways of resistance to checkpoint inhibitor therapy in NSCLC. J Immunother Cancer. 2025;13(3).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLjubimov VA, Sun T, Wang J, Li L, Wang PZ, Ljubimov AV, et al. Blood-brain barrier crossing biopolymer targeting c-Myc and anti-PD-1 activate primary brain lymphoma immunity: Artificial intelligence analysis. J Control Release. 2025;381:113611.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eCannarozzi AL, Latiano A, Massimino L, Bossa F, Giuliani F, Riva M, et al. Inflammatory bowel disease genomics, transcriptomics, proteomics and metagenomics meet artificial intelligence. United Eur Gastroenterol J. 2024;12(10):1461\u0026ndash;80.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChen B, Sun X, Huang H, Feng C, Chen W, Wu D. An integrated machine learning framework for developing and validating a diagnostic model of major depressive disorder based on interstitial cystitis-related genes. J Affect Disord. 2024;359:22\u0026ndash;32.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHoang DT, Dinstag G, Shulman ED, Hermida LC, Ben-Zvi DS, Elis E, et al. A deep-learning framework to predict cancer treatment response from histopathology images through imputed transcriptomics. Nat Cancer. 2024;5(9):1305\u0026ndash;17.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWang M, Wang Y, Li Y, Zhang C, Li C, Bi N. Interpretable artificial intelligence based on immunoregulation-related genes predicts prognosis and immunotherapy response in lung adenocarcinoma. Front Bioinform. 2025;5:1613761.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHe X, Liu X, Zuo F, Shi H, Jing J. Artificial intelligence-based multi-omics analysis fuels cancer precision medicine. Semin Cancer Biol. 2023;88:187\u0026ndash;200.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLi J, Li L, You P, Wei Y, Xu B. Towards artificial intelligence to multi-omics characterization of tumor heterogeneity in esophageal cancer. Semin Cancer Biol. 2023;91:35\u0026ndash;49.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBoretti A. Improving chimeric antigen receptor T-cell therapies by using artificial intelligence and internet of things technologies: A narrative review. Eur J Pharmacol. 2024;974:176618.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eJumper J, Evans R, Pritzel A, Green T, Figurnov M, Ronneberger O, et al. Highly accurate protein structure prediction with AlphaFold. Nature. 2021;596(7873):583\u0026ndash;9.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAhluwalia VS, Parikh RB. Explainable Machine Learning to Predict Treatment Response in Advanced Non-Small Cell Lung Cancer. JCO Clin Cancer Inf. 2025;9:e2400157.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eCaballero Mateos AM, de la Ca\u0026ntilde;adas GA, Gros B. Paradigm Shift in Inflammatory Bowel Disease Management: Precision Medicine, Artificial Intelligence, and Emerging Therapies. J Clin Med. 2025;14(5).\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHe YJ, Liu PL, Wei T, Liu T, Li YF, Yang J, et al. Artificial intelligence in kidney transplantation: a 30-year bibliometric analysis of research trends, innovations, and future directions. Ren Fail. 2025;47(1):2458754.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKim J, Lee BJ, Moon S, Lee H, Lee J, Kim BS, et al. Strategies to Overcome Hurdles in Cancer Immunotherapy. Biomater Res. 2024;28:0080.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eVivas AJ, Boumediene S, Tob\u0026oacute;n GJ. Predicting autoimmune diseases: A comprehensive review of classic biomarkers and advances in artificial intelligence. Autoimmun Rev. 2024;23(9):103611.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChen Z, Chen Y, Sun Y, Tang L, Zhang L, Hu Y, et al. Predicting gastric cancer response to anti-HER2 therapy or anti-HER2 combined immunotherapy based on multi-modal data. Signal Transduct Target Ther. 2024;9(1):222.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eCheng Z, Du Y, Yu L, Yuan Z, Tian J. Application of Noninvasive Imaging to Combined Immune Checkpoint Inhibitors for Breast Cancer: Facts and Future. Mol Imaging Biol. 2022;24(2):264\u0026ndash;79.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eCiccolini J, Benzekry S, Barlesi F. Deciphering the response and resistance to immune-checkpoint inhibitors in lung cancer with artificial intelligence-based analysis: when PIONeeR meets QUANTIC. Br J Cancer. 2020;123(3):337\u0026ndash;8.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLee S, Chu Y, Ryu J, Park YJ, Yang S, Koh SB. Artificial Intelligence for Detection of Cardiovascular-Related Diseases from Wearable Devices: A Systematic Review and Meta-Analysis. Yonsei Med J. 2022;63(Suppl):S93\u0026ndash;107.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZuo D, Yang L, Jin Y, Qi H, Liu Y, Ren L. Machine learning-based models for the prediction of breast cancer recurrence risk. BMC Med Inf Decis Mak. 2023;23(1):276.\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBijlsma S, Maal T, Rubbert C, Mannil M, Meijer A, van der Kolk A, et al. AI radiomics predicts spatial glioma recurrence on preoperative MRI: a systematic review. Eur J Radiol. 2025;193:112412.\u003c/span\u003e\u003c/li\u003e\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"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":"Artificial intelligence, Immune checkpoint inhibitors, bibliometric","lastPublishedDoi":"10.21203/rs.3.rs-8873872/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8873872/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThis bibliometric analysis examines the transformative role of artificial intelligence (AI) in immune checkpoint inhibitor (ICI) research. Analyzing 597 publications from the Web of Science Core Collection (2016\u0026ndash;2025), we reveal a dramatic rise in AI-related ICI studies, led by the USA and China. Key findings demonstrate AI's integration in predicting treatment response, optimizing dosing strategies, and managing immune-related adverse events. Through keyword co-occurrence and citation analyses, we identify critical AI applications including novel gene target discovery, drug structure design, and multimodal data fusion for personalized immunotherapy. While highlighting AI's potential to bridge preclinical research and clinical practice, we emphasize the need for interpretable models, robust validation, and ethical frameworks to ensure equitable clinical translation. This comprehensive overview provides valuable insights into research trends and future directions for AI-driven innovations in cancer immunotherapy.\u003c/p\u003e","manuscriptTitle":"Artificial Intelligence in Immune Checkpoint Inhibitor Research: A Bibliometric Analysis of the Landscape","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-03-09 16:11:40","doi":"10.21203/rs.3.rs-8873872/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":"0141e03d-2f5e-4ef0-b3b8-62445a1ab2b2","owner":[],"postedDate":"March 9th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-03-25T09:13:27+00:00","versionOfRecord":[],"versionCreatedAt":"2026-03-09 16:11:40","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-8873872","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8873872","identity":"rs-8873872","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}