Computers in biology and medicine最新文献

{"title":"Identification of effective cyclin-dependent kinase 3/cyclin E inhibitors using multi-level computational screening and simulation.","authors":"Srutishree Sarma, Dikshita Dowerah, Shilpa Neog, Nishant Biswakarma, Priyanka Dutta, Gaurisankar Phukan, Ramesh Ch Deka","doi":"10.1016/j.compbiomed.2025.111134","DOIUrl":"https://doi.org/10.1016/j.compbiomed.2025.111134","url":null,"abstract":"<p><strong>Introduction: </strong>Cyclin-dependent kinase 3 (CDK3) plays a crucial role in regulating cell cycle progression through the G0/G1 and G1/S phases. Although extensively lowered in normal tissue, CDK3 is overexpressed in multiple cancers, making it a promising target for anticancer therapy. Despite its significance, no established inhibitors of CDK3 are currently available.</p><p><strong>Methods: </strong>We aimed to identify effective inhibitors of CDK3/cyclin E from a library of 204 derivatives of five potent CDK3 inhibitors-Purvalanol A, NU6102, R547, dinaciclib, and RO-3306, using a multi-tiered computational pipeline. Molecular docking was first used to screen these candidates which has emerged as an efficient technique to elucidate binding energies and interactions of compounds to target receptors, thereby playing indispensable roles in drug discovery. Five top-scoring candidates from docking were evaluated through ADMET profiling, global reactivity studies, 100ns duplicate molecular dynamics (MD) simulations and Our own N-layered Integrated molecular Orbital and molecular Mechanics (ONIOM) calculations. Two hits showing optimal inhibition were subjected to extended 1200ns MD simulations.</p><p><strong>Results and discussion: </strong>Docking studies identified interactions of the five selected candidates with crucial residues of CDK3. Global reactivity suggested favourable electronic properties for receptor binding. MD simulations, MM-PBSA and ONIOM revealed stable ligand-receptor interactions and favourable binding energetics. Extended 1200ns simulations of the two hits, CID_11212010 and CID_25211747, demonstrated exceptional stability of CID_25211747 with minimal conformational fluctuation. Additional ONIOM calculations reproduced the strong binding affinity of CID_25211747 with CDK3. Collectively, these results nominate CID_25211747 as a promising lead towards the development of effective CDK3 antagonists, offering valuable insight for future drug design.</p>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"198 Pt A","pages":"111134"},"PeriodicalIF":6.3,"publicationDate":"2025-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145257844","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Neural responses in premature infants to repetition and alternation stimulations: A CNN-based analysis of EEG signals for temporal and spatial insights.","authors":"Mandana Sadat Ghafourian, Javad Safaie, Amin Ramezani","doi":"10.1016/j.compbiomed.2025.111175","DOIUrl":"https://doi.org/10.1016/j.compbiomed.2025.111175","url":null,"abstract":"<p><p>Premature infants respond to different stimuli. This research intends to assess the temporal and spatial convolution layers of a convolutional neural network (CNN) to enhance our understanding of their operations. Additionally, it seeks to analyze and compare the variations and similarities in electroencephalography (EEG) responses among premature infants, particularly those at 31 weeks of gestational age (wGA), when exposed to repetitive and alternating auditory stimulus patterns. In our study, we employed the CNN to classify two auditory sequences: \"ga ga ga ga ga\" and \"ga ga ga ga ba\" or \"ba ga ba ga ba\" and \"ba ga ba ga ga\". The use of the CNN is advantageous because it can effectively handle noise and does not necessitate manual feature extraction. By performing average area under the curve (AUC) calculations for each brain region via the weights and trained network, we were able to assess the discrimination capabilities of different regions. The AUCs for the CNN in distinguishing syllables from repetition and alternation stimuli were 0.91 and 0.92, respectively. In premature infants, alternating sequences generate a delayed response compared to repetitive sequences. Results clearly indicate that the right temporal frontal region has the highest AUC values for the repetition protocol, whereas the left temporal frontal region has the highest AUC values for the alternation protocol. By integrating spatial and temporal convolutions in our CNN model, we effectively captured the complex interactions between auditory processing and cognitive functions.