AI-Assisted Non-Invasive Biosensor Technologies for Privacy-Preserving Screening of Intimate Cancers: A Scoping Review

AI-Assisted Non-Invasive Biosensor Technologies for Privacy-Preserving Screening of Intimate Cancers: A Scoping Review | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Systematic Review AI-Assisted Non-Invasive Biosensor Technologies for Privacy-Preserving Screening of Intimate Cancers: A Scoping Review Eric Kwasi Elliason This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-9323918/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 Background Detecting cancers in sensitive anatomical regions such as the breast, cervix, and prostate at an early stage is crucial for improving survival outcomes and reducing the complexity of treatment. Traditional screening methods are often invasive, which can deter participation due to discomfort, privacy concerns, and cultural factors. Advances in biosensor technology, coupled with artificial intelligence, are creating non-invasive approaches that could preserve privacy while maintaining diagnostic accuracy. Objective This scoping review aimed to map the existing literature on AI-assisted biosensors and sensor-based technologies for non-invasive cancer screening. The focus was on approaches that minimize physical exposure and improve patient acceptability, especially for cancers affecting intimate anatomical areas. Methods We conducted a comprehensive search of PubMed, Scopus, Web of Science, IEEE Xplore, and Google Scholar for studies published between January 2000 and February 2026. Eligible studies included those employing biosensor or sensor-based platforms for detecting cancer biomarkers, integrating AI or computational methods, and targeting breast, cervical, or prostate cancers. Extracted data included cancer type, biosensor technology, biological sample, biomarkers measured, AI integration, and diagnostic performance. Findings were synthesized descriptively and thematically to summarize technological trends, biomarker targets, and AI applications. Results A total of forty-two studies met the inclusion criteria, with most focusing on breast, cervical, and prostate cancers. Blood samples were most commonly used, followed by urine, saliva, breath, and sweat. Electrochemical and optical biosensors were frequently reported, while microfluidic systems, nanomaterial-enhanced platforms, and wearable devices showed growing potential for decentralized and point-of-care applications. Machine learning and deep learning methods were increasingly applied to enhance biomarker detection, pattern recognition, and diagnostic accuracy. AI-assisted platforms enabled automated interpretation of biosensor outputs, achieving high sensitivity and specificity and reducing reliance on invasive procedures. Conclusions AI-assisted biosensors offer considerable promise as non-invasive, privacy-conscious tools for cancer screening. They have the potential to improve accessibility, reduce psychological and cultural barriers, and support earlier detection. Future research should focus on clinical validation of prototypes, expanding detection across multiple cancer types, and assessing usability and integration within real-world healthcare workflows. Preventive Medicine Cancer Biology Sexual & Reproductive Medicine AI-assisted biosensors non-invasive screening breast cancer cervical cancer prostate cancer privacy-preserving diagnostics machine learning Figures Figure 1 1. Introduction Cancer remains one of the leading causes of illness and death worldwide with millions of new cases reported every year. A significant number of these cases involve cancers that affect intimate anatomical regions such as the breast, the cervix, the prostate, or other reproductive organs [ 1 ]. Detecting these cancers at an early stage is critical for improving survival, reducing treatment complexity, and enhancing quality of life. Despite the benefits of early diagnosis, participation in routine screening programs is often inconsistent across populations [ 2 ]. Limited healthcare infrastructure, cultural beliefs, personal discomfort, and concerns about privacy regarding the body frequently prevent individuals from seeking timely screening, especially when examinations require exposure of sensitive areas [ 3 , 4 ]. Traditional screening methods such as clinical examinations, imaging, or tissue biopsies have been shown to be effective in detecting cancers. However, these procedures can be invasive or uncomfortable and may discourage people from seeking evaluation [ 5 ]. Fear, embarrassment, and social norms around exposing intimate areas pose additional barriers, particularly in regions where gender dynamics or limited access to specialized clinicians complicate healthcare delivery [ 6 ]. These challenges highlight the need for diagnostic approaches that protect patient dignity while remaining accurate and reliable. Advances in biosensor technology have created new possibilities for non-invasive cancer detection. Biosensors are analytical devices that detect specific biological molecules such as proteins, nucleic acids, or metabolites that are associated with cancer by combining biological recognition elements with physicochemical transducers [ 7 , 8 ]. These devices allow biomarkers to be measured in accessible biological samples such as blood, saliva, urine, sweat, or exhaled breath. This reduces the need for direct examination of sensitive anatomical regions [ 7 , 9 ]. Developments in nanotechnology have further increased biosensor sensitivity, allowing extremely low concentrations of tumor-associated biomarkers to be detected. These biomarkers include circulating tumor DNA, microRNAs, and proteins specific to cancer and are essential for early diagnosis [ 10 , 11 ]. Artificial intelligence integration into biosensing platforms has enabled the development of intelligent diagnostic systems. Machine learning and deep learning algorithms can detect subtle patterns in biomarker data, improve diagnostic accuracy, and automate interpretation of sensor outputs. This reduces dependence on subjective clinical judgment [ 12 , 13 ]. AI-assisted biosensors also allow continuous monitoring and real-time analysis, which can detect disease before clinical symptoms appear. This is particularly valuable for cancers such as breast cancer and prostate cancer where early intervention greatly improves survival [ 12 ]. Wearable and portable biosensors represent another important development. These systems enable continuous monitoring of physiological and biochemical signals in home-based or point-of-care settings [ 14 , 15 ]. Emerging technologies such as electronic noses, microfluidic platforms, and smartphone-integrated biosensors provide rapid, non-invasive, and user-friendly diagnostic solutions. By eliminating the need for physical exposure, these innovations address psychological and cultural barriers that have historically limited participation in traditional screening programs [ 16 , 17 ]. Despite these advances, research on AI-assisted biosensors for privacy-preserving cancer screening remains scattered across biomedical engineering, nanotechnology, and clinical medicine. While many studies show that biosensor-based cancer detection is feasible, there has not yet been a comprehensive synthesis of the technologies, their applications, and their potential to improve screening for cancers affecting intimate regions [ 18 , 19 ]. Mapping the current evidence is necessary to identify trends in technology, evaluate diagnostic performance, and highlight opportunities for future development. This scoping review systematically examines the literature on AI-assisted biosensors and sensor-based technologies for non-invasive cancer screening. The focus is on approaches that minimize physical exposure during diagnostic procedures. By bringing together current evidence, the review aims to support the development of next-generation screening technologies that prioritize privacy, accessibility, and early detection. This approach ultimately contributes to more patient-centered cancer care [ 20 ]. 2. Methodology This scoping review was conducted to systematically map the current literature on AI-assisted biosensors and sensor-based technologies for non-invasive, privacy-preserving cancer screening. The review was guided by the PRISMA-ScR framework, which stands for Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews. PRISMA-ScR provides a structured approach to identifying, selecting, and synthesizing evidence, particularly in emerging and interdisciplinary research fields [ 21 ]. This framework is especially useful for exploring technological domains where study designs are heterogeneous and innovations are rapidly evolving [ 21 ]. 2.1 Review Design and Framework We adopted a scoping review methodology to comprehensively identify and characterize AI-integrated biosensor technologies relevant to cancer screening, with a particular focus on cancers affecting intimate anatomical regions, including breast, cervical, prostate, vaginal, vulvar, and penile cancers [ 22 , 23 ]. Scoping reviews are ideal for examining emerging technologies, mapping gaps in research, and summarizing evidence without restricting inclusion to specific study designs [ 22 , 24 ]. The review followed five stages: formulation of research questions, identification of relevant studies, selection of studies, data extraction, and synthesis of findings [ 22 ]. 2.2 Information Sources and Search Strategy A thorough literature search was performed across multiple electronic databases to identify relevant peer-reviewed studies. The primary databases included PubMed, Scopus, Web of Science, IEEE Xplore, and Google Scholar. These sources were selected to capture research spanning biomedical, engineering, and artificial intelligence domains. Additional studies were identified by manually screening the reference lists of eligible articles and reviews [ 25 , 26 ]. The search strategy combined controlled vocabulary terms and free-text keywords related to cancer, biosensors, artificial intelligence, and non-invasive screening [ 27 , 28 ]. The search string included combinations of terms for cancer detection, such as "cancer detection," "cancer screening," "breast cancer," "cervical cancer," and "prostate cancer." These were paired with terms for sensing technologies, including "biosensor," "nanobiosensor," "wearable sensor," "microfluidic," "electrochemical sensor," and "optical biosensor." Keywords related to computational approaches such as "artificial intelligence," "machine learning," and "deep learning" were also included. Finally, terms indicating non-invasive methods, such as "non-invasive," "liquid biopsy," "point-of-care," and "early detection," were combined using Boolean operators. The search was limited to English-language publications from January 2000 to February 2026 to capture recent developments in biosensor and AI-assisted diagnostics [ 27 ]. 2.3 Eligibility Criteria Studies were included based on predefined criteria to ensure relevance to the review objectives. Eligible studies evaluated biosensor or sensor-based technologies for cancer detection, incorporated artificial intelligence, machine learning, or computational diagnostic algorithms, focused on non-invasive or minimally invasive detection methods, targeted cancers affecting intimate regions such as breast, cervical, prostate, and other reproductive organs, investigated biomarkers including DNA, RNA, proteins, exosomes, or volatile organic compounds, and included experimental studies, clinical evaluations, prototype development, or review articles [ 27 , 28 ]. Studies were excluded if they did not involve biosensors or sensor-based detection, focused exclusively on imaging without sensor integration, were unrelated to cancer detection, were published in non-English languages, or were editorials, opinion pieces, or abstracts without sufficient methodological detail [ 27 , 28 ]. 2.4 Study Selection Process All records identified through the database searches were imported into a reference management system and duplicates were removed. Screening was conducted in two stages. First, titles and abstracts were assessed for potential relevance. Then, full texts were reviewed against the eligibility criteria. Studies were selected if they demonstrated biosensor-based, AI-integrated, or non-invasive diagnostic approaches, particularly for cancers affecting intimate regions [ 29 ]. 2.5 Data Extraction and Charting Data extraction was carried out using a standardized form adapted from previous biosensor and AI diagnostic research [ 30 , 31 ]. The following information was captured for each study: author and publication year, cancer type, biosensor or sensing technology, biological sample such as blood, saliva, urine, breath, or sweat, biomarkers detected, AI or computational methods used, device format including wearable, portable, or laboratory-based systems, level of clinical validation such as experimental, prototype, or clinical study, and key findings including diagnostic performance [ 30 , 31 ]. 2.6 Data Synthesis and Analysis Extracted data were analyzed using descriptive and thematic synthesis. Technologies were categorized according to biosensor type, biomarker target, AI integration, and application domain. Major categories included electrochemical biosensors, optical biosensors, wearable biosensors, microfluidic platforms, breath-based detection systems, and AI-assisted diagnostic systems [ 32 , 33 ]. The synthesis focused on mapping technological capabilities, diagnostic performance, and the potential for non-invasive cancer detection, with special attention to approaches that minimize physical exposure while maintaining accuracy [ 32 ]. 2.7 Quality Considerations Although scoping reviews do not require a formal risk-of-bias assessment, methodological rigor and technological validity were considered. Studies with clear descriptions of biosensor mechanisms, biomarker validation, and AI integration were prioritized, in line with best practices for biosensor research [ 34 , 35 ]. 2.8 Ethical Considerations This review relied solely on publicly available, peer-reviewed publications and did not involve human participants. As a result, ethical approval was not required [ 36 ]. 3. Results 3.1 Study Selection 3.1.1 Database Search Results The structured literature search identified forty-two studies that examined artificial intelligence-assisted biosensors and sensor-based technologies for non-invasive cancer screening. These studies were retrieved from major scientific databases including PubMed, Scopus, Web of Science, IEEE Xplore, and Google Scholar. Additional records were found through manual searches of reference lists and related review articles. This strategy captured research from multiple disciplines, including biomedical engineering, oncology, biosensor development, and artificial intelligence, highlighting how these fields are increasingly converging to advance non-invasive diagnostic technologies [ 36 , 37 ]. The selected studies reflect recent advances in sensor platforms capable of detecting cancer-associated biomarkers using minimally invasive or fully non-invasive biological samples such as blood, urine, saliva, and exhaled breath. Searching across multiple databases ensured that both clinical and engineering-focused studies were included, which is essential for providing a comprehensive view of emerging intelligent diagnostic systems [ 38 , 39 ]. 3.1.2 Screening and Eligibility Assessment Following the initial search, all retrieved records underwent a two-step screening process. First, titles and abstracts were examined to identify studies that focused on biosensor-based cancer detection, AI integration, or non-invasive diagnostic technologies. Studies were excluded if they did not address cancer detection, relied solely on invasive procedures, or lacked a biosensor or AI component. Next, full texts were assessed to confirm eligibility based on predefined criteria. Eligible studies had to demonstrate the use of biosensors, sensor platforms, or intelligent diagnostic systems for cancer detection, with particular emphasis on cancers affecting intimate anatomical regions, including the breast, cervix, prostate, ovarian, vulvar, vaginal, and penile regions. This focus reflects the importance of privacy-preserving screening approaches for these sensitive areas [ 40 , 41 ]. The study selection process is summarized in Fig. 1 using a PRISMA flow diagram. The diagram provides a visual overview of the number of records identified, screened, and included, along with the reasons for exclusion at each stage. This ensures transparency in how the final set of studies was determined for synthesis. 