Aug 2026· Translational Medical Engineering· 0 citations
TL;DR
This review aims to examine how AI can help optical sensors overcome major barriers limiting their adoption in clinical settings and to identify the major barriers limiting their adoption in clinical settings.
Abstract
Background/Objectives: The growing demand for precision prevention and personalized medicine has accelerated the need for non/minimally invasive, point-of-care testing (POCT), and continuous monitoring systems. Optical sensors offer significant advantages for such applications, including high sensitivity, rapid response, and excellent immunity to electromagnetic interference. However, their translation into clinical practice is hindered by issues such as low signal-to-noise ratios and complex data structures. Artificial intelligence (AI) can help overcome these limitations by improving weak signal extraction, high-dimensional signal analysis, and multimodal data integration. Accordingly, this review aims to examine how AI can help optical sensors overcome these challenges and to identify the major barriers limiting their adoption in clinical settings. Methods: We first review four key classes of optical hardware: optical fiber sensors, integrated nanophotonic devices, laser/spectral imaging systems, and wearable flexible devices. Building upon these platforms, we further evaluate common data processing methodologies, highlighting their effectiveness in weak-signal amplification, feature extraction, and cross-source data fusion. Results: Across these platforms, data-driven methods have improved signal recovery, noise suppression, and drift compensation and have also enabled the extraction of clinically useful features from high-dimensional data. Multimodal integration may further reduce diagnostic error. Early clinical use has emerged in home monitoring, intraoperative guidance, and POCT. However, translation remains constrained by sample complexity, manufacturing variability, limited long-term stability, and the mismatch between rapid algorithm updates and conventional regulatory pathways. Conclusions: Optical sensing is moving from passive measurement toward more integrated diagnostic workflows. Further progress will depend on closed-loop sensing-computing-intervention systems, edge deployment, adaptive regulation, scalable manufacturing, and improved long-term robustness. Coordinated progress across technology, clinical validation, industry, and regulation will be essential for broader clinical adoption.
ABSTRACT
Conventional medical sensors primarily function as passive transducers and often struggle to maintain accuracy and stability under complex physiological conditions. Their limited capacity for local data processing, adaptive compensation, and real-time interaction also constrains continuous monitoring and individualized clinical decision-making. The convergence of microelectronics, materials science, wireless communication, and artificial intelligence (AI) has therefore accelerated the development of intelligent medical sensors that integrate sensing, processing, communication, and decision-support functions. This review summarizes recent advances and remaining challenges in this field. We examine the technical architectures and core functions of next-generation sensors, including self-compensation, self-calibration, self-diagnosis, and bidirectional data interaction, and compare four major technological platforms: flexible wearable sensors, optical fiber sensors, electrochemical sensors, and functional nucleic acid and molecularly imprinted biosensors. We further discuss signal-transduction, anti-interference, and data-transmission mechanisms; advances in flexible materials, micro/nano-fabrication, multimodal integration, and AI-enabled signal processing; and applications in physiological monitoring, biomarker detection, chronic disease management, wearable therapy, interventional support, and extreme environments. Despite rapid progress, clinical translation remains limited by data security and privacy risks, insufficient standardization and regulatory alignment, long-term stability and biocompatibility concerns, and uneven validation maturity across technologies. Future development should prioritize clinically driven design, staged and technology-specific validation, multimodal and low-power integration, and coordinated regulatory and manufacturing strategies to support reliable, scalable, and patient-centered implementation.