</p>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"198 Pt A","pages":"111175"},"PeriodicalIF":6.3,"publicationDate":"2025-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145257798","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Computational assessment of fibromuscular dysplasia-related renal artery stenosis.","authors":"Luca Soliveri, Maria Stoenoiu, Michela Bozzetto, Francesco Meris, Tom Robberechts, Frank Hammer, Etienne Danse, Laurent Toubiana, Andrzej Januszewicz, Magdalena Januszewicz, Andrea Remuzzi, Anna Caroli, Alexandre Persu","doi":"10.1016/j.compbiomed.2025.111181","DOIUrl":"https://doi.org/10.1016/j.compbiomed.2025.111181","url":null,"abstract":"<p><strong>Background: </strong>Fibromuscular dysplasia (FMD) is a potentially curable cause of renovascular hypertension, primarily affecting middle-aged women. Percutaneous angioplasty is the recommended treatment for patients with hemodynamically significant renal artery stenosis (RAS). However, no established non-invasive method currently exists to estimate the pressure drop across stenosis and assess its hemodynamic impact. This study aimed to assess the clinical applicability of an image-based computational fluid dynamic (CFD) pipeline, functioning as a digital twin of the renal vasculature, for non-invasive assessment of fractional flow reserve (FFR) and trans-stenotic pressure drop in patients with FMD-related RAS.</p><p><strong>Methods: </strong>This retrospective study included 10 middle-aged women: six with FMD-related stenosis (two focal and four multifocal), two with atherosclerotic RAS and two healthy volunteers. For each subject, a patient-specific 3D surface model of the renal vasculature was reconstructed from medical images and CFD simulations were performed using Simvascular. FFR and trans-stenotic pressure drop were assessed across each renal artery.</p><p><strong>Results: </strong>The imaged-based CFD pipeline was feasible for all 10 subjects. A wide range of FFR (0.57 - >0.95) and pressure drops (11-73 mmHg) was observed across subjects, depending on the phenotype and severity of stenosis. The computed pressure drops and FFR values were consistent with the clinical decision on revascularization (AUC = 0.988), supporting the diagnostic relevance of the model.</p><p><strong>Conclusion: </strong>The proposed pipeline represents a promising non-invasive approach to assess the hemodynamic significance of RAS due to FMD. As a digital twin for personalized cardiovascular medicine, it could serve as valuable tool for selecting patients requiring angioplasty and predicting revascularization outcomes.</p>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"198 Pt A","pages":"111181"},"PeriodicalIF":6.3,"publicationDate":"2025-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145257836","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Reconstructing ventricular activation sequences from epicardial data: Insights from Geodesic Back-Propagation optimization in porcine models.","authors":"Lindsay C R Tanner, Anna Busatto, Thomas Grandits, Jake A Bergquist, Brian Zenger, Simone Pezzuto, Gernot Plank, Rob S MacLeod, Karli Gillette","doi":"10.1016/j.compbiomed.2025.111178","DOIUrl":"https://doi.org/10.1016/j.compbiomed.2025.111178","url":null,"abstract":"<p><p>Cardiac digital twins (CDTs) are emerging as powerful tools in personalized medicine, providing subject-specific models to simulate and understand cardiac function. A central challenge in constructing CDTs is accurately personalizing the structure and function of the His-Purkinje system (HPS), which determines ventricular activation. In this study, we leveraged a novel modified Geodesic-BP method to infer early activation sites (EASs) from epicardial activation times. The EASs can then serve as a surrogate for Purkinje-myocardial junctions, facilitating anterograde ventricular activation. We used both experimental porcine (N = 5) and synthetic (N = 5) datasets of epicardial activation times measured or assigned to locations on an electrode sock. For both datasets, we optimized for initial estimates of 5, 50, 100, and 200 EASs and assessed output variability by repeating the inference process 10 times. Assessments were based on matching the predicted activation times at both the epicardial locations and from intracardiac measurements made with multielectrode needles, and throughout the ventricular myocardium for the synthetic dataset. The algorithm could consistently recover global ventricular activation patterns from epicardial data alone. For the experimental dataset, the minimum and maximum mean absolute differences were 0.19 ms and 3.86 ms on the epicardial