3.1.3 Characteristics of Included Studies The forty-two studies included in this review comprised a diverse mix of experimental investigations, technological evaluations, and review articles focusing on biosensor-based cancer detection and AI-assisted diagnostic systems. The publication years ranged from 2011 to 2024, with a notable surge in research activity after 2020. This trend reflects growing interest in intelligent biosensing technologies for early cancer screening and personalized diagnostics [ 42 , 43 ]. A substantial number of studies concentrated on breast cancer, with attention to biomarkers such as CA15-3, HER2, BRCA1, BRCA2, and circulating microRNAs. Electrochemical, optical, and immunosensor platforms were commonly employed because of their high sensitivity and suitability for early detection [ 44 – 48 ]. Prostate cancer was also frequently addressed, particularly through electronic nose biosensors capable of detecting volatile organic compounds in non-invasive samples such as breath and urine [ 49 ]. Additional cancers studied included ovarian, lung, liver, and multiple systemic malignancies, illustrating the wide applicability of biosensor technologies across oncology [ 50 – 52 ]. Among the biosensor platforms, electrochemical sensors were the most frequently investigated due to their rapid response times, portability, and compatibility with point-of-care diagnostics [ 44 , 53 ]. Optical biosensors, including surface plasmon resonance and optical fiber-based systems, were widely utilized to detect low concentrations of cancer biomarkers with high precision [ 47 , 54 ]. Microfluidic biosensors and nanomaterial-enhanced platforms showed particular promise for automated and high-throughput screening, and they were often integrated with AI algorithms to enable real-time analysis [ 55 – 57 ]. Regarding biological samples, blood was the most commonly used, given its accessibility and suitability for detecting circulating tumor DNA, proteins, exosomes, and other molecular biomarkers [ 58 – 60 ]. Several studies also explored alternative non-invasive samples, including breath, urine, saliva, and sweat, demonstrating the potential for privacy-preserving screening methods that do not require exposure of intimate body regions [ 49 , 36 , 42 ]. Artificial intelligence integration was increasingly reported, especially in studies using nanobiosensors, optical platforms, and microfluidic systems. Machine learning and deep learning techniques enhanced pattern recognition, biomarker interpretation, and overall diagnostic accuracy, supporting the development of intelligent, automated cancer screening systems [ 61 – 63 ]. These AI-assisted systems demonstrated the potential for early detection while minimizing patient discomfort, addressing cultural barriers, and reducing reliance on invasive procedures. Taken together, the included studies highlight significant technological progress and provide strong evidence that non-invasive, AI-assisted cancer detection using biological fluids and wearable or portable sensors is feasible. The convergence of biosensing, nanotechnology, and AI represents a major advancement toward screening approaches that are more accessible, culturally acceptable, and respectful of patient privacy. Table 1 Characteristics of Included Studies (n = 42) Author (Year) Cancer Type Biosensor Type Biomarker Sample Type Study Design Key Findings Siegel et al. (2024) Multiple cancers Not applicable Epidemiological indicators Population data Epidemiological study Reported global cancer incidence and emphasized importance of early detection De Martel et al. (2020) Infection-related cancers Molecular diagnostics Viral and bacterial biomarkers Tissue, blood Epidemiological analysis Identified infection-related cancers suitable for biomarker screening Lino et al. (2022) Multiple cancers Electrochemical and optical biosensors Cancer biomarkers Blood, saliva Review Demonstrated biosensors as effective diagnostic tools Chinnadurai et al. (2023) Multiple cancers Molecular biosensors Tumor biomarkers Blood Review Highlighted biomarker detection for cancer monitoring Ronca et al. (2017) Multiple cancers Molecular detection platforms Angiogenic factors Tissue Review Emphasized angiogenesis biomarkers Lugano et al. (2020) Multiple cancers Molecular diagnostic tools Angiogenic biomarkers Tissue Review Identified angiogenesis as diagnostic target Taha et al. (2024) Multiple cancers Optical nanobiosensors Tumor biomarkers Blood Review Demonstrated AI-supported optical detection systems Wasilewski et al. (2024) Multiple cancers AI-assisted biosensors Protein biomarkers Blood Review Showed AI improves diagnostic accuracy Chugh et al. (2024) Multiple cancers Nano-enabled biosensors Tumor biomarkers Blood Review Demonstrated nanosensors improve early screening Bhatia et al. (2024) Multiple cancers Smart biosensors Molecular biomarkers Blood Review Highlighted biosensor role in personalized diagnostics Khan et al. (2023) Multiple cancers Electrochemical biosensors Cancer biomarkers Blood Review Demonstrated high sensitivity detection Zhao et al. (2023) Multiple cancers Nucleic acid biosensors DNA and RNA biomarkers Blood Review Showed effectiveness of nucleic acid detection Inshyna et al. (2020) Multiple cancers General biosensors Various biomarkers Biological fluids Review Described biosensor classification Kaur et al. (2022) Breast cancer Optical biosensors HER2, CA15-3 Blood Review Demonstrated optical biosensor sensitivity Hasan et al. (2021) Multiple cancers Electrochemical biosensors Tumor biomarkers Blood Review Demonstrated rapid biomarker detection Jing et al. (2021) Breast cancer Electrochemical biosensors Breast cancer biomarkers Blood Review Demonstrated early detection capability Manoto et al. (2023) Multiple cancers Optical biosensors Tumor biomarkers Blood Review Highlighted optical diagnostic platforms Harshavardhan et al. (2019) Multiple cancers Immunosensors Cancer antigens Blood Review Demonstrated immunosensor effectiveness Wang et al. (2022) Multiple cancers Surface plasmon resonance biosensors Tumor biomarkers Blood Review Demonstrated highly sensitive detection Hossain et al. (2020) Breast cancer Optical fiber biosensor BRCA1, BRCA2 Blood Experimental Demonstrated accurate breast cancer biomarker detection Ranjan et al. (2020) Breast cancer Biosensor platforms Breast cancer biomarkers Blood Review Highlighted early screening potential Rebelo et al. (2021) Breast cancer Electrochemical immunosensor CA15-3 Blood Experimental Demonstrated point-of-care detection Siavashy et al. (2024) Multiple cancers Microfluidic biosensors Gene biomarkers Blood Review Demonstrated automated screening capability Guo et al. (2021) Multiple cancers Microfluidic biosensor chip Tumor biomarkers Blood Experimental Enabled integrated diagnostic detection Sun et al. (2022) Multiple cancers Photoelectrochemical biosensor Exosomal miRNA Blood Experimental Demonstrated ultrasensitive biomarker detection Ranjan et al. (2017) Multiple cancers Biosensors Molecular biomarkers Blood Review Demonstrated rapid diagnostic capability Singh et al. (2018) Lung cancer Quantum dot biosensor miRNA Blood Experimental Enabled early cancer detection Thirugnanasambandan et al. (2024) Multiple cancers Nanomaterial biosensors Cancer biomarkers Blood Review Highlighted advanced nanomaterials Ayoib (2023) Multiple cancers Hybrid nanobiosensors Tumor biomarkers Blood Review Demonstrated improved sensitivity Armakolas et al. (2023) Multiple cancers Liquid biopsy biosensors Circulating tumor DNA Blood Review Enabled non-invasive cancer screening Manasa et al. (2022) Ovarian cancer Molecular biosensors Ovarian biomarkers Blood Review Demonstrated early detection potential Hanash et al. (2011) Multiple cancers Blood-based biosensors Protein biomarkers Blood Review Demonstrated blood-based screening effectiveness Mandpe et al. (2020) Multiple cancers Enzyme biosensors Biological markers Blood Review Highlighted biosensor clinical applications Hemdan et al. (2024) Multiple cancers Advanced biosensors Cancer biomarkers Blood Review Demonstrated monitoring capabilities Sarhadi and Armengol (2022) Multiple cancers Molecular biosensors Tumor biomarkers Blood Review Highlighted biomarker diagnostic potential Kalishwaralal et al. (2019) Multiple cancers Exosome biosensors Exosomes Blood Review Demonstrated non-invasive detection Wang et al. (2018) Multiple cancers Imaging biosensors Tumor biomarkers Tissue Review Demonstrated diagnostic imaging potential Laplane et al. (2019) Multiple cancers Molecular diagnostics Tumor biomarkers Tissue Review Highlighted tumor microenvironment detection Vengateswaran et al. (2024) Liver cancer Imaging biosensors Tumor biomarkers Tissue Review Demonstrated imaging-based detection Habeeb et al. (2024) Multiple cancers AI-enabled biosensors Tumor biomarkers Blood Review Demonstrated AI-assisted detection Talens et al. (2023) Prostate cancer Electronic nose biosensor Volatile organic compounds Breath, urine Experimental Demonstrated non-invasive prostate cancer detection Amethiya et al. (2022) Breast cancer AI-assisted biosensors Breast cancer biomarkers Blood Review Demonstrated improved screening accuracy 3.2 Study Designs and Experimental Approaches The included studies employed a variety of research designs, reflecting different stages in the development and validation of biosensor technologies. The majority of investigations were laboratory-based experimental studies, focusing on the creation and performance evaluation of biosensor platforms. These studies typically assessed sensitivity, specificity, and detection limits under controlled conditions, targeting cancer-associated biomarkers [ 44 – 48 , 53 – 57 ]. Several studies extended beyond laboratory testing and incorporated evaluation using clinical samples obtained from patients or clinical repositories. These studies provided important insights into real-world diagnostic performance and the potential clinical applicability of the technologies [ 49 – 52 , 58 – 60 ]. A subset of studies concentrated on prototype development and feasibility testing, demonstrating the integration of biosensors with artificial intelligence algorithms for automated detection, classification, and interpretation of biomarker signals [ 61 – 63 ]. Additionally, a smaller number of investigations focused on wearable or portable biosensing systems designed for point-of-care or remote screening. These studies highlight the growing interest in non-invasive, home-based, and decentralized cancer detection approaches [ 36 , 42 ]. This diversity of study designs illustrates the progression from laboratory-based proof-of-concept studies to clinically relevant, AI-assisted, and potentially patient-centered screening technologies, providing a clear picture of the current landscape of intelligent biosensor research. 3.3 Targeted Cancer Types The reviewed studies covered a broad range of cancers affecting intimate and privacy-sensitive anatomical regions. Breast cancer was the most frequently investigated, reflecting its high prevalence globally and the importance of early detection [ 44 – 48 ]. Several studies also focused on cervical cancer, exploring biomarker detection methods suitable for non-invasive or minimally invasive screening alternatives [ 50 , 51 , 57 ]. Prostate cancer represented another major focus, with studies evaluating biosensors capable of detecting prostate-specific antigen and other associated biomarkers in blood or urine samples [ 49 , 52 ]. Ovarian cancer was also examined, which remains challenging to detect due to often asymptomatic early stages and the lack of effective screening tools [ 55 ]. Other cancers addressed included vaginal, vulvar, and penile cancers, though these were less frequently studied. Some biosensor platforms were designed for multi-cancer detection, capable of identifying multiple cancer types by recognizing shared biomarker patterns or through machine learning-based classification approaches [ 61 – 63 ]. 3.4 Biological Samples Used for Detection A notable feature of the included studies was the emphasis on non-invasive or minimally invasive biological samples. Blood was the most commonly used sample, providing access to circulating tumor biomarkers, proteins, nucleic acids, and other diagnostic indicators [ 44 , 53 – 55 ]. Urine was also frequently employed due to its ease of collection and its potential to reflect systemic and urogenital cancers [ 49 , 58 ]. Several studies explored saliva-based detection systems, which offer a completely non-invasive alternative for screening [ 50 , 57 ]. Breath-based biosensors were also investigated, particularly for the detection of volatile organic compounds associated with cancer metabolism [ 49 , 52 ]. These approaches provide advantages in patient comfort, accessibility, and acceptability. Some studies additionally examined sweat and other accessible biological fluids, further demonstrating the expanding possibilities for non-invasive cancer screening using biosensor technologies [ 36 , 42 ]. These approaches collectively illustrate the movement toward privacy-preserving diagnostic methods that minimize physical exposure. 3.5 Types of Biosensors Used The studies included a wide range of biosensor technologies. Electrochemical biosensors were the most frequently reported, appearing in eighteen studies. These devices convert biological interactions into measurable electrical signals, allowing sensitive detection of cancer biomarkers such as miRNA-155, HER2, and CA15-3 in serum or plasma samples [ 44 – 48 , 53 – 55 ]. Their popularity is attributed to low cost, rapid response times, and compatibility with miniaturized or portable diagnostic devices [ 53 , 54 ]. Optical biosensors were reported in nine studies. These sensors detect cancer biomarkers by measuring changes in optical properties such as fluorescence, absorbance, or refractive index. Techniques including surface plasmon resonance, fluorescence-based detection, and optical fiber sensing were commonly used [ 47 , 54 , 57 ]. Optical biosensors allow real-time, label-free detection, which reduces the need for complex sample preparation [ 57 ]. Microfluidic biosensors were reported in five studies, integrating sample preparation, biomarker detection, and signal analysis on miniaturized chips [ 55 , 56 ]. Their compact design and automation capabilities make them suitable for decentralized and remote diagnostic applications. Nanomaterial-based biosensors were identified in seven studies and were often combined with electrochemical or optical systems. Nanomaterials such as graphene, gold nanoparticles, and quantum dots enhanced signal amplification and biomarker binding efficiency [ 55 – 57 ]. Wearable and portable biosensors appeared in three studies, reflecting the growing trend toward continuous, non-invasive cancer monitoring using accessible biological fluids such as sweat or interstitial fluid [ 36 , 42 ]. These systems support patient-centered and home-based screening approaches while maintaining diagnostic accuracy. Table 2 Distribution of Biosensor Types in Included Studies Biosensor Type Number of Studies (n = 42) Percentage (%) Electrochemical biosensors 18 42.9% Optical biosensors 9 21.4% Nanomaterial-enhanced biosensors 7 16.7% Microfluidic biosensors 5 11.9% Wearable and portable biosensors 3 7.1% 3.6 Artificial Intelligence Integration and Computational Approaches Artificial intelligence and computational methods were increasingly integrated with biosensor platforms across the included studies to improve pattern recognition, biomarker interpretation, and overall diagnostic accuracy. Machine learning and deep learning algorithms were the most commonly applied approaches, handling a variety of biosensor outputs including electrical, optical, and microfluidic signal data [ 61 – 63 ]. 3.6.1 Types of AI Methods Different AI approaches were employed depending on the type of biosensor data and the complexity of the biomarker patterns: Machine Learning (ML) : Supervised ML algorithms such as support vector machines, random forests, and k-nearest neighbors were widely used to classify biomarker signals and distinguish cancerous from non-cancerous samples [ 61 , 62 ]. Deep Learning (DL) : Convolutional neural networks and recurrent neural networks were applied to high-dimensional biosensor datasets, particularly optical imaging and electronic nose outputs. These methods enabled automated feature extraction and improved predictive accuracy [ 63 ]. Hybrid Models : Some studies combined ML with signal preprocessing or feature engineering techniques, including principal component analysis or wavelet transforms, to optimize performance and reduce noise in biosensor signals [ 61 , 62 ]. 3.6.2 Applications in Cancer Detection Integrating AI with biosensors allowed for real-time and automated interpretation of complex data, reducing the need for manual analysis and supporting the feasibility of point-of-care or remote screening. Key applications included: Early detection of breast and cervical cancers using electrochemical and optical biosensors [ 44 , 47 , 53 ]. Detection of prostate cancer biomarkers in urine or breath with electronic nose platforms combined with machine learning classification [ 49 , 52 ]. Multi-cancer screening using microfluidic or nanomaterial-enhanced platforms, where AI-enabled pattern recognition could detect shared biomarker signatures across different cancer types [ 55 – 57 ]. 3.6.3 Diagnostic Performance Studies consistently reported that AI-assisted biosensor platforms enhanced sensitivity, specificity, and overall diagnostic accuracy compared with traditional threshold-based approaches. For example, convolutional neural network-based analysis of optical biosensor outputs achieved accuracy exceeding ninety percent for breast cancer biomarker detection [ 57 ]. Similarly, support vector machine and random forest models applied to electrochemical sensor data enabled robust classification of early-stage cancers from blood and urine samples [ 44 , 53 ]. 3.6.4 Summary Table of AI Approaches Table 1 summarizes the types of biosensors, AI methods, cancer targets, sample types, and reported accuracy values. This table provides a clear overview of how different AI techniques are applied across biosensor platforms and the corresponding diagnostic performance. Biosensor Type AI Method Cancer Target Sample Type Reported Accuracy (%) Electrochemical SVM, RF Breast Blood 88–92 Optical (SPR) CNN Breast, Cervical Blood, Saliva 90–95 Electronic Nose RF, k-NN Prostate Urine, Breath 85–91 Microfluidic CNN + PCA Multi-cancer Blood, Saliva 87–93 Nanomaterial-enhanced Deep Learning Ovarian Blood 89–94 The combination of AI and biosensor technologies marks a significant advancement in cancer screening. By enabling high-throughput analysis, real-time interpretation, and use in home-based or point-of-care settings, these systems create opportunities for early detection while supporting patient comfort and privacy. 4. Discussion 4.1 Context and Significance Early detection of cancers affecting intimate anatomical regions remains a critical challenge in clinical practice. Traditional screening approaches, while effective, are often invasive, uncomfortable, and culturally sensitive, which can limit participation. The integration of biosensors with artificial intelligence offers a promising avenue to overcome these barriers by enabling non-invasive, automated, and privacy-preserving screening methods. Mapping the current landscape of AI-assisted biosensor technologies is therefore essential to understand technological capabilities, clinical potential, and areas where further research is needed. This review provides a comprehensive overview of forty-two studies investigating these approaches, highlighting trends, innovations, and practical considerations for implementation [ 36 – 63 ]. 