Jirui Wen, Jiang Wu, Yi Yang et al.· Chinese Medical Journal· 0 citations
Analytical tools may revolutionize healthcare by enabling accessible, rapid, and decentralized testing. Wearable (bio)sensors, in particular, provide frequent or continuous patient monitoring through non- to minimally invasive measurements. This approach yields unprecedented amounts of health-related information, leading to more informed clinical decision-making and closer patient follow-up. In this mega-review article, we bring together leading researchers in the field to discuss the state of the art in wearable devices for health monitoring. We begin by providing a broad overview of the field through citation network analysis. We then review the application of chemical (bio)sensors in biofluids (e.g., sweat, saliva, tears, interstitial fluid, and cerebrospinal fluid), highlighting the challenges and advantages associated with each. Subsequently, we discuss the construction of wearable devices and their main formats (e.g., smart contact lenses, textiles, mouthguards, watches/wristbands, and implantable systems). Physical sensors are addressed in a dedicated section focusing on the assessment of heart rate, blood pressure, and body temperature. The role of soft electronics in wearable devices is also examined, as these technologies are essential for enhancing user comfort and sensor reliability, which demands advances in materials science. Furthermore, we present strategies for signal acquisition and transmission, as well as approaches for on-body energy harvesting and device self-powering. The use of artificial intelligence and machine learning is then discussed as a means of enhancing analytical performance and managing the large volumes of data generated by wearable devices. Finally, business, regulatory, and ethical considerations are examined. We expect that this review will provide an overview of sensing and biosensing technologies for health-related applications, identify promising research directions, and inspire future developments.
L. Brazaca, Alvaro Moreno Lozano, Beatriz Mayol et al.· ACS Applied Materials and In...· 1 citation
Biosensors have become important analytical platforms that enable rapid, selective, sensitive and portable analysis for early disease diagnosis, biomarker monitoring and point-of-care diagnostic applications. Their analytical performance depends on the coordinated function of molecular recognition elements, surface chemistry, transduction mechanisms and signal-processing strategies. Nevertheless, the analysis of real biological samples remains challenging because of low target concentrations, matrix effects, interfering species, signal noise, sensor drift and device-to-device variability. Therefore, artificial intelligence and machine learning are gaining increasing importance as data-driven tools for signal preprocessing, calibration, feature extraction, pattern recognition, quantitative prediction and diagnostic decision support. These approaches are particularly valuable for interpreting complex datasets generated by electrochemical, optical, wearable and microfluidic biosensors. This review presents an overview of healthcare-oriented biosensor systems beginning with molecular recognition principles, bioreceptor design, and transduction technologies, and extending to applications in clinical diagnosis and health monitoring. It also examines the roles of supervised, unsupervised and deep learning approaches in biosensor data analysis, while critically discussing model validation, generalizability, interpretability and clinical translation. By linking molecular-level recognition with computational signal interpretation, this review highlights the advantages and limitations of artificial intelligence-integrated biosensors for next-generation point-of-care diagnostics, continuous health monitoring, and personalized healthcare applications.
Özge Altıntaş, Adil Denizli· Electronics· 0 citations
Multimodal sensing strategies—electrical, electrochemical, transistor-based, and optical—integrated with AI-enabled interpretation establish a systems-level framework for continuous, individualized precision diagnosis across metabolites, electrophysiological signals, and molecular biomarkers in diverse biofluids. Advanced manufacturing and heterogeneous integration strategies, spanning printing, photolithography, 3D fabrication, and laser writing, enable skin-conformal platforms that unify sensing, signal transduction, power, and wireless communication into compact, long-term wearable diagnostic systems. Wearable diagnostic platforms demonstrate broad clinical applicability across neurological, cardiovascular, respiratory, ocular, musculoskeletal, oncological, diabetic, and inflammatory conditions; by enabling longitudinal multi-parameter data fusion and personalized physiological baselines, they provide a clinically actionable pathway for early disease detection, risk stratification, and real-time health management. Multimodal sensing strategies—electrical, electrochemical, transistor-based, and optical—integrated with AI-enabled interpretation establish a systems-level framework for continuous, individualized precision diagnosis across metabolites, electrophysiological signals, and molecular biomarkers in diverse biofluids. Advanced manufacturing and heterogeneous integration strategies, spanning