sock and 2.65 ms and 10.69 ms for the needles. For the synthetic dataset, the corresponding values were 0.13 ms and 2.81 ms on the sock and 2.42 ms and 14.07 ms ms throughout the ventricular myocardium. However, discrepancies between the epicardial surface and intramural myocardium, overfitting of EASs, and variability across repeated runs revealed key limitations. These findings highlight both the overall potential and current limitations of inferring EASs using the proposed optimization approach. They demonstrate the feasibility of deriving informative activation patterns from limited data, while underscoring the need to incorporate stronger physiological priors and anatomical constraints. Ultimately, our results motivate future efforts to refine simulation-based personalization frameworks, improve robustness, and enhance the physiological realism of CDTs for more accurate and reliable applications.</p>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"198 Pt A","pages":"111178"},"PeriodicalIF":6.3,"publicationDate":"2025-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145257865","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Magnetically controlled oscillatory flow of micropolar-Jeffrey fluid in a diseased artery: A sensitivity analysis-based model for non-invasive thrombosis treatment.","authors":"P Vaidehi, J Sasikumar, Mustafa Turkyilmazoglu","doi":"10.1016/j.compbiomed.2025.111133","DOIUrl":"https://doi.org/10.1016/j.compbiomed.2025.111133","url":null,"abstract":"<p><p>The study addresses the complex hemodynamics of diseased arteries by incorporating micropolar and Jeffrey fluid characteristics under magnetic influence, which is significant for improving non-invasive diagnostic and therapeutic strategies. The primary aim is to analyze the effect of vortex viscosity, spin gradient viscosity, micro-inertia, fluid elasticity and magnetic fields on oscillatory blood flow, microrotation and heat transfer in a stenosed arterial segment. The governing equations for velocity, microrotation and temperature are non-dimensionalized and solved using the Crank-Nicolson finite difference method, with additional sensitivity and uncertainty analyses performed via orthogonal array techniques and Monte Carlo simulations. Results reveal that magnetic fields reduce flow velocity and microrotation due to Lorentz force damping, while fluid elasticity enhances them and that heat transfer is most sensitive to the Eckert and Peclet numbers, with vortex and spin gradient viscosities having the strongest impact on couple stress. These findings provide a robust computational framework for predicting flow and thermal behaviors in magnetically assisted treatments, supporting targeted clinical applications such as magnetic therapy, vascular hyperthermia and localized drug delivery.</p>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"198 Pt A","pages":"111133"},"PeriodicalIF":6.3,"publicationDate":"2025-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145257871","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evaluating visco-hyperelastic mechanical responses of hydrogel-based scaffolds and their potential for biomechanical restoration of the human mandibular joint.","authors":"Daniel Fidalgo, Pedro Rebolo, Marcelo Costa, João Maia, Nilza Ramião, Rita Sobreiro-Almeida, Bruno Areias, Ana Guerra, Catarina Custódio, Paula Torres, Nilza Ribeiro, Susana Olhero, João Mano, Marco Parente","doi":"10.1016/j.compbiomed.2025.111185","DOIUrl":"https://doi.org/10.1016/j.compbiomed.2025.111185","url":null,"abstract":"<p><p>This study researches the viscous and hyperelastic mechanical behaviors of hydrogel-based nanocomposite materials, including: (i) a composite of human methacryloyl platelet lysate (hPLMA), human platelet lysates (hPL), and nanohydroxyapatite (nHA); (ii) bovine serum albumin methacryloyl (BSAMA); and (iii) hyaluronic acid methacryloyl (HAMA). These materials stand out for their enhanced bioactivity and mechanical strength compared to traditional hydrogels. Their potential applications in various scaffold architectures and the biomechanical restoration of the mandibular joint are investigated. Mechanical compression and relaxation tests are performed on the hydrogel-based samples, with varying nHA content (0%, 1%, and 5%) in the hPL/hPLMA composite, to characterize their visco-hyperelastic behavior. Mechanical parameters are optimized using a micro-genetic algorithm. Results show that increasing nHA content raises compressive stress and intensifies the viscoelastic response. Besides, higher strut density and staggered orthogonal patterns produce more uniform