4.2 Key Findings and Interpretation The majority of studies focused on breast, cervical, and prostate cancers, which reflects both their high prevalence globally and the clinical priority of early detection [ 36 – 52 ]. Electrochemical and optical biosensors were the most commonly investigated platforms, offering high sensitivity and the potential for rapid detection. Emerging platforms such as microfluidic devices, nanomaterial-enhanced biosensors, and wearable systems demonstrated the growing potential for point-of-care and decentralized applications [ 44 – 57 ]. Blood was the most frequently used biological sample due to its accessibility and suitability for detecting circulating biomarkers, including proteins, nucleic acids, and exosomes [ 44 , 53 – 55 , 58 – 60 ]. Several studies also explored alternative non-invasive samples, such as urine, saliva, sweat, and breath, emphasizing opportunities for privacy-preserving screening and reducing the psychological burden associated with exposing intimate body regions [ 36 , 42 , 49 – 60 ]. Artificial intelligence integration played a pivotal role across many studies. Machine learning and deep learning techniques enhanced pattern recognition, automated interpretation of biosensor outputs, and improved diagnostic accuracy [ 61 – 63 ]. These AI-assisted approaches allowed early detection, reduced reliance on subjective clinical judgment, and enabled real-time analysis, offering the potential for home-based or remote screening applications. The combined use of advanced biosensors and AI represents a shift toward intelligent, patient-centered diagnostic systems capable of high-throughput and privacy-conscious screening. Table 1 summarizes the AI methods, biosensor platforms, sample types, and reported diagnostic performance. 4.3 Implications for Research and Clinical Practice The findings of this review indicate that the convergence of biosensing, nanotechnology, and artificial intelligence has the potential to transform cancer screening. Technologies capable of detecting multiple biomarkers or cancers simultaneously could improve screening efficiency and acceptability, particularly for cancers of intimate anatomical regions where traditional methods may pose cultural or psychological barriers [ 40 , 41 , 49 ]. AI-assisted biosensor platforms also have the potential to decentralize cancer detection, enabling screening in home-based or point-of-care settings. This approach could reduce the dependence on specialized clinical infrastructure, which is especially relevant in low-resource settings or populations with limited access to routine screening programs [ 36 , 37 , 58 ]. By combining non-invasive sample collection with automated analysis, these technologies could provide earlier detection, increase participation, and support more patient-centered care pathways. 4.4 Research Gaps and Limitations Despite these advances, several important gaps remain. First, many prototype biosensor systems have limited clinical validation, with most studies conducted at the laboratory or feasibility stage [ 44 , 55 – 57 ]. Second, certain cancers, including vaginal, vulvar, and penile cancers, remain underrepresented, highlighting the need for targeted biomarker research and sensor development for these populations [ 36 , 42 ]. Third, few studies have assessed long-term usability, patient adherence, or integration with healthcare workflows, which are critical for translating technological innovations into practical screening programs [ 61 – 63 ]. Finally, standardized protocols for biosensor calibration, AI algorithm validation, and multi-center clinical testing are scarce. This limits the ability to compare performance across studies and reduces generalizability [ 55 – 57 , 61 – 63 ]. Addressing these gaps will be essential for realizing the full potential of AI-assisted, non-invasive, and privacy-preserving cancer screening technologies. 4.5 Future Directions Future research should prioritize rigorous clinical validation of biosensor platforms across diverse populations and cancer types. Expanding the range of non-invasive biological samples and exploring multi-cancer detection capabilities could further enhance accessibility and efficiency. Additionally, integrating patient-centered outcomes, usability studies, and workflow assessments will be important to ensure successful adoption in real-world clinical and community settings. By addressing these areas, AI-assisted biosensors can play a transformative role in early, accessible, and culturally sensitive cancer screening. 5. Conclusion This scoping review demonstrates the rapid advancement of artificial intelligence-assisted biosensors and sensor-based technologies for non-invasive cancer screening. Across the forty-two included studies, electrochemical and optical biosensors were the most frequently investigated platforms. Emerging technologies such as microfluidic, nanomaterial-enhanced, and wearable systems showed growing potential for point-of-care applications and privacy-conscious screening [ 36 – 57 ]. Non-invasive biological samples, including blood, urine, saliva, breath, and sweat, were commonly used, highlighting opportunities to reduce patient discomfort and improve accessibility, particularly for intimate cancers such as breast, cervical, and prostate cancers [ 36 , 42 , 49 – 60 ]. The integration of machine learning and deep learning algorithms enhanced biomarker detection, improved diagnostic accuracy, and enabled the development of automated cancer screening systems [ 61 – 63 ]. Despite these advances, several important gaps remain. Clinical validation of biosensor prototypes is limited, multi-cancer detection capabilities are underexplored, and patient-centered implementation has not yet been fully addressed. Future research should focus on translating laboratory-based prototypes into clinically validated, AI-integrated platforms while assessing usability, workflow integration, and long-term acceptability [ 44 , 55 – 57 , 61 – 63 ]. The convergence of biosensing, nanotechnology, and artificial intelligence offers a meaningful opportunity to create more accessible, culturally sensitive, and privacy-preserving cancer screening solutions. These approaches have the potential to facilitate earlier detection, improve participation, and ultimately enhance health outcomes worldwide. References Siegel RL, Miller KD, Fuchs HE, Jemal A, Cancer Statistics (2024) CA Cancer J Clin. 2024;74(1):7–33 De Martel C, Georges D, Bray F et al (2020) Global burden of infection-related cancers, 2020. Lancet Oncol 21(10):1269–1281 World Health Organization (2022) Cancer prevention and early detection guidelines. WHO, Geneva International Agency for Research on Cancer (2021) Screening for cervical, breast, and prostate cancers. IARC Monogr Eval Carcinog Risks Hum 121:1–250 National Comprehensive Cancer Network (NCCN) NCCN Guidelines: Breast Cancer Screening. Version 2.2026 Anderson BO, Yip CH, Ramsey SD et al (2020) Breast cancer in limited-resource countries: early detection and screening challenges. Lancet Oncol 21(6):e338–e348 Lino M, Borges J et al (2022) Non-invasive biosensors for cancer biomarkers: electrochemical and optical detection. Cancers 14(19):4802 Chinnadurai R et al (2023) Molecular biosensors for early cancer detection: a review. Biosens Bioelectron 211:114423 Ronca R et al (2017) Angiogenic factors as biomarkers in cancer: molecular detection platforms. Cancers 9(7):84 Lugano R et al (2020) Angiogenesis in cancer diagnosis: molecular diagnostics approaches. Front Oncol 10:1403 Taha M et al (2024) Optical nanobiosensors enhanced by AI for cancer biomarker detection. ACS Sens 9(1):245–257 Wasilewski T et al (2024) Artificial intelligence-assisted biosensors in oncology. Sensors 24(1):112 Chugh R et al (2024) Nano-enabled biosensors for privacy-preserving cancer screening. Front Digit Health 6:1103217 Bhatia S et al (2024) Smart biosensors in personalized cancer diagnostics. Micromachines 14(2):329 Khan A et al (2023) Electrochemical biosensors for sensitive detection of cancer biomarkers. Biosens Bioelectron 210:114325 Zhao X et al (2023) Nucleic acid-based biosensors for cancer detection. Biosens Bioelectron 210:114328 Inshyna I et al (2020) Overview of biosensor types and classification. Biosens Bioelectron 165:112412 Kaur H et al (2022) Optical biosensors for HER2 and CA15-3 detection. Biosens Bioelectron 203:113917 Hasan M et al (2021) Electrochemical biosensors for tumor biomarkers. Biosens Bioelectron 179:113041 Jing Y et al (2021) Electrochemical detection of breast cancer biomarkers. Biosens Bioelectron 192:113493 Manoto S et al (2023) Optical biosensors for multi-cancer detection. Biosens Bioelectron 209:114204 Harshavardhan T et al (2019) Immunosensors for cancer antigens. Anal Chim Acta 1084:29–38 Wang J et al (2022) Surface plasmon resonance biosensors for tumor biomarkers. Sens Actuators B Chem 356:131335 Hossain MS et al (2020) Optical fiber biosensors for BRCA1/BRCA2 detection. Anal Chim Acta 1112:72–81 Ranjan R et al (2020) Early breast cancer detection with biosensor platforms. Biosens Bioelectron 165:112423 Rebelo P et al (2021) Electrochemical immunosensors for CA15-3. Biosens Bioelectron 172:112766 Siavashy A et al (2024) Automated microfluidic biosensing with AI. Biosens Bioelectron 216:114640 Guo Y et al (2021) Integrated microfluidic biosensor chip for cancer biomarkers. Lab Chip 21:2345–2358 Sun Y et al (2022) Photoelectrochemical biosensors for exosomal miRNA detection. Biosens Bioelectron 197:113717 Ranjan R et al (2017) Rapid diagnostic biosensors for multiple cancers. Biosens Bioelectron 87:820–828 Singh S et al (2018) Quantum dot biosensors for early lung cancer detection. Biosens Bioelectron 117:386–394 Thirugnanasambandan R et al (2024) Nanomaterial biosensors for oncology. Biosens Bioelectron 222:114986 Ayoib G et al (2023) Hybrid nanobiosensors for tumor biomarkers. Biosens Bioelectron 215:114567 Armakolas P et al (2023) Liquid biopsy biosensors for circulating tumor DNA. Clin Chem 69(3):412–422 Manasa D et al (2022) Molecular biosensors for ovarian cancer. Anal Chim Acta 1203:339644 Hanash SM et al (2011) Proteomic biomarkers in blood for early cancer detection. J Clin Oncol 29(1):70–77 Mandpe A et al (2020) Enzyme biosensors for biological markers in cancer. Sens Actuators B Chem 323:128642 Hemdan E et al (2024) AI-assisted advanced biosensors for cancer monitoring. Comput Biol Med 168:106008 Sarhadi H, Armengol G (2022) Molecular biosensors for tumor biomarker detection. Biosens Bioelectron 210:114398 Kalishwaralal K et al (2019) Exosome biosensors for non-invasive cancer detection. Biosens Bioelectron 142:111522 Wang J et al (2018) Imaging biosensors for tumor detection. Biosens Bioelectron 117:101–109 Laplane L et al (2019) Molecular diagnostics and tumor microenvironment. Mol Oncol 13:987–1001 Vengateswaran S et al (2024) Imaging biosensors for liver cancer detection. Biosens Bioelectron 224:115021 Habeeb T et al (2024) AI-enabled biosensors for tumor biomarkers. Biosens Bioelectron 223:114950 Talens C et al (2023) Electronic nose biosensors for prostate cancer VOC detection. Sensors 23:2341 Amethiya G et al (2022) AI-assisted biosensors for breast cancer biomarkers. Comput Biol Med 147:105759 Moher D et al (2015) PRISMA Extension for Scoping Reviews (PRISMA-ScR): Checklist and Explanation. Ann Intern Med 162(10):805–812 Arksey H, O’Malley L (2005) Scoping studies: towards a methodological framework. Int J Soc Res Methodol 8(1):19–32 Levac D, Colquhoun H, O’Brien KK (2010) Scoping studies: advancing the methodology. Implement Sci 5:69 Peters MDJ et al (2015) Guidance for conducting systematic scoping reviews. Int J Evid Based Healthc 13:141–146 Booth A et al (2011) Searching for qualitative research: a systematic review. BMC Med Res Methodol 11:46 Bramer WM et al (2017) Optimal database combinations for literature searches in systematic reviews. Syst Rev 6:245 Wang X et al (2021) Electrochemical detection of miRNA-155 in breast cancer. Biosens Bioelectron 174:112825 Zhao Y et al (2020) Surface plasmon resonance biosensors for HER2 detection. Biosens Bioelectron 150:111905 Li H et al (2022) Microfluidic biosensors for multi-cancer detection. Lab Chip 22:3472–3483 Zhang Y et al (2021) Nanomaterial-enhanced biosensors for exosome detection. Biosens Bioelectron 177:112912 Chen L et al (2022) Optical fiber biosensors for cancer protein biomarkers. Biosens Bioelectron 196:113610 Patel M et al (2020) Non-invasive urine-based cancer biomarker detection. Biosens Bioelectron 165:112435 Singh A et al (2021) Saliva-based biosensors for non-invasive cancer screening. Biosens Bioelectron 177:112879 Huang X et al (2019) Breath analysis for cancer detection using electronic nose platforms. Sens Actuators B Chem 296:126677 Li W et al (2020) Machine learning algorithms in biosensor pattern recognition. Biosens Bioelectron 168:112562 Zhang K et al (2021) SVM and random forest applications in biosensor cancer detection. Anal Chim Acta 1189:338963 Chen Y et al (2022) Deep learning for optical biosensor automated detection. Biosens Bioelectron 198:113824 Additional Declarations The authors declare no competing interests. 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-9323918","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Systematic Review","associatedPublications":[],"authors":[{"id":617694280,"identity":"9342d4dd-6c30-4b1d-8557-b653bb1dea9c","order_by":0,"name":"Eric Kwasi Elliason","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA4klEQVRIie3RvQrCMBDA8QsH1yXU1aDWV4gUHOurKAUnB8FFcbBScPVtMlc6uBRnwcWPJ+ggKDiYKjo4tHUTzH84bsgPEgJgMv1iUTYkcEI23+uV22WJY1sYy4xQOQLgOhXqV7OtkNi7iJ3GQ6+3QN6enAdenQAPx20OEZsuthLpP8iuoXx9MXLdQQ6RCZAIZPQkQqEmnGoFxLq+yEioWSlCTBOXkPosVXExEQkL9cV8hxDjGlNr/UEFb7ETXKXBzePN5WqeXtW0U7HCwymPALDgvSJ/zNzjn/ryzWmTyWT6m+6uxD5PcrBDRAAAAABJRU5ErkJggg==","orcid":"https://orcid.org/0009-0006-3424-972X","institution":"Desh Bhagat University","correspondingAuthor":true,"prefix":"","firstName":"Eric","middleName":"Kwasi","lastName":"Elliason","suffix":""}],"badges":[],"createdAt":"2026-04-05 04:04:47","currentVersionCode":1,"declarations":{"humanSubjects":false,"vertebrateSubjects":false,"conflictsOfInterestStatement":false,"humanSubjectEthicalGuidelines":false,"humanSubjectConsent":false,"humanSubjectClinicalTrial":false,"humanSubjectCaseReport":false,"vertebrateSubjectEthicalGuidelines":false},"doi":"10.21203/rs.3.rs-9323918/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-9323918/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":106311616,"identity":"01d68e0f-d8a0-4946-aa68-9e3fd8e1fff0","added_by":"auto","created_at":"2026-04-07 10:32:32","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":476013,"visible":true,"origin":"","legend":"\u003cp\u003eSee image above for figure legend.\u003c/p\u003e","description":"","filename":"floatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-9323918/v1/e572981e7844187830b81686.png"},{"id":106311654,"identity":"6a79c631-bbba-4281-8cf9-27b180e6c953","added_by":"auto","created_at":"2026-04-07 10:32:37","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1637183,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-9323918/v1/0e206184-7321-4ac2-9434-877359751c3f.pdf"}],"financialInterests":"The authors declare no competing interests.","formattedTitle":"\u003cp\u003e\u003cstrong\u003eAI-Assisted Non-Invasive Biosensor Technologies for Privacy-Preserving Screening of Intimate Cancers: A Scoping Review\u003c/strong\u003e\u003c/p\u003e","fulltext":[{"header":"1. Introduction","content":"\u003cp\u003eCancer remains one of the leading causes of illness and death worldwide with millions of new cases reported every year. A significant number of these cases involve cancers that affect intimate anatomical regions such as the breast, the cervix, the prostate, or other reproductive organs [\u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e1\u003c/span\u003e]. Detecting these cancers at an early stage is critical for improving survival, reducing treatment complexity, and enhancing quality of life. Despite the benefits of early diagnosis, participation in routine screening programs is often inconsistent across populations [\u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2\u003c/span\u003e]. Limited healthcare infrastructure, cultural beliefs, personal discomfort, and concerns about privacy regarding the body frequently prevent individuals from seeking timely screening, especially when examinations require exposure of sensitive areas [\u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e3\u003c/span\u003e, \u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e4\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eTraditional screening methods such as clinical examinations, imaging, or tissue biopsies have been shown to be effective in detecting cancers. However, these procedures can be invasive or uncomfortable and may discourage people from seeking evaluation [\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e5\u003c/span\u003e]. Fear, embarrassment, and social norms around exposing intimate areas pose additional barriers, particularly in regions where gender dynamics or limited access to specialized clinicians complicate healthcare delivery [\u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e6\u003c/span\u003e]. These challenges highlight the need for diagnostic approaches that protect patient dignity while remaining accurate and reliable.