printing, photolithography, 3D fabrication, and laser writing, enable skin-conformal platforms that unify sensing, signal transduction, power, and wireless communication into compact, long-term wearable diagnostic systems. Wearable diagnostic platforms demonstrate broad clinical applicability across neurological, cardiovascular, respiratory, ocular, musculoskeletal, oncological, diabetic, and inflammatory conditions; by enabling longitudinal multi-parameter data fusion and personalized physiological baselines, they provide a clinically actionable pathway for early disease detection, risk stratification, and real-time health management. Wearable electronics are rapidly transforming healthcare by enabling continuous, real-time monitoring of physiological and molecular signals directly at the point of need. This shift supports a transition from episodic, generalized care toward precision diagnosis, where individualized, longitudinal data guide early detection, risk stratification, and treatment decisions. Central to this transformation is the convergence of advanced manufacturing and heterogeneous integration strategies, which enable the development of compact, multimodal, and highly conformable diagnostic platforms. In this review, we examine how advances in materials engineering, micro/nanofabrication, and system integration have transformed wearable devices from single-parameter sensors into fully integrated, multimodal diagnostic systems. We outline key architectures and transduction mechanisms and highlight manufacturing approaches such as printing, 3D fabrication, photolithography, and laser writing. We emphasize heterogeneous integration strategies that combine sensing, electronics, power, and communication into skin-conformal platforms for long-term use. These advances enable precision diagnostics through continuous monitoring, multimodal data fusion, and individualized baselines. We also outline key challenges to clinical translation and discuss future directions toward robust, scalable, and clinically actionable systems, providing a strategic outlook for next-generation wearable electronics in precision diagnosis.
Optical fibre sensors (OFS) have advanced substantially in recent years, progressing from predominantly laboratory-based prototypes to promising tools for real-world biomedical applications. Their growing integration into healthcare systems highlights the value of OFS for continuous physiological monitoring, early disease detection, and therapy guidance. Key application domains include the measurement of physical parameters (e.g. pressure, strain, temperature) and biological targets (e.g. proteins, metabolites, and nucleic acids), and chemical analytes (e.g. pH, drugs, gases). Instead of focusing only on sensor design and theoretical concepts, this review highlights the clinical translation of OFS technologies and their readiness for real-world use. The paper also discusses new trends in medical OFS, including personalised and decentralised monitoring and data-driven clinical decision-making. Finally, this review outlines the main challenges to clinical adoption and suggests future directions for the wider use of OFS in biomedical sensing.
Y. Chen, Chenyang He, Stephen P. Morgan et al.· Journal of Optics· 0 citations
Artificial intelligence (AI) enabled wearable devices have revolutionized the healthcare monitoring by offering real-time and continuous monitoring of users' physiological signals used at home. This review analyzed the technological, algorithmic and clinical advancement from 2020 to 2025, detailing the technologies for biosensor design, e-enabled Machine Learning (ML) solutions, edge computing architectures, and privacy-preserving frameworks. Based on the PRISMA-ScR approach, quantitative Neural Networks (NNs), AutoML pipelines, federated learning and secure on-device analytics in a representative fashion were reviewed. Significant innovations in core basic pillars were detected: frontier sensor technologies, including multimodal fusion, and self-powered systems. Resource-efficient embedded AI models customized for constrained environments have further enhanced on-device intelligence, real-time analytics, ethical norms and regulatory paradigms. Nevertheless, such challenges are still very complicated and hard to solve. Signal instability, energy constraints, algorithmic bias and lack of demographic diversity in training data undermine model reliability and generalizability, compromising the safe, fair, and scalable implementation of such AI-driven wearable health monitoring systems in real clinical settings. The lack of validation in real-world scenarios, model explainability and alignment with regulatory frameworks of most have hampered their clinical adoption and broad-scale deployment. Ethical aspects like data sovereignty, fairness, and dynamic consent are still largely to be formed. This work connects biomedical signal capture, on-device AI, clinical translation, and digital ethics to delineate a roadmap for frontier AI wearables. This proposed edge-aware transformer-based models, privacy-preserving analytics, and global multimodal sensing advance intelligent, scalable, and fair AI-driven health monitoring systems.
Known for his clear and elegant writing style, Bertsekas shaped fields from control and optimization to large-scale computation and artificial intelligence.