stress distribution despite a less stable viscous response. In in silico simulations of the human mandible, a multimaterial scaffold was created, featuring a hydrogel core with ceramic-based scaffold ends (hydroxyapatite-based cement enriched with hPL). The ceramic phase provided effective mechanical protection for the hydrogel. Besides, substituting the hPL/hPLMA core with HAMA reduced the stress values in the hydrogel phase, while using BSAMA led to increased stress. This study introduces a novel framework integrating experimental data, mechanical optimization, and numerical simulations to elucidate the viscoelastic behavior of hydrogel-based nanocomposite inks and multimaterial scaffolds. This research advances the development of next-generation biomaterials with improved durability and functionality, promoting regenerative medicine and personalized tissue engineering.</p>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"198 Pt A","pages":"111185"},"PeriodicalIF":6.3,"publicationDate":"2025-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145257820","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"SAPP: Structure Aware PTM Prediction.","authors":"Yujin Choo, Seungjin Na, Eunok Paek","doi":"10.1016/j.compbiomed.2025.111169","DOIUrl":"https://doi.org/10.1016/j.compbiomed.2025.111169","url":null,"abstract":"<p><p>Post-translational modifications (PTMs) play critical roles in regulating cellular processes such as signal transduction, cell growth, and differentiation. Accurate identification of PTM sites is fundamental to understanding cellular mechanisms and developing therapeutic interventions. However, traditional computational models have predominantly relied on sequence data alone, neglecting important structural contexts such as intrinsically disordered regions and solvent accessibility. To address this gap, we introduce SAPP (Structure-Aware PTM Prediction), a pioneering model that integrates structural features derived from AlphaFold2 predictions with sequence information using a unified Transformer-based framework. Utilizing self-attention and cross-attention mechanisms, SAPP effectively captures complex interactions between sequences and their structural states, improving prediction accuracy and biological relevance over sequence-based models. Notably, SAPP is among the first structure-based PTM prediction frameworks, which allows for fine-tuning from a phosphorylation-pretrained model to other PTM types, achieving generalization performance in PTM types with limited training data. This supports the critical role of structural information in PTM prediction, deepening our understanding of their biological significance.</p>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"198 Pt A","pages":"111169"},"PeriodicalIF":6.3,"publicationDate":"2025-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145257806","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Advanced concept for identifying chemico-biological interactions associated with programmed cell death using a multi-scale attention residual convolutional neural network.","authors":"Igor V Pantic, Jovana Paunovic Pantic","doi":"10.1016/j.compbiomed.2025.111186","DOIUrl":"https://doi.org/10.1016/j.compbiomed.2025.111186","url":null,"abstract":"<p><p>Early detection of programmed cell death (apoptosis) remains a significant challenge in microscopy and cell biology, particularly when relying on subtle nuclear texture changes observed in stained micrographs. Traditional machine learning models, such as decision trees and random forests, are limited in their methodological capacity and often fail to capture complex spatial relationships within nuclear architecture. Unlike these conventional approaches, our study introduces a novel Multi-Scale Attention Residual Convolutional Neural Network (MSA-RCNN) designed to learn discriminative features from nuclear chromatin patterns associated with early apoptotic changes. We suggest using quantifiers of the Gray-Level Entropy Matrix (GLEM), Run-Length Matrix (RLM), and Discrete Fourier Transform (DFT) as input parameters during training and testing, focusing on the combination of four parameters: RLM Short Run Emphasis, RLM Long Run Emphasis, GLEM Entropy, and DFT Magnitude Spectrum Mean. We also discuss the advantages and limitations of this approach and its potential to be included in future artificial intelligence-based sensing systems for apoptosis detection in research and clinical conditions. Like many deep learning models, the proposed MSA-RCNN is limited by challenges in interpretability and generalization, which future work will address through explainability analyses and validation on different datasets.