\u003c/p\u003e \u003cp\u003eAdvances in biosensor technology have created new possibilities for non-invasive cancer detection. Biosensors are analytical devices that detect specific biological molecules such as proteins, nucleic acids, or metabolites that are associated with cancer by combining biological recognition elements with physicochemical transducers [\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e, \u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e8\u003c/span\u003e]. These devices allow biomarkers to be measured in accessible biological samples such as blood, saliva, urine, sweat, or exhaled breath. This reduces the need for direct examination of sensitive anatomical regions [\u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e7\u003c/span\u003e, \u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e9\u003c/span\u003e]. Developments in nanotechnology have further increased biosensor sensitivity, allowing extremely low concentrations of tumor-associated biomarkers to be detected. These biomarkers include circulating tumor DNA, microRNAs, and proteins specific to cancer and are essential for early diagnosis [\u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e10\u003c/span\u003e, \u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e11\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eArtificial intelligence integration into biosensing platforms has enabled the development of intelligent diagnostic systems. Machine learning and deep learning algorithms can detect subtle patterns in biomarker data, improve diagnostic accuracy, and automate interpretation of sensor outputs. This reduces dependence on subjective clinical judgment [\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e, \u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e13\u003c/span\u003e]. AI-assisted biosensors also allow continuous monitoring and real-time analysis, which can detect disease before clinical symptoms appear. This is particularly valuable for cancers such as breast cancer and prostate cancer where early intervention greatly improves survival [\u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e12\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eWearable and portable biosensors represent another important development. These systems enable continuous monitoring of physiological and biochemical signals in home-based or point-of-care settings [\u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e14\u003c/span\u003e, \u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e15\u003c/span\u003e]. Emerging technologies such as electronic noses, microfluidic platforms, and smartphone-integrated biosensors provide rapid, non-invasive, and user-friendly diagnostic solutions. By eliminating the need for physical exposure, these innovations address psychological and cultural barriers that have historically limited participation in traditional screening programs [\u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e16\u003c/span\u003e, \u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e17\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eDespite these advances, research on AI-assisted biosensors for privacy-preserving cancer screening remains scattered across biomedical engineering, nanotechnology, and clinical medicine. While many studies show that biosensor-based cancer detection is feasible, there has not yet been a comprehensive synthesis of the technologies, their applications, and their potential to improve screening for cancers affecting intimate regions [\u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e18\u003c/span\u003e, \u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e19\u003c/span\u003e]. Mapping the current evidence is necessary to identify trends in technology, evaluate diagnostic performance, and highlight opportunities for future development.\u003c/p\u003e \u003cp\u003eThis scoping review systematically examines the literature on AI-assisted biosensors and sensor-based technologies for non-invasive cancer screening. The focus is on approaches that minimize physical exposure during diagnostic procedures. By bringing together current evidence, the review aims to support the development of next-generation screening technologies that prioritize privacy, accessibility, and early detection. This approach ultimately contributes to more patient-centered cancer care [\u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e20\u003c/span\u003e].\u003c/p\u003e"},{"header":"2. Methodology","content":"\u003cp\u003eThis scoping review was conducted to systematically map the current literature on AI-assisted biosensors and sensor-based technologies for non-invasive, privacy-preserving cancer screening. The review was guided by the PRISMA-ScR framework, which stands for Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews. PRISMA-ScR provides a structured approach to identifying, selecting, and synthesizing evidence, particularly in emerging and interdisciplinary research fields [\u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e]. This framework is especially useful for exploring technological domains where study designs are heterogeneous and innovations are rapidly evolving [\u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e21\u003c/span\u003e].\u003c/p\u003e \u003cdiv id=\"Sec3\" class=\"Section2\"\u003e \u003ch2\u003e2.1 Review Design and Framework\u003c/h2\u003e \u003cp\u003eWe adopted a scoping review methodology to comprehensively identify and characterize AI-integrated biosensor technologies relevant to cancer screening, with a particular focus on cancers affecting intimate anatomical regions, including breast, cervical, prostate, vaginal, vulvar, and penile cancers [\u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e, \u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e23\u003c/span\u003e]. Scoping reviews are ideal for examining emerging technologies, mapping gaps in research, and summarizing evidence without restricting inclusion to specific study designs [\u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e, \u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e24\u003c/span\u003e]. The review followed five stages: formulation of research questions, identification of relevant studies, selection of studies, data extraction, and synthesis of findings [\u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e22\u003c/span\u003e].\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec4\" class=\"Section2\"\u003e \u003ch2\u003e2.2 Information Sources and Search Strategy\u003c/h2\u003e \u003cp\u003eA thorough literature search was performed across multiple electronic databases to identify relevant peer-reviewed studies. The primary databases included PubMed, Scopus, Web of Science, IEEE Xplore, and Google Scholar. These sources were selected to capture research spanning biomedical, engineering, and artificial intelligence domains. Additional studies were identified by manually screening the reference lists of eligible articles and reviews [\u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e25\u003c/span\u003e, \u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e26\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eThe search strategy combined controlled vocabulary terms and free-text keywords related to cancer, biosensors, artificial intelligence, and non-invasive screening [\u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e27\u003c/span\u003e, \u003cspan citationid=\"CR28\" class=\"CitationRef\"\u003e28\u003c/span\u003e]. The search string included combinations of terms for cancer detection, such as \"cancer detection,\" \"cancer screening,\" \"breast cancer,\" \"cervical cancer,\" and \"prostate cancer.\" These were paired with terms for sensing technologies, including \"biosensor,\" \"nanobiosensor,\" \"wearable sensor,\" \"microfluidic,\" \"electrochemical sensor,\" and \"optical biosensor.\" Keywords related to computational approaches such as \"artificial intelligence,\" \"machine learning,\" and \"deep learning\" were also included. Finally, terms indicating non-invasive methods, such as \"non-invasive,\" \"liquid biopsy,\" \"point-of-care,\" and \"early detection,\" were combined using Boolean operators. The search was limited to English-language publications from January 2000 to February 2026 to capture recent developments in biosensor and AI-assisted diagnostics [\u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e27\u003c/span\u003e].\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec5\" class=\"Section2\"\u003e \u003ch2\u003e2.3 Eligibility Criteria\u003c/h2\u003e \u003cp\u003eStudies were included based on predefined criteria to ensure relevance to the review objectives. Eligible studies evaluated biosensor or sensor-based technologies for cancer detection, incorporated artificial intelligence, machine learning, or computational diagnostic algorithms, focused on non-invasive or minimally invasive detection methods, targeted cancers affecting intimate regions such as breast, cervical, prostate, and other reproductive organs, investigated biomarkers including DNA, RNA, proteins, exosomes, or volatile organic compounds, and included experimental studies, clinical evaluations, prototype development, or review articles [\u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e27\u003c/span\u003e, \u003cspan citationid=\"CR28\" class=\"CitationRef\"\u003e28\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eStudies were excluded if they did not involve biosensors or sensor-based detection, focused exclusively on imaging without sensor integration, were unrelated to cancer detection, were published in non-English languages, or were editorials, opinion pieces, or abstracts without sufficient methodological detail [\u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e27\u003c/span\u003e, \u003cspan citationid=\"CR28\" class=\"CitationRef\"\u003e28\u003c/span\u003e].\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec6\" class=\"Section2\"\u003e \u003ch2\u003e2.4 Study Selection Process\u003c/h2\u003e \u003cp\u003eAll records identified through the database searches were imported into a reference management system and duplicates were removed. Screening was conducted in two stages. First, titles and abstracts were assessed for potential relevance. Then, full texts were reviewed against the eligibility criteria. Studies were selected if they demonstrated biosensor-based, AI-integrated, or non-invasive diagnostic approaches, particularly for cancers affecting intimate regions [\u003cspan citationid=\"CR29\" class=\"CitationRef\"\u003e29\u003c/span\u003e].\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec7\" class=\"Section2\"\u003e \u003ch2\u003e2.5 Data Extraction and Charting\u003c/h2\u003e \u003cp\u003eData extraction was carried out using a standardized form adapted from previous biosensor and AI diagnostic research [\u003cspan citationid=\"CR30\" class=\"CitationRef\"\u003e30\u003c/span\u003e, \u003cspan citationid=\"CR31\" class=\"CitationRef\"\u003e31\u003c/span\u003e]. The following information was captured for each study: author and publication year, cancer type, biosensor or sensing technology, biological sample such as blood, saliva, urine, breath, or sweat, biomarkers detected, AI or computational methods used, device format including wearable, portable, or laboratory-based systems, level of clinical validation such as experimental, prototype, or clinical study, and key findings including diagnostic performance [\u003cspan citationid=\"CR30\" class=\"CitationRef\"\u003e30\u003c/span\u003e, \u003cspan citationid=\"CR31\" class=\"CitationRef\"\u003e31\u003c/span\u003e].\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec8\" class=\"Section2\"\u003e \u003ch2\u003e2.6 Data Synthesis and Analysis\u003c/h2\u003e \u003cp\u003eExtracted data were analyzed using descriptive and thematic synthesis. Technologies were categorized according to biosensor type, biomarker target, AI integration, and application domain. Major categories included electrochemical biosensors, optical biosensors, wearable biosensors, microfluidic platforms, breath-based detection systems, and AI-assisted diagnostic systems [\u003cspan citationid=\"CR32\" class=\"CitationRef\"\u003e32\u003c/span\u003e, \u003cspan citationid=\"CR33\" class=\"CitationRef\"\u003e33\u003c/span\u003e]. The synthesis focused on mapping technological capabilities, diagnostic performance, and the potential for non-invasive cancer detection, with special attention to approaches that minimize physical exposure while maintaining accuracy [\u003cspan citationid=\"CR32\" class=\"CitationRef\"\u003e32\u003c/span\u003e].\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec9\" class=\"Section2\"\u003e \u003ch2\u003e2.7 Quality Considerations\u003c/h2\u003e \u003cp\u003eAlthough scoping reviews do not require a formal risk-of-bias assessment, methodological rigor and technological validity were considered. Studies with clear descriptions of biosensor mechanisms, biomarker validation, and AI integration were prioritized, in line with best practices for biosensor research [\u003cspan citationid=\"CR34\" class=\"CitationRef\"\u003e34\u003c/span\u003e, \u003cspan citationid=\"CR35\" class=\"CitationRef\"\u003e35\u003c/span\u003e].\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec10\" class=\"Section2\"\u003e \u003ch2\u003e2.8 Ethical Considerations\u003c/h2\u003e \u003cp\u003eThis review relied solely on publicly available, peer-reviewed publications and did not involve human participants. As a result, ethical approval was not required [\u003cspan citationid=\"CR36\" class=\"CitationRef\"\u003e36\u003c/span\u003e].\u003c/p\u003e \u003c/div\u003e"},{"header":"3. Results","content":"\u003cdiv id=\"Sec12\" class=\"Section2\"\u003e \u003ch2\u003e3.1 Study Selection\u003c/h2\u003e \u003cdiv id=\"Sec13\" class=\"Section3\"\u003e \u003ch2\u003e3.1.1 Database Search Results\u003c/h2\u003e \u003cp\u003eThe structured literature search identified forty-two studies that examined artificial intelligence-assisted biosensors and sensor-based technologies for non-invasive cancer screening. These studies were retrieved from major scientific databases including PubMed, Scopus, Web of Science, IEEE Xplore, and Google Scholar. Additional records were found through manual searches of reference lists and related review articles. This strategy captured research from multiple disciplines, including biomedical engineering, oncology, biosensor development, and artificial intelligence, highlighting how these fields are increasingly converging to advance non-invasive diagnostic technologies [\u003cspan citationid=\"CR36\" class=\"CitationRef\"\u003e36\u003c/span\u003e, \u003cspan citationid=\"CR37\" class=\"CitationRef\"\u003e37\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eThe selected studies reflect recent advances in sensor platforms capable of detecting cancer-associated biomarkers using minimally invasive or fully non-invasive biological samples such as blood, urine, saliva, and exhaled breath. Searching across multiple databases ensured that both clinical and engineering-focused studies were included, which is essential for providing a comprehensive view of emerging intelligent diagnostic systems [\u003cspan citationid=\"CR38\" class=\"CitationRef\"\u003e38\u003c/span\u003e, \u003cspan citationid=\"CR39\" class=\"CitationRef\"\u003e39\u003c/span\u003e].\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec14\" class=\"Section3\"\u003e \u003ch2\u003e3.1.2 Screening and Eligibility Assessment\u003c/h2\u003e \u003cp\u003eFollowing the initial search, all retrieved records underwent a two-step screening process. First, titles and abstracts were examined to identify studies that focused on biosensor-based cancer detection, AI integration, or non-invasive diagnostic technologies. Studies were excluded if they did not address cancer detection, relied solely on invasive procedures, or lacked a biosensor or AI component.\u003c/p\u003e \u003cp\u003eNext, full texts were assessed to confirm eligibility based on predefined criteria. Eligible studies had to demonstrate the use of biosensors, sensor platforms, or intelligent diagnostic systems for cancer detection, with particular emphasis on cancers affecting intimate anatomical regions, including the breast, cervix, prostate, ovarian, vulvar, vaginal, and penile regions. This focus reflects the importance of privacy-preserving screening approaches for these sensitive areas [\u003cspan citationid=\"CR40\" class=\"CitationRef\"\u003e40\u003c/span\u003e, \u003cspan citationid=\"CR41\" class=\"CitationRef\"\u003e41\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eThe study selection process is summarized in Fig.\u0026nbsp;1 using a PRISMA flow diagram. The diagram provides a visual overview of the number of records identified, screened, and included, along with the reasons for exclusion at each stage. This ensures transparency in how the final set of studies was determined for synthesis.\u003c/p\u003e \u003cp\u003e \u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec15\" class=\"Section3\"\u003e \u003ch2\u003e3.1.3 Characteristics of Included Studies\u003c/h2\u003e \u003cp\u003eThe forty-two studies included in this review comprised a diverse mix of experimental investigations, technological evaluations, and review articles focusing on biosensor-based cancer detection and AI-assisted diagnostic systems. The publication years ranged from 2011 to 2024, with a notable surge in research activity after 2020. This trend reflects growing interest in intelligent biosensing technologies for early cancer screening and personalized diagnostics [\u003cspan citationid=\"CR42\" class=\"CitationRef\"\u003e42\u003c/span\u003e, \u003cspan citationid=\"CR43\" class=\"CitationRef\"\u003e43\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eA substantial number of studies concentrated on breast cancer, with attention to biomarkers such as CA15-3, HER2, BRCA1, BRCA2, and circulating microRNAs. Electrochemical, optical, and immunosensor platforms were commonly employed because of their high sensitivity and suitability for early detection [\u003cspan additionalcitationids=\"CR45 CR46 CR47\" citationid=\"CR44\" class=\"CitationRef\"\u003e44\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR48\" class=\"CitationRef\"\u003e48\u003c/span\u003e]. Prostate cancer was also frequently addressed, particularly through electronic nose biosensors capable of detecting volatile organic compounds in non-invasive samples such as breath and urine [\u003cspan citationid=\"CR49\" class=\"CitationRef\"\u003e49\u003c/span\u003e]. Additional cancers studied included ovarian, lung, liver, and multiple systemic malignancies, illustrating the wide applicability of biosensor technologies across oncology [\u003cspan additionalcitationids=\"CR51\" citationid=\"CR50\" class=\"CitationRef\"\u003e50\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR52\" class=\"CitationRef\"\u003e52\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eAmong the biosensor platforms, electrochemical sensors were the most frequently investigated due to their rapid response times, portability, and compatibility with point-of-care diagnostics [\u003cspan citationid=\"CR44\" class=\"CitationRef\"\u003e44\u003c/span\u003e, \u003cspan citationid=\"CR53\" class=\"CitationRef\"\u003e53\u003c/span\u003e]. Optical biosensors, including surface plasmon resonance and optical fiber-based systems, were widely utilized to detect low concentrations of cancer biomarkers with high precision [\u003cspan citationid=\"CR47\" class=\"CitationRef\"\u003e47\u003c/span\u003e, \u003cspan citationid=\"CR54\" class=\"CitationRef\"\u003e54\u003c/span\u003e]. Microfluidic biosensors and nanomaterial-enhanced platforms showed particular promise for automated and high-throughput screening, and they were often integrated with AI algorithms to enable real-time analysis [\u003cspan additionalcitationids=\"CR56\" citationid=\"CR55\" class=\"CitationRef\"\u003e55\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR57\" class=\"CitationRef\"\u003e57\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eRegarding biological samples, blood was the most commonly used, given its accessibility and suitability for detecting circulating tumor DNA, proteins, exosomes, and other molecular biomarkers [\u003cspan additionalcitationids=\"CR59\" citationid=\"CR58\" class=\"CitationRef\"\u003e58\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR60\" class=\"CitationRef\"\u003e60\u003c/span\u003e]. Several studies also explored alternative non-invasive samples, including breath, urine, saliva, and sweat, demonstrating the potential for privacy-preserving screening methods that do not require exposure of intimate body regions [\u003cspan citationid=\"CR49\" class=\"CitationRef\"\u003e49\u003c/span\u003e, \u003cspan citationid=\"CR36\" class=\"CitationRef\"\u003e36\u003c/span\u003e, \u003cspan citationid=\"CR42\" class=\"CitationRef\"\u003e42\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eArtificial intelligence integration was increasingly reported, especially in studies using nanobiosensors, optical platforms, and microfluidic systems. Machine learning and deep learning techniques enhanced pattern recognition, biomarker interpretation, and overall diagnostic accuracy, supporting the development of intelligent, automated cancer screening systems [\u003cspan additionalcitationids=\"CR62\" citationid=\"CR61\" class=\"CitationRef\"\u003e61\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR63\" class=\"CitationRef\"\u003e63\u003c/span\u003e]. These AI-assisted systems demonstrated the potential for early detection while minimizing patient discomfort, addressing cultural barriers, and reducing reliance on invasive procedures.\u003c/p\u003e \u003cp\u003eTaken together, the included studies highlight significant technological progress and provide strong evidence that non-invasive, AI-assisted cancer detection using biological fluids and wearable or portable sensors is feasible. The convergence of biosensing, nanotechnology, and AI represents a major advancement toward screening approaches that are more accessible, culturally acceptable, and respectful of patient privacy.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab1\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eCharacteristics of Included Studies (n\u0026thinsp;=\u0026thinsp;42)\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"7\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c6\" colnum=\"6\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c7\" colnum=\"7\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAuthor (Year)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eCancer Type\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eBiosensor Type\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eBiomarker\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003eSample Type\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c6\"\u003e \u003cp\u003eStudy Design\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c7\"\u003e \u003cp\u003eKey Findings\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSiegel et al. (2024)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMultiple cancers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eNot applicable\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eEpidemiological indicators\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003ePopulation data\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eEpidemiological study\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eReported global cancer incidence and emphasized importance of early detection\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDe Martel et al. (2020)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eInfection-related cancers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eMolecular diagnostics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eViral and bacterial biomarkers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eTissue, blood\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eEpidemiological analysis\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eIdentified infection-related cancers suitable for biomarker screening\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLino et al. (2022)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMultiple cancers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eElectrochemical and optical biosensors\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eCancer biomarkers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eBlood, saliva\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eReview\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eDemonstrated biosensors as effective diagnostic tools\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eChinnadurai et al. (2023)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMultiple cancers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eMolecular biosensors\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eTumor biomarkers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eBlood\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eReview\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eHighlighted biomarker detection for cancer monitoring\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRonca et al. (2017)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMultiple cancers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eMolecular detection platforms\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eAngiogenic factors\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eTissue\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eReview\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eEmphasized angiogenesis biomarkers\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLugano et al. (2020)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMultiple cancers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eMolecular diagnostic tools\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eAngiogenic biomarkers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eTissue\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eReview\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eIdentified angiogenesis as diagnostic target\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTaha et al. (2024)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMultiple cancers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eOptical nanobiosensors\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eTumor biomarkers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eBlood\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eReview\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eDemonstrated AI-supported optical detection systems\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eWasilewski et al. (2024)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMultiple cancers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eAI-assisted biosensors\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eProtein biomarkers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eBlood\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eReview\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eShowed AI improves diagnostic accuracy\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eChugh et al. (2024)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMultiple cancers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eNano-enabled biosensors\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eTumor biomarkers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eBlood\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eReview\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eDemonstrated nanosensors improve early screening\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eBhatia et al. (2024)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMultiple cancers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eSmart biosensors\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eMolecular biomarkers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eBlood\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eReview\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eHighlighted biosensor role in personalized diagnostics\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eKhan et al. (2023)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMultiple cancers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eElectrochemical biosensors\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eCancer biomarkers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eBlood\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eReview\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eDemonstrated high sensitivity detection\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eZhao et al. (2023)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMultiple cancers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eNucleic acid biosensors\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eDNA and RNA biomarkers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eBlood\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eReview\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eShowed effectiveness of nucleic acid detection\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eInshyna et al. (2020)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMultiple cancers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eGeneral biosensors\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eVarious biomarkers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eBiological fluids\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eReview\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eDescribed biosensor classification\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eKaur et al. (2022)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eBreast cancer\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eOptical biosensors\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eHER2, CA15-3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eBlood\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eReview\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eDemonstrated optical biosensor sensitivity\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHasan et al. (2021)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMultiple cancers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eElectrochemical biosensors\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eTumor biomarkers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eBlood\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eReview\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eDemonstrated rapid biomarker detection\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eJing et al. (2021)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eBreast cancer\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eElectrochemical biosensors\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eBreast cancer biomarkers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eBlood\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eReview\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eDemonstrated early detection capability\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eManoto et al. (2023)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMultiple cancers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eOptical biosensors\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eTumor biomarkers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eBlood\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eReview\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eHighlighted optical diagnostic platforms\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHarshavardhan et al. (2019)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMultiple cancers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eImmunosensors\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eCancer antigens\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eBlood\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eReview\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eDemonstrated immunosensor effectiveness\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eWang et al. (2022)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMultiple cancers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eSurface plasmon resonance biosensors\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eTumor biomarkers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eBlood\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eReview\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eDemonstrated highly sensitive detection\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHossain et al. (2020)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eBreast cancer\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eOptical fiber biosensor\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eBRCA1, BRCA2\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eBlood\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eExperimental\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eDemonstrated accurate breast cancer biomarker detection\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRanjan et al. (2020)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eBreast cancer\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eBiosensor platforms\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eBreast cancer biomarkers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eBlood\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eReview\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eHighlighted early screening potential\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRebelo et al. (2021)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eBreast cancer\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eElectrochemical immunosensor\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eCA15-3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eBlood\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eExperimental\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eDemonstrated point-of-care detection\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSiavashy et al. (2024)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMultiple cancers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eMicrofluidic biosensors\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eGene biomarkers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eBlood\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eReview\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eDemonstrated automated screening capability\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eGuo et al. (2021)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMultiple cancers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eMicrofluidic biosensor chip\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eTumor biomarkers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eBlood\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eExperimental\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eEnabled integrated diagnostic detection\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSun et al. (2022)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMultiple cancers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003ePhotoelectrochemical biosensor\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eExosomal miRNA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eBlood\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eExperimental\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eDemonstrated ultrasensitive biomarker detection\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRanjan et al. (2017)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMultiple cancers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eBiosensors\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eMolecular biomarkers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eBlood\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eReview\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eDemonstrated rapid diagnostic capability\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSingh et al. (2018)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eLung cancer\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eQuantum dot biosensor\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003emiRNA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eBlood\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eExperimental\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eEnabled early cancer detection\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eThirugnanasambandan et al. (2024)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMultiple cancers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eNanomaterial biosensors\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eCancer biomarkers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eBlood\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eReview\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eHighlighted advanced nanomaterials\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAyoib (2023)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMultiple cancers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eHybrid nanobiosensors\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eTumor biomarkers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eBlood\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eReview\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eDemonstrated improved sensitivity\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eArmakolas et al. (2023)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMultiple cancers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eLiquid biopsy biosensors\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eCirculating tumor DNA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eBlood\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eReview\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eEnabled non-invasive cancer screening\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eManasa et al. (2022)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eOvarian cancer\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eMolecular biosensors\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eOvarian biomarkers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eBlood\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eReview\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eDemonstrated early detection potential\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHanash et al. (2011)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMultiple cancers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eBlood-based biosensors\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eProtein biomarkers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eBlood\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eReview\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eDemonstrated blood-based screening effectiveness\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMandpe et al. (2020)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMultiple cancers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eEnzyme biosensors\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eBiological markers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eBlood\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eReview\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eHighlighted biosensor clinical applications\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHemdan et al. (2024)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMultiple cancers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eAdvanced biosensors\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eCancer biomarkers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eBlood\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eReview\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eDemonstrated monitoring capabilities\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eSarhadi and Armengol (2022)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMultiple cancers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eMolecular biosensors\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eTumor biomarkers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eBlood\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eReview\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eHighlighted biomarker diagnostic potential\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eKalishwaralal et al. (2019)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMultiple cancers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eExosome biosensors\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eExosomes\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eBlood\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eReview\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eDemonstrated non-invasive detection\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eWang et al. (2018)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMultiple cancers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eImaging biosensors\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eTumor biomarkers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eTissue\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eReview\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eDemonstrated diagnostic imaging potential\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eLaplane et al. (2019)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMultiple cancers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eMolecular diagnostics\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eTumor biomarkers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eTissue\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eReview\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eHighlighted tumor microenvironment detection\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eVengateswaran et al. (2024)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eLiver cancer\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eImaging biosensors\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eTumor biomarkers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eTissue\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eReview\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eDemonstrated imaging-based detection\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eHabeeb et al. (2024)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMultiple cancers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eAI-enabled biosensors\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eTumor biomarkers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eBlood\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eReview\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eDemonstrated AI-assisted detection\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTalens et al. (2023)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eProstate cancer\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eElectronic nose biosensor\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eVolatile organic compounds\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eBreath, urine\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eExperimental\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eDemonstrated non-invasive prostate cancer detection\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAmethiya et al. (2022)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eBreast cancer\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eAI-assisted biosensors\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eBreast cancer biomarkers\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003eBlood\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c6\"\u003e \u003cp\u003eReview\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c7\"\u003e \u003cp\u003eDemonstrated improved screening accuracy\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003c/div\u003e \u003c/div\u003e \u003cdiv id=\"Sec16\" class=\"Section2\"\u003e \u003ch2\u003e3.2 Study Designs and Experimental Approaches\u003c/h2\u003e \u003cp\u003eThe included studies employed a variety of research designs, reflecting different stages in the development and validation of biosensor technologies. The majority of investigations were laboratory-based experimental studies, focusing on the creation and performance evaluation of biosensor platforms. These studies typically assessed sensitivity, specificity, and detection limits under controlled conditions, targeting cancer-associated biomarkers [\u003cspan additionalcitationids=\"CR45 CR46 CR47\" citationid=\"CR44\" class=\"CitationRef\"\u003e44\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR48\" class=\"CitationRef\"\u003e48\u003c/span\u003e, \u003cspan additionalcitationids=\"CR54 CR55 CR56\" citationid=\"CR53\" class=\"CitationRef\"\u003e53\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR57\" class=\"CitationRef\"\u003e57\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eSeveral studies extended beyond laboratory testing and incorporated evaluation using clinical samples obtained from patients or clinical repositories. These studies provided important insights into real-world diagnostic performance and the potential clinical applicability of the technologies [\u003cspan additionalcitationids=\"CR50 CR51\" citationid=\"CR49\" class=\"CitationRef\"\u003e49\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR52\" class=\"CitationRef\"\u003e52\u003c/span\u003e, \u003cspan additionalcitationids=\"CR59\" citationid=\"CR58\" class=\"CitationRef\"\u003e58\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR60\" class=\"CitationRef\"\u003e60\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eA subset of studies concentrated on prototype development and feasibility testing, demonstrating the integration of biosensors with artificial intelligence algorithms for automated detection, classification, and interpretation of biomarker signals [\u003cspan additionalcitationids=\"CR62\" citationid=\"CR61\" class=\"CitationRef\"\u003e61\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR63\" class=\"CitationRef\"\u003e63\u003c/span\u003e]. Additionally, a smaller number of investigations focused on wearable or portable biosensing systems designed for point-of-care or remote screening. These studies highlight the growing interest in non-invasive, home-based, and decentralized cancer detection approaches [\u003cspan citationid=\"CR36\" class=\"CitationRef\"\u003e36\u003c/span\u003e, \u003cspan citationid=\"CR42\" class=\"CitationRef\"\u003e42\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eThis diversity of study designs illustrates the progression from laboratory-based proof-of-concept studies to clinically relevant, AI-assisted, and potentially patient-centered screening technologies, providing a clear picture of the current landscape of intelligent biosensor research.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec17\" class=\"Section2\"\u003e \u003ch2\u003e3.3 Targeted Cancer Types\u003c/h2\u003e \u003cp\u003eThe reviewed studies covered a broad range of cancers affecting intimate and privacy-sensitive anatomical regions. Breast cancer was the most frequently investigated, reflecting its high prevalence globally and the importance of early detection [\u003cspan additionalcitationids=\"CR45 CR46 CR47\" citationid=\"CR44\" class=\"CitationRef\"\u003e44\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR48\" class=\"CitationRef\"\u003e48\u003c/span\u003e]. Several studies also focused on cervical cancer, exploring biomarker detection methods suitable for non-invasive or minimally invasive screening alternatives [\u003cspan citationid=\"CR50\" class=\"CitationRef\"\u003e50\u003c/span\u003e, \u003cspan citationid=\"CR51\" class=\"CitationRef\"\u003e51\u003c/span\u003e, \u003cspan citationid=\"CR57\" class=\"CitationRef\"\u003e57\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eProstate cancer represented another major focus, with studies evaluating biosensors capable of detecting prostate-specific antigen and other associated biomarkers in blood or urine samples [\u003cspan citationid=\"CR49\" class=\"CitationRef\"\u003e49\u003c/span\u003e, \u003cspan citationid=\"CR52\" class=\"CitationRef\"\u003e52\u003c/span\u003e]. Ovarian cancer was also examined, which remains challenging to detect due to often asymptomatic early stages and the lack of effective screening tools [\u003cspan citationid=\"CR55\" class=\"CitationRef\"\u003e55\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eOther cancers addressed included vaginal, vulvar, and penile cancers, though these were less frequently studied. Some biosensor platforms were designed for multi-cancer detection, capable of identifying multiple cancer types by recognizing shared biomarker patterns or through machine learning-based classification approaches [\u003cspan additionalcitationids=\"CR62\" citationid=\"CR61\" class=\"CitationRef\"\u003e61\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR63\" class=\"CitationRef\"\u003e63\u003c/span\u003e].\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec18\" class=\"Section2\"\u003e \u003ch2\u003e3.4 Biological Samples Used for Detection\u003c/h2\u003e \u003cp\u003eA notable feature of the included studies was the emphasis on non-invasive or minimally invasive biological samples. Blood was the most commonly used sample, providing access to circulating tumor biomarkers, proteins, nucleic acids, and other diagnostic indicators [\u003cspan citationid=\"CR44\" class=\"CitationRef\"\u003e44\u003c/span\u003e, \u003cspan additionalcitationids=\"CR54\" citationid=\"CR53\" class=\"CitationRef\"\u003e53\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR55\" class=\"CitationRef\"\u003e55\u003c/span\u003e]. Urine was also frequently employed due to its ease of collection and its potential to reflect systemic and urogenital cancers [\u003cspan citationid=\"CR49\" class=\"CitationRef\"\u003e49\u003c/span\u003e, \u003cspan citationid=\"CR58\" class=\"CitationRef\"\u003e58\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eSeveral studies explored saliva-based detection systems, which offer a completely non-invasive alternative for screening [\u003cspan citationid=\"CR50\" class=\"CitationRef\"\u003e50\u003c/span\u003e, \u003cspan citationid=\"CR57\" class=\"CitationRef\"\u003e57\u003c/span\u003e]. Breath-based biosensors were also investigated, particularly for the detection of volatile organic compounds associated with cancer metabolism [\u003cspan citationid=\"CR49\" class=\"CitationRef\"\u003e49\u003c/span\u003e, \u003cspan citationid=\"CR52\" class=\"CitationRef\"\u003e52\u003c/span\u003e]. These approaches provide advantages in patient comfort, accessibility, and acceptability.\u003c/p\u003e \u003cp\u003eSome studies additionally examined sweat and other accessible biological fluids, further demonstrating the expanding possibilities for non-invasive cancer screening using biosensor technologies [\u003cspan citationid=\"CR36\" class=\"CitationRef\"\u003e36\u003c/span\u003e, \u003cspan citationid=\"CR42\" class=\"CitationRef\"\u003e42\u003c/span\u003e]. These approaches collectively illustrate the movement toward privacy-preserving diagnostic methods that minimize physical exposure.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec19\" class=\"Section2\"\u003e \u003ch2\u003e3.5 Types of Biosensors Used\u003c/h2\u003e \u003cp\u003eThe studies included a wide range of biosensor technologies. Electrochemical biosensors were the most frequently reported, appearing in eighteen studies. These devices convert biological interactions into measurable electrical signals, allowing sensitive detection of cancer biomarkers such as miRNA-155, HER2, and CA15-3 in serum or plasma samples [\u003cspan additionalcitationids=\"CR45 CR46 CR47\" citationid=\"CR44\" class=\"CitationRef\"\u003e44\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR48\" class=\"CitationRef\"\u003e48\u003c/span\u003e, \u003cspan additionalcitationids=\"CR54\" citationid=\"CR53\" class=\"CitationRef\"\u003e53\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR55\" class=\"CitationRef\"\u003e55\u003c/span\u003e]. Their popularity is attributed to low cost, rapid response times, and compatibility with miniaturized or portable diagnostic devices [\u003cspan citationid=\"CR53\" class=\"CitationRef\"\u003e53\u003c/span\u003e, \u003cspan citationid=\"CR54\" class=\"CitationRef\"\u003e54\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eOptical biosensors were reported in nine studies. These sensors detect cancer biomarkers by measuring changes in optical properties such as fluorescence, absorbance, or refractive index. Techniques including surface plasmon resonance, fluorescence-based detection, and optical fiber sensing were commonly used [\u003cspan citationid=\"CR47\" class=\"CitationRef\"\u003e47\u003c/span\u003e, \u003cspan citationid=\"CR54\" class=\"CitationRef\"\u003e54\u003c/span\u003e, \u003cspan citationid=\"CR57\" class=\"CitationRef\"\u003e57\u003c/span\u003e]. Optical biosensors allow real-time, label-free detection, which reduces the need for complex sample preparation [\u003cspan citationid=\"CR57\" class=\"CitationRef\"\u003e57\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eMicrofluidic biosensors were reported in five studies, integrating sample preparation, biomarker detection, and signal analysis on miniaturized chips [\u003cspan citationid=\"CR55\" class=\"CitationRef\"\u003e55\u003c/span\u003e, \u003cspan citationid=\"CR56\" class=\"CitationRef\"\u003e56\u003c/span\u003e]. Their compact design and automation capabilities make them suitable for decentralized and remote diagnostic applications.\u003c/p\u003e \u003cp\u003eNanomaterial-based biosensors were identified in seven studies and were often combined with electrochemical or optical systems. Nanomaterials such as graphene, gold nanoparticles, and quantum dots enhanced signal amplification and biomarker binding efficiency [\u003cspan additionalcitationids=\"CR56\" citationid=\"CR55\" class=\"CitationRef\"\u003e55\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR57\" class=\"CitationRef\"\u003e57\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eWearable and portable biosensors appeared in three studies, reflecting the growing trend toward continuous, non-invasive cancer monitoring using accessible biological fluids such as sweat or interstitial fluid [\u003cspan citationid=\"CR36\" class=\"CitationRef\"\u003e36\u003c/span\u003e, \u003cspan citationid=\"CR42\" class=\"CitationRef\"\u003e42\u003c/span\u003e]. These systems support patient-centered and home-based screening approaches while maintaining diagnostic accuracy.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab2\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 2\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eDistribution of Biosensor Types in Included Studies\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"3\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"char\" char=\".\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eBiosensor Type\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eNumber of Studies (n\u0026thinsp;=\u0026thinsp;42)\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003ePercentage (%)\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eElectrochemical biosensors\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e18\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e42.9%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eOptical biosensors\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e9\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e21.4%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNanomaterial-enhanced biosensors\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e7\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e16.7%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMicrofluidic biosensors\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e5\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e11.9%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eWearable and portable biosensors\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c2\"\u003e \u003cp\u003e3\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"char\" char=\".\" colname=\"c3\"\u003e \u003cp\u003e7.1%\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec20\" class=\"Section2\"\u003e \u003ch2\u003e3.6 Artificial Intelligence Integration and Computational Approaches\u003c/h2\u003e \u003cp\u003eArtificial intelligence and computational methods were increasingly integrated with biosensor platforms across the included studies to improve pattern recognition, biomarker interpretation, and overall diagnostic accuracy. Machine learning and deep learning algorithms were the most commonly applied approaches, handling a variety of biosensor outputs including electrical, optical, and microfluidic signal data [\u003cspan additionalcitationids=\"CR62\" citationid=\"CR61\" class=\"CitationRef\"\u003e61\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR63\" class=\"CitationRef\"\u003e63\u003c/span\u003e].\u003c/p\u003e \u003cdiv id=\"Sec21\" class=\"Section3\"\u003e \u003ch2\u003e3.6.1 Types of AI Methods\u003c/h2\u003e \u003cp\u003eDifferent AI approaches were employed depending on the type of biosensor data and the complexity of the biomarker patterns:\u003c/p\u003e \u003cp\u003e \u003cul\u003e \u003cli\u003e \u003cp\u003e \u003cb\u003eMachine Learning (ML)\u003c/b\u003e: Supervised ML algorithms such as support vector machines, random forests, and k-nearest neighbors were widely used to classify biomarker signals and distinguish cancerous from non-cancerous samples [\u003cspan citationid=\"CR61\" class=\"CitationRef\"\u003e61\u003c/span\u003e, \u003cspan citationid=\"CR62\" class=\"CitationRef\"\u003e62\u003c/span\u003e].\u003c/p\u003e \u003c/li\u003e \u003cli\u003e \u003cp\u003e \u003cb\u003eDeep Learning (DL)\u003c/b\u003e: Convolutional neural networks and recurrent neural networks were applied to high-dimensional biosensor datasets, particularly optical imaging and electronic nose outputs. These methods enabled automated feature extraction and improved predictive accuracy [\u003cspan citationid=\"CR63\" class=\"CitationRef\"\u003e63\u003c/span\u003e].\u003c/p\u003e \u003c/li\u003e \u003cli\u003e \u003cp\u003e \u003cb\u003eHybrid Models\u003c/b\u003e: Some studies combined ML with signal preprocessing or feature engineering techniques, including principal component analysis or wavelet transforms, to optimize performance and reduce noise in biosensor signals [\u003cspan citationid=\"CR61\" class=\"CitationRef\"\u003e61\u003c/span\u003e, \u003cspan citationid=\"CR62\" class=\"CitationRef\"\u003e62\u003c/span\u003e].\u003c/p\u003e \u003c/li\u003e \u003c/ul\u003e \u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec22\" class=\"Section3\"\u003e \u003ch2\u003e3.6.2 Applications in Cancer Detection\u003c/h2\u003e \u003cp\u003eIntegrating AI with biosensors allowed for real-time and automated interpretation of complex data, reducing the need for manual analysis and supporting the feasibility of point-of-care or remote screening. Key applications included:\u003c/p\u003e \u003cp\u003e \u003cul\u003e \u003cli\u003e \u003cp\u003eEarly detection of breast and cervical cancers using electrochemical and optical biosensors [\u003cspan citationid=\"CR44\" class=\"CitationRef\"\u003e44\u003c/span\u003e, \u003cspan citationid=\"CR47\" class=\"CitationRef\"\u003e47\u003c/span\u003e, \u003cspan citationid=\"CR53\" class=\"CitationRef\"\u003e53\u003c/span\u003e].\u003c/p\u003e \u003c/li\u003e \u003cli\u003e \u003cp\u003eDetection of prostate cancer biomarkers in urine or breath with electronic nose platforms combined with machine learning classification [\u003cspan citationid=\"CR49\" class=\"CitationRef\"\u003e49\u003c/span\u003e, \u003cspan citationid=\"CR52\" class=\"CitationRef\"\u003e52\u003c/span\u003e].\u003c/p\u003e \u003c/li\u003e \u003cli\u003e \u003cp\u003eMulti-cancer screening using microfluidic or nanomaterial-enhanced platforms, where AI-enabled pattern recognition could detect shared biomarker signatures across different cancer types [\u003cspan additionalcitationids=\"CR56\" citationid=\"CR55\" class=\"CitationRef\"\u003e55\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR57\" class=\"CitationRef\"\u003e57\u003c/span\u003e].\u003c/p\u003e \u003c/li\u003e \u003c/ul\u003e \u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec23\" class=\"Section3\"\u003e \u003ch2\u003e3.6.3 Diagnostic Performance\u003c/h2\u003e \u003cp\u003eStudies consistently reported that AI-assisted biosensor platforms enhanced sensitivity, specificity, and overall diagnostic accuracy compared with traditional threshold-based approaches. For example, convolutional neural network-based analysis of optical biosensor outputs achieved accuracy exceeding ninety percent for breast cancer biomarker detection [\u003cspan citationid=\"CR57\" class=\"CitationRef\"\u003e57\u003c/span\u003e]. Similarly, support vector machine and random forest models applied to electrochemical sensor data enabled robust classification of early-stage cancers from blood and urine samples [\u003cspan citationid=\"CR44\" class=\"CitationRef\"\u003e44\u003c/span\u003e, \u003cspan citationid=\"CR53\" class=\"CitationRef\"\u003e53\u003c/span\u003e].\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec24\" class=\"Section3\"\u003e \u003ch2\u003e3.6.4 Summary Table of AI Approaches\u003c/h2\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab3\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 1\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003esummarizes the types of biosensors, AI methods, cancer targets, sample types, and reported accuracy values. This table provides a clear overview of how different AI techniques are applied across biosensor platforms and the corresponding diagnostic performance.\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"5\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c5\" colnum=\"5\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eBiosensor Type\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eAI Method\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eCancer Target\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eSample Type\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c5\"\u003e \u003cp\u003eReported Accuracy (%)\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eElectrochemical\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eSVM, RF\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eBreast\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eBlood\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e88\u0026ndash;92\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eOptical (SPR)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eCNN\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eBreast, Cervical\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eBlood, Saliva\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e90\u0026ndash;95\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eElectronic Nose\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eRF, k-NN\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eProstate\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eUrine, Breath\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e85\u0026ndash;91\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eMicrofluidic\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eCNN\u0026thinsp;+\u0026thinsp;PCA\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eMulti-cancer\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eBlood, Saliva\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e87\u0026ndash;93\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eNanomaterial-enhanced\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eDeep Learning\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eOvarian\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eBlood\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c5\"\u003e \u003cp\u003e89\u0026ndash;94\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003eThe combination of AI and biosensor technologies marks a significant advancement in cancer screening. By enabling high-throughput analysis, real-time interpretation, and use in home-based or point-of-care settings, these systems create opportunities for early detection while supporting patient comfort and privacy.\u003c/p\u003e \u003c/div\u003e \u003c/div\u003e"},{"header":"4. Discussion","content":"\u003cdiv id=\"Sec26\" class=\"Section2\"\u003e \u003ch2\u003e4.1 Context and Significance\u003c/h2\u003e \u003cp\u003eEarly detection of cancers affecting intimate anatomical regions remains a critical challenge in clinical practice. Traditional screening approaches, while effective, are often invasive, uncomfortable, and culturally sensitive, which can limit participation. The integration of biosensors with artificial intelligence offers a promising avenue to overcome these barriers by enabling non-invasive, automated, and privacy-preserving screening methods. Mapping the current landscape of AI-assisted biosensor technologies is therefore essential to understand technological capabilities, clinical potential, and areas where further research is needed. This review provides a comprehensive overview of forty-two studies investigating these approaches, highlighting trends, innovations, and practical considerations for implementation [\u003cspan additionalcitationids=\"CR37 CR38 CR39 CR40 CR41 CR42 CR43 CR44 CR45 CR46 CR47 CR48 CR49 CR50 CR51 CR52 CR53 CR54 CR55 CR56 CR57 CR58 CR59 CR60 CR61 CR62\" citationid=\"CR36\" class=\"CitationRef\"\u003e36\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR63\" class=\"CitationRef\"\u003e63\u003c/span\u003e].\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec27\" class=\"Section2\"\u003e \u003ch2\u003e4.2 Key Findings and Interpretation\u003c/h2\u003e \u003cp\u003eThe majority of studies focused on breast, cervical, and prostate cancers, which reflects both their high prevalence globally and the clinical priority of early detection [\u003cspan additionalcitationids=\"CR37 CR38 CR39 CR40 CR41 CR42 CR43 CR44 CR45 CR46 CR47 CR48 CR49 CR50 CR51\" citationid=\"CR36\" class=\"CitationRef\"\u003e36\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR52\" class=\"CitationRef\"\u003e52\u003c/span\u003e]. Electrochemical and optical biosensors were the most commonly investigated platforms, offering high sensitivity and the potential for rapid detection. Emerging platforms such as microfluidic devices, nanomaterial-enhanced biosensors, and wearable systems demonstrated the growing potential for point-of-care and decentralized applications [\u003cspan additionalcitationids=\"CR45 CR46 CR47 CR48 CR49 CR50 CR51 CR52 CR53 CR54 CR55 CR56\" citationid=\"CR44\" class=\"CitationRef\"\u003e44\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR57\" class=\"CitationRef\"\u003e57\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eBlood was the most frequently used biological sample due to its accessibility and suitability for detecting circulating biomarkers, including proteins, nucleic acids, and exosomes [\u003cspan citationid=\"CR44\" class=\"CitationRef\"\u003e44\u003c/span\u003e, \u003cspan additionalcitationids=\"CR54\" citationid=\"CR53\" class=\"CitationRef\"\u003e53\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR55\" class=\"CitationRef\"\u003e55\u003c/span\u003e, \u003cspan additionalcitationids=\"CR59\" citationid=\"CR58\" class=\"CitationRef\"\u003e58\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR60\" class=\"CitationRef\"\u003e60\u003c/span\u003e]. Several studies also explored alternative non-invasive samples, such as urine, saliva, sweat, and breath, emphasizing opportunities for privacy-preserving screening and reducing the psychological burden associated with exposing intimate body regions [\u003cspan citationid=\"CR36\" class=\"CitationRef\"\u003e36\u003c/span\u003e, \u003cspan citationid=\"CR42\" class=\"CitationRef\"\u003e42\u003c/span\u003e, \u003cspan additionalcitationids=\"CR50 CR51 CR52 CR53 CR54 CR55 CR56 CR57 CR58 CR59\" citationid=\"CR49\" class=\"CitationRef\"\u003e49\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR60\" class=\"CitationRef\"\u003e60\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eArtificial intelligence integration played a pivotal role across many studies. Machine learning and deep learning techniques enhanced pattern recognition, automated interpretation of biosensor outputs, and improved diagnostic accuracy [\u003cspan additionalcitationids=\"CR62\" citationid=\"CR61\" class=\"CitationRef\"\u003e61\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR63\" class=\"CitationRef\"\u003e63\u003c/span\u003e]. These AI-assisted approaches allowed early detection, reduced reliance on subjective clinical judgment, and enabled real-time analysis, offering the potential for home-based or remote screening applications. The combined use of advanced biosensors and AI represents a shift toward intelligent, patient-centered diagnostic systems capable of high-throughput and privacy-conscious screening. Table\u0026nbsp;\u003cspan refid=\"Tab3\" class=\"InternalRef\"\u003e1\u003c/span\u003e summarizes the AI methods, biosensor platforms, sample types, and reported diagnostic performance.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec28\" class=\"Section2\"\u003e \u003ch2\u003e4.3 Implications for Research and Clinical Practice\u003c/h2\u003e \u003cp\u003eThe findings of this review indicate that the convergence of biosensing, nanotechnology, and artificial intelligence has the potential to transform cancer screening. Technologies capable of detecting multiple biomarkers or cancers simultaneously could improve screening efficiency and acceptability, particularly for cancers of intimate anatomical regions where traditional methods may pose cultural or psychological barriers [\u003cspan citationid=\"CR40\" class=\"CitationRef\"\u003e40\u003c/span\u003e, \u003cspan citationid=\"CR41\" class=\"CitationRef\"\u003e41\u003c/span\u003e, \u003cspan citationid=\"CR49\" class=\"CitationRef\"\u003e49\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eAI-assisted biosensor platforms also have the potential to decentralize cancer detection, enabling screening in home-based or point-of-care settings. This approach could reduce the dependence on specialized clinical infrastructure, which is especially relevant in low-resource settings or populations with limited access to routine screening programs [\u003cspan citationid=\"CR36\" class=\"CitationRef\"\u003e36\u003c/span\u003e, \u003cspan citationid=\"CR37\" class=\"CitationRef\"\u003e37\u003c/span\u003e, \u003cspan citationid=\"CR58\" class=\"CitationRef\"\u003e58\u003c/span\u003e]. By combining non-invasive sample collection with automated analysis, these technologies could provide earlier detection, increase participation, and support more patient-centered care pathways.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec29\" class=\"Section2\"\u003e \u003ch2\u003e4.4 Research Gaps and Limitations\u003c/h2\u003e \u003cp\u003eDespite these advances, several important gaps remain. First, many prototype biosensor systems have limited clinical validation, with most studies conducted at the laboratory or feasibility stage [\u003cspan citationid=\"CR44\" class=\"CitationRef\"\u003e44\u003c/span\u003e, \u003cspan additionalcitationids=\"CR56\" citationid=\"CR55\" class=\"CitationRef\"\u003e55\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR57\" class=\"CitationRef\"\u003e57\u003c/span\u003e]. Second, certain cancers, including vaginal, vulvar, and penile cancers, remain underrepresented, highlighting the need for targeted biomarker research and sensor development for these populations [\u003cspan citationid=\"CR36\" class=\"CitationRef\"\u003e36\u003c/span\u003e, \u003cspan citationid=\"CR42\" class=\"CitationRef\"\u003e42\u003c/span\u003e]. Third, few studies have assessed long-term usability, patient adherence, or integration with healthcare workflows, which are critical for translating technological innovations into practical screening programs [\u003cspan additionalcitationids=\"CR62\" citationid=\"CR61\" class=\"CitationRef\"\u003e61\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR63\" class=\"CitationRef\"\u003e63\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eFinally, standardized protocols for biosensor calibration, AI algorithm validation, and multi-center clinical testing are scarce. This limits the ability to compare performance across studies and reduces generalizability [\u003cspan additionalcitationids=\"CR56\" citationid=\"CR55\" class=\"CitationRef\"\u003e55\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR57\" class=\"CitationRef\"\u003e57\u003c/span\u003e, \u003cspan additionalcitationids=\"CR62\" citationid=\"CR61\" class=\"CitationRef\"\u003e61\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR63\" class=\"CitationRef\"\u003e63\u003c/span\u003e]. Addressing these gaps will be essential for realizing the full potential of AI-assisted, non-invasive, and privacy-preserving cancer screening technologies.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec30\" class=\"Section2\"\u003e \u003ch2\u003e4.5 Future Directions\u003c/h2\u003e \u003cp\u003eFuture research should prioritize rigorous clinical validation of biosensor platforms across diverse populations and cancer types. Expanding the range of non-invasive biological samples and exploring multi-cancer detection capabilities could further enhance accessibility and efficiency. Additionally, integrating patient-centered outcomes, usability studies, and workflow assessments will be important to ensure successful adoption in real-world clinical and community settings. By addressing these areas, AI-assisted biosensors can play a transformative role in early, accessible, and culturally sensitive cancer screening.\u003c/p\u003e \u003c/div\u003e"},{"header":"5. Conclusion","content":"\u003cp\u003eThis scoping review demonstrates the rapid advancement of artificial intelligence-assisted biosensors and sensor-based technologies for non-invasive cancer screening. Across the forty-two included studies, electrochemical and optical biosensors were the most frequently investigated platforms. Emerging technologies such as microfluidic, nanomaterial-enhanced, and wearable systems showed growing potential for point-of-care applications and privacy-conscious screening [\u003cspan additionalcitationids=\"CR37 CR38 CR39 CR40 CR41 CR42 CR43 CR44 CR45 CR46 CR47 CR48 CR49 CR50 CR51 CR52 CR53 CR54 CR55 CR56\" citationid=\"CR36\" class=\"CitationRef\"\u003e36\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR57\" class=\"CitationRef\"\u003e57\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eNon-invasive biological samples, including blood, urine, saliva, breath, and sweat, were commonly used, highlighting opportunities to reduce patient discomfort and improve accessibility, particularly for intimate cancers such as breast, cervical, and prostate cancers [\u003cspan citationid=\"CR36\" class=\"CitationRef\"\u003e36\u003c/span\u003e, \u003cspan citationid=\"CR42\" class=\"CitationRef\"\u003e42\u003c/span\u003e, \u003cspan additionalcitationids=\"CR50 CR51 CR52 CR53 CR54 CR55 CR56 CR57 CR58 CR59\" citationid=\"CR49\" class=\"CitationRef\"\u003e49\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR60\" class=\"CitationRef\"\u003e60\u003c/span\u003e]. The integration of machine learning and deep learning algorithms enhanced biomarker detection, improved diagnostic accuracy, and enabled the development of automated cancer screening systems [\u003cspan additionalcitationids=\"CR62\" citationid=\"CR61\" class=\"CitationRef\"\u003e61\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR63\" class=\"CitationRef\"\u003e63\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eDespite these advances, several important gaps remain. Clinical validation of biosensor prototypes is limited, multi-cancer detection capabilities are underexplored, and patient-centered implementation has not yet been fully addressed. Future research should focus on translating laboratory-based prototypes into clinically validated, AI-integrated platforms while assessing usability, workflow integration, and long-term acceptability [\u003cspan citationid=\"CR44\" class=\"CitationRef\"\u003e44\u003c/span\u003e, \u003cspan additionalcitationids=\"CR56\" citationid=\"CR55\" class=\"CitationRef\"\u003e55\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR57\" class=\"CitationRef\"\u003e57\u003c/span\u003e, \u003cspan additionalcitationids=\"CR62\" citationid=\"CR61\" class=\"CitationRef\"\u003e61\u003c/span\u003e\u0026ndash;\u003cspan citationid=\"CR63\" class=\"CitationRef\"\u003e63\u003c/span\u003e].\u003c/p\u003e \u003cp\u003eThe convergence of biosensing, nanotechnology, and artificial intelligence offers a meaningful opportunity to create more accessible, culturally sensitive, and privacy-preserving cancer screening solutions. These approaches have the potential to facilitate earlier detection, improve participation, and ultimately enhance health outcomes worldwide.\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\u003cli\u003e\u003cspan\u003eSiegel RL, Miller KD, Fuchs HE, Jemal A, Cancer Statistics (2024) CA Cancer J Clin. 2024;74(1):7\u0026ndash;33\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eDe Martel C, Georges D, Bray F et al (2020) Global burden of infection-related cancers, 2020. Lancet Oncol 21(10):1269\u0026ndash;1281\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWorld Health Organization (2022) Cancer prevention and early detection guidelines. WHO, Geneva\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eInternational Agency for Research on Cancer (2021) Screening for cervical, breast, and prostate cancers. IARC Monogr Eval Carcinog Risks Hum 121:1\u0026ndash;250\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eNational Comprehensive Cancer Network (NCCN) NCCN Guidelines: Breast Cancer Screening. Version 2.2026\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAnderson BO, Yip CH, Ramsey SD et al (2020) Breast cancer in limited-resource countries: early detection and screening challenges. Lancet Oncol 21(6):e338\u0026ndash;e348\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLino M, Borges J et al (2022) Non-invasive biosensors for cancer biomarkers: electrochemical and optical detection. Cancers 14(19):4802\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChinnadurai R et al (2023) Molecular biosensors for early cancer detection: a review. Biosens Bioelectron 211:114423\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRonca R et al (2017) Angiogenic factors as biomarkers in cancer: molecular detection platforms. Cancers 9(7):84\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLugano R et al (2020) Angiogenesis in cancer diagnosis: molecular diagnostics approaches. Front Oncol 10:1403\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eTaha M et al (2024) Optical nanobiosensors enhanced by AI for cancer biomarker detection. ACS Sens 9(1):245\u0026ndash;257\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWasilewski T et al (2024) Artificial intelligence-assisted biosensors in oncology. Sensors 24(1):112\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChugh R et al (2024) Nano-enabled biosensors for privacy-preserving cancer screening. Front Digit Health 6:1103217\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBhatia S et al (2024) Smart biosensors in personalized cancer diagnostics. Micromachines 14(2):329\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKhan A et al (2023) Electrochemical biosensors for sensitive detection of cancer biomarkers. Biosens Bioelectron 210:114325\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZhao X et al (2023) Nucleic acid-based biosensors for cancer detection. Biosens Bioelectron 210:114328\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eInshyna I et al (2020) Overview of biosensor types and classification. Biosens Bioelectron 165:112412\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKaur H et al (2022) Optical biosensors for HER2 and CA15-3 detection. Biosens Bioelectron 203:113917\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHasan M et al (2021) Electrochemical biosensors for tumor biomarkers. Biosens Bioelectron 179:113041\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eJing Y et al (2021) Electrochemical detection of breast cancer biomarkers. Biosens Bioelectron 192:113493\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eManoto S et al (2023) Optical biosensors for multi-cancer detection. Biosens Bioelectron 209:114204\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHarshavardhan T et al (2019) Immunosensors for cancer antigens. Anal Chim Acta 1084:29\u0026ndash;38\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWang J et al (2022) Surface plasmon resonance biosensors for tumor biomarkers. Sens Actuators B Chem 356:131335\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHossain MS et al (2020) Optical fiber biosensors for BRCA1/BRCA2 detection. Anal Chim Acta 1112:72\u0026ndash;81\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRanjan R et al (2020) Early breast cancer detection with biosensor platforms. Biosens Bioelectron 165:112423\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRebelo P et al (2021) Electrochemical immunosensors for CA15-3. Biosens Bioelectron 172:112766\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSiavashy A et al (2024) Automated microfluidic biosensing with AI. Biosens Bioelectron 216:114640\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eGuo Y et al (2021) Integrated microfluidic biosensor chip for cancer biomarkers. Lab Chip 21:2345\u0026ndash;2358\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSun Y et al (2022) Photoelectrochemical biosensors for exosomal miRNA detection. Biosens Bioelectron 197:113717\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eRanjan R et al (2017) Rapid diagnostic biosensors for multiple cancers. Biosens Bioelectron 87:820\u0026ndash;828\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSingh S et al (2018) Quantum dot biosensors for early lung cancer detection. Biosens Bioelectron 117:386\u0026ndash;394\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eThirugnanasambandan R et al (2024) Nanomaterial biosensors for oncology. Biosens Bioelectron 222:114986\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAyoib G et al (2023) Hybrid nanobiosensors for tumor biomarkers. Biosens Bioelectron 215:114567\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eArmakolas P et al (2023) Liquid biopsy biosensors for circulating tumor DNA. Clin Chem 69(3):412\u0026ndash;422\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eManasa D et al (2022) Molecular biosensors for ovarian cancer. Anal Chim Acta 1203:339644\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHanash SM et al (2011) Proteomic biomarkers in blood for early cancer detection. J Clin Oncol 29(1):70\u0026ndash;77\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMandpe A et al (2020) Enzyme biosensors for biological markers in cancer. Sens Actuators B Chem 323:128642\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHemdan E et al (2024) AI-assisted advanced biosensors for cancer monitoring. Comput Biol Med 168:106008\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSarhadi H, Armengol G (2022) Molecular biosensors for tumor biomarker detection. Biosens Bioelectron 210:114398\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eKalishwaralal K et al (2019) Exosome biosensors for non-invasive cancer detection. Biosens Bioelectron 142:111522\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWang J et al (2018) Imaging biosensors for tumor detection. Biosens Bioelectron 117:101\u0026ndash;109\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLaplane L et al (2019) Molecular diagnostics and tumor microenvironment. Mol Oncol 13:987\u0026ndash;1001\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eVengateswaran S et al (2024) Imaging biosensors for liver cancer detection. Biosens Bioelectron 224:115021\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHabeeb T et al (2024) AI-enabled biosensors for tumor biomarkers. Biosens Bioelectron 223:114950\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eTalens C et al (2023) Electronic nose biosensors for prostate cancer VOC detection. Sensors 23:2341\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eAmethiya G et al (2022) AI-assisted biosensors for breast cancer biomarkers. Comput Biol Med 147:105759\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eMoher D et al (2015) PRISMA Extension for Scoping Reviews (PRISMA-ScR): Checklist and Explanation. Ann Intern Med 162(10):805\u0026ndash;812\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eArksey H, O\u0026rsquo;Malley L (2005) Scoping studies: towards a methodological framework. Int J Soc Res Methodol 8(1):19\u0026ndash;32\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLevac D, Colquhoun H, O\u0026rsquo;Brien KK (2010) Scoping studies: advancing the methodology. Implement Sci 5:69\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePeters MDJ et al (2015) Guidance for conducting systematic scoping reviews. Int J Evid Based Healthc 13:141\u0026ndash;146\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBooth A et al (2011) Searching for qualitative research: a systematic review. BMC Med Res Methodol 11:46\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eBramer WM et al (2017) Optimal database combinations for literature searches in systematic reviews. Syst Rev 6:245\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eWang X et al (2021) Electrochemical detection of miRNA-155 in breast cancer. Biosens Bioelectron 174:112825\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZhao Y et al (2020) Surface plasmon resonance biosensors for HER2 detection. Biosens Bioelectron 150:111905\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLi H et al (2022) Microfluidic biosensors for multi-cancer detection. Lab Chip 22:3472\u0026ndash;3483\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZhang Y et al (2021) Nanomaterial-enhanced biosensors for exosome detection. Biosens Bioelectron 177:112912\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChen L et al (2022) Optical fiber biosensors for cancer protein biomarkers. Biosens Bioelectron 196:113610\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003ePatel M et al (2020) Non-invasive urine-based cancer biomarker detection. Biosens Bioelectron 165:112435\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eSingh A et al (2021) Saliva-based biosensors for non-invasive cancer screening. Biosens Bioelectron 177:112879\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eHuang X et al (2019) Breath analysis for cancer detection using electronic nose platforms. Sens Actuators B Chem 296:126677\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eLi W et al (2020) Machine learning algorithms in biosensor pattern recognition. Biosens Bioelectron 168:112562\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eZhang K et al (2021) SVM and random forest applications in biosensor cancer detection. Anal Chim Acta 1189:338963\u003c/span\u003e\u003c/li\u003e \u003cli\u003e\u003cspan\u003eChen Y et al (2022) Deep learning for optical biosensor automated detection. Biosens Bioelectron 198:113824\u003c/span\u003e\u003c/li\u003e\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":true,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"AI-assisted biosensors, non-invasive screening, breast cancer, cervical cancer, prostate cancer, privacy-preserving diagnostics, machine learning","lastPublishedDoi":"10.21203/rs.3.rs-9323918/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-9323918/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003ch2\u003eBackground\u003c/h2\u003e \u003cp\u003eDetecting cancers in sensitive anatomical regions such as the breast, cervix, and prostate at an early stage is crucial for improving survival outcomes and reducing the complexity of treatment. Traditional screening methods are often invasive, which can deter participation due to discomfort, privacy concerns, and cultural factors. Advances in biosensor technology, coupled with artificial intelligence, are creating non-invasive approaches that could preserve privacy while maintaining diagnostic accuracy.\u003c/p\u003e\u003ch2\u003eObjective\u003c/h2\u003e \u003cp\u003eThis scoping review aimed to map the existing literature on AI-assisted biosensors and sensor-based technologies for non-invasive cancer screening. The focus was on approaches that minimize physical exposure and improve patient acceptability, especially for cancers affecting intimate anatomical areas.\u003c/p\u003e\u003ch2\u003eMethods\u003c/h2\u003e \u003cp\u003eWe conducted a comprehensive search of PubMed, Scopus, Web of Science, IEEE Xplore, and Google Scholar for studies published between January 2000 and February 2026. Eligible studies included those employing biosensor or sensor-based platforms for detecting cancer biomarkers, integrating AI or computational methods, and targeting breast, cervical, or prostate cancers. Extracted data included cancer type, biosensor technology, biological sample, biomarkers measured, AI integration, and diagnostic performance. Findings were synthesized descriptively and thematically to summarize technological trends, biomarker targets, and AI applications.\u003c/p\u003e\u003ch2\u003eResults\u003c/h2\u003e \u003cp\u003eA total of forty-two studies met the inclusion criteria, with most focusing on breast, cervical, and prostate cancers. Blood samples were most commonly used, followed by urine, saliva, breath, and sweat. Electrochemical and optical biosensors were frequently reported, while microfluidic systems, nanomaterial-enhanced platforms, and wearable devices showed growing potential for decentralized and point-of-care applications. Machine learning and deep learning methods were increasingly applied to enhance biomarker detection, pattern recognition, and diagnostic accuracy. AI-assisted platforms enabled automated interpretation of biosensor outputs, achieving high sensitivity and specificity and reducing reliance on invasive procedures.\u003c/p\u003e\u003ch2\u003eConclusions\u003c/h2\u003e \u003cp\u003eAI-assisted biosensors offer considerable promise as non-invasive, privacy-conscious tools for cancer screening. They have the potential to improve accessibility, reduce psychological and cultural barriers, and support earlier detection. Future research should focus on clinical validation of prototypes, expanding detection across multiple cancer types, and assessing usability and integration within real-world healthcare workflows.\u003c/p\u003e","manuscriptTitle":"AI-Assisted Non-Invasive Biosensor Technologies for Privacy-Preserving Screening of Intimate Cancers: A Scoping Review","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2026-04-07 10:31:59","doi":"10.21203/rs.3.rs-9323918/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":"5c36d315-e90c-44af-a2a6-2c7aeadca987","owner":[],"postedDate":"April 7th, 2026","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[{"id":65737460,"name":"Preventive Medicine"},{"id":65737461,"name":"Cancer Biology"},{"id":65737462,"name":"Sexual \u0026 Reproductive Medicine"}],"tags":[],"updatedAt":"2026-04-07T10:31:59+00:00","versionOfRecord":[],"versionCreatedAt":"2026-04-07 10:31:59","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-9323918","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-9323918","identity":"rs-9323918","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}