This review provides a systematic overview of ML-reinforced optical sensing arrays, with a particular focus on three major modalities: colorimetric, fluorescent, and surface-enhanced Raman scattering (SERS) sensor arrays.
Abstract
Optical sensing arrays have emerged as transformative tools for disease diagnosis, offering low-cost, rapid, and multiplexed fingerprint detection capabilities. However, the high-dimensional and complex data generated by these arrays pose significant challenges for conventional analytical methods. The integration of machine learning (ML) has advanced this field by enabling automated feature extraction, robust pattern recognition, and accurate disease classification. This review provides a systematic overview of ML-reinforced optical sensing arrays, with a particular focus on three major modalities: colorimetric, fluorescent, and surface-enhanced Raman scattering (SERS) sensor arrays. We critically evaluate how ML algorithms—encompassing unsupervised, supervised, and deep learning paradigms—synergistically enhance the diagnostic performance of each sensor modality. Representative applications are highlighted, demonstrating high accuracy in detecting cancers and infectious diseases. Finally, we discuss the pressing challenges related to data standardization, model interpretability, and clinical translation, while outlining future directions toward intelligent, point-of-care, and personalized diagnostic systems.
Carbon quantum dots (CQDs) exhibit rich photophysical behaviors, including excitation-dependent emission, surface-state variability, and multimodal fluorescence pathways, which complicate accurate, signal interpretation in chemical sensing. Recent advances in machine learning (ML) offer powerful solutions for modeling these complexities and enhancing fluorescence-based detection performance. This review provides a comprehensive analysis of ML-driven methodologies for denoising, spectral decomposition, feature extraction, and high-accuracy classification in CQD fluorescence systems. Mathematical foundations of key ML paradigms are outlined to establish a rigorous framework for signal reconstruction and generalization. Evaluations of recent applications demonstrate how ML enables ultra-low-level analyte detection, interpretable photophysical modeling, and real-time intelligent sensing across chemical and biological environments. Emerging trends—including physics-informed learning, generative data augmentation, autonomous closed-loop sensing, and distributed multimodal architectures—are examined as frontiers poised to redefine CQD fluorescence analytics. Collectively, the integration of ML with CQD photophysics represents a transformative pathway toward robust, adaptive, and next-generation chemical sensing platforms.
B. T. Sayed, Maharshi B Shukla, Sumit Sharma et al.· RSC Advances· 0 citations
The growing problem of air pollution and its direct impact on human health have created an urgent need for reliable, intelligent, and machine learning (ML)-enabled gas-sensing technologies. Among various sensing platforms, metal oxide gas sensors (MO-GSs) have emerged as promising candidates owing to their low cost, high sensitivity, and scalability. However, their practical application is limited by poor selectivity, cross-sensitivity, sensor drift, and high operating temperatures. Recent advances in ML have provided effective strategies to overcome these limitations through data-driven optimization of sensing performance. This review summarizes recent progress in ML-assisted MO-GSs, covering sensor array design, feature engineering, and classification algorithms, including support vector machines (SVMs), random forests (RFs), and deep neural networks (DNNs). In addition, key data-processing techniques such as preprocessing, dimensionality reduction, and hybrid learning approaches are critically discussed. The application of ML-enabled MO-GSs in medical diagnostics, environmental monitoring, industrial safety, and food quality assessment is also reviewed. Despite significant progress, challenges including limited dataset availability, sensor drift, and poor model generalization remain. Future research should focus on developing adaptive, energy-efficient, and IoT-enabled smart sensing systems. The integration of machine learning with metal oxide gas sensors represents a significant step toward intelligent, next-generation, high-performance gas-sensing technologies.
Abdul Shakoor, Syed Adil Sardar, Farhan Akhtar et al.· Processes· 0 citations
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
The clinical adoption of liquid biopsy for early cancer detection is often hindered by the need for complex sample preparation and the difficulty of identifying rare malignant cells within a dominant background of normal blood cells. While surface-enhanced Raman spectroscopy (SERS) offers distinct analytical advantages as a label-free, non-invasive tool, its practical implementation faces challenges due to limited training samples in early stage, weak signals and the necessity for expert spectral interpretation, which introduces undesirable operator-dependent variability. To address these challenges, this study proposes an integrated SERS, machine learning (Spectral-ML) framework to automatically extract features, improving diagnostic consistency and efficiency. This study presents a systematic evaluation of three nonlinear ML classifiers, including random forest (RF), extreme gradient boosting (XGB), and support vector machine (SVM), while integrating advanced spectral preprocessing methods such as modified Vancouver Raman algorithm, multiframe non-local means (MNLM) denoising with principal component analysis (PCA) for classification. We validated this framework across two datasets consisting of lung cancer cell lines: Dataset 1 (A549/WBC) and Dataset 2 (H1299/WBC). The results demonstrated that the combination of SVM, PCA, and MNLM achieved the optimal performance, yielding a high accuracy when distinguishing cancer cells from a white blood cell background, effectively simulating a post-erythrocytelysis clinical scenario. PCA-based feature analysis further provided biological interpretability by mapping discriminative bands to specific nucleic acid and protein markers.
Hsien-Ting Chang, I- Tsu Chyuan, Jia-Ling Li et al.· Journal of Micromechanics an...· 0 citations
Microbial communities play a critical role in human health, and their metabolic activities are directly implicated in the pathogenesis and progression of various diseases. Conventional detection methods for microbes and biomarkers, however, are hampered by limitations including poor real-time performance, high invasiveness, low specificity, and limited capacity for multi-parameter parallel detection, which severely restrict their application in clinical and scientific research. In recent years, the deep integration of interdisciplinary fields such as synthetic biology, nanotechnology, optical imaging, and artificial intelligence has catalyzed the rapid development of intelligent detection technologies. These innovations provide novel solutions for achieving highly sensitive, noninvasive, real-time, and multi-modal detection of microbes and disease biomarkers. This review systematically summarizes the breakthroughs in these technologies for microbial visualization and disease biomarker tracking, with a focus on four core strategies: physical information-based sensing (e.g. photoacoustic imaging, acoustic reporter genes), specific probe labeling (fluorescent, isotopic, nanomaterial-based probes), genetically engineered biosensors, and bioluminescence imaging. Collectively, these approaches not only enable real-time in vivo monitoring of microbial dynamics but also hold substantial promise for biomarker detection. Finally, we discuss the pivotal challenges confronting their clinical translation, aiming to provide a valuable reference for advancing precision medicine, personalized health monitoring, and microbiome research.
Shuang Liu, Yanhua Yang, Ye Pan et al.· Critical reviews in microbio...· 0 citations
Ensuring food safety necessitates rapid, non-destructive, and reliable monitoring strategies, among which colorimetric sensor arrays (CSAs), based on analyte-induced color changes, have emerged as cost-effective tools for real-time food quality monitoring. Recent advances in sensing materials, fabrication strategies, and colorimetric mechanisms have expanded the analytical capability of CSAs, particularly through integration with machine learning. Automated feature extraction, pattern recognition, and predictive modeling significantly improve sensitivity, specificity, and classification accuracy, enabling more reliable food freshness assessment. Both traditional algorithms and deep learning models have been applied to CSA data analysis, supporting their implementation in portable, smartphone-based, and embedded sensing platforms. However, practical deployment is still limited by sensor degradation, environmental variability, response inconsistency, and the lack of standardized imaging and evaluation protocols. Future efforts should prioritize adaptive and lightweight algorithms, standardized data workflows, multimodal sensing systems, and sustainable, high-stability materials to enhance robustness, reproducibility, and industrial applicability.