</p>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"198 Pt A","pages":"111186"},"PeriodicalIF":6.3,"publicationDate":"2025-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145257751","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Multimodal adaptive fusion deep analysis model for Alzheimer's disease exploration and diagnosis.","authors":"Yi-Ming Wang, Jingyu Zhang, Cui-Na Jiao, Bao-Min Liu, Tian-Ru Wu, Jin-Xing Liu, Shan Huang","doi":"10.1016/j.compbiomed.2025.111117","DOIUrl":"https://doi.org/10.1016/j.compbiomed.2025.111117","url":null,"abstract":"<p><p>Alzheimer's disease (AD) is a chronic progressive neurodegenerative disorder, the etiology and pathogenesis of which are currently unclear. Brain imaging genetics, which analyzes genetic factors and neuroimaging phenotypic data in association, is an effective technique for identifying AD-related biomarkers. With the rapid advancement of imaging and genetic sequencing technologies, the association between multimodal imaging data and genetic data has gradually received widespread attention. However, how to make full use of the complementary information between multimodal data is an urgent problem to be solved. Therefore, Multimodal Adaptive Fusion Deep Association Analysis Model (MAFDAA) is proposed to solve the above problems. Firstly, a novel multi-head attention graph convolutional model is proposed to extract and reconstruct complementary information among multimodal data, thus constructing a comprehensive representation of brain information. Secondly, the representation module statistically encodes genetic data to obtain genetic representations, while embedding demographic information as a supplement to the genetic representation. Subsequently, in the association analysis module, nonlinear correlation analysis is conducted between genetic representations and brain reconstruction data, yielding latent association vectors for subsequent research. Finally, the diagnostic module diagnoses the subjects and identifies AD-related biomarkers based on the association analysis results. The experimental results demonstrate that MAFDAA exhibits excellent diagnostic performance. Additionally, the identified biomarkers were analyzed from different perspectives, establishing a new approach for studying the complex genetic mechanisms of neurodegenerative diseases from a micro to macro scale.</p>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"198 Pt A","pages":"111117"},"PeriodicalIF":6.3,"publicationDate":"2025-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145257823","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Use of machine learning for predicting stress episodes based on wearable sensor data: A systematic review.","authors":"António Oseas Pataca, Eftim Zdravevski, Paulo Jorge Coelho, Nuno M Garcia, Margot Deryuck, Carlos Albuquerque, Ivan Miguel Pires","doi":"10.1016/j.compbiomed.2025.111166","DOIUrl":"https://doi.org/10.1016/j.compbiomed.2025.111166","url":null,"abstract":"<p><strong>Objective: </strong>This study consists of a systematic literature review that aims to explore the potential of integrating wearable sensor data and machine learning (ML) techniques for predicting stress episodes. It aims to identify prevalent sensors, key physiological features, and the effectiveness of ML methods in real-world stress monitoring and prediction.</p><p><strong>Methods: </strong>This systematic review follows the PRISMA methodology, analyzing literature from January 2010 to June 2025. Data sources included IEEE Xplore, Elsevier, Springer, Multidisciplinary Digital Publishing Institute (MDPI), and paper repositories such as PubMed Central and the Association of Computing Machinery (ACM). The inclusion criteria encompassed studies that employed wearable devices for ML stress prediction, focusing on physiological data such as heart rate variability (HRV), skin conductance, and sleep patterns. Articles were screened for originality, clinical relevance, and methodological rigor.</p><p><strong>Results: </strong>Key findings highlighted the use of diverse wearable sensors, including electrodermal activity (EDA), photoplethysmography (PPG), and accelerometers. Commonly extracted features included HRV metrics, skin conductance levels, and respiratory patterns. ML models, such as Random Forest (RF), Support Vector Machines (SVM), and deep neural networks (DNN), have demonstrated high predictive accuracy (e.g., up to 99%). Despite promising results, challenges such as small sample sizes, variability in data quality, and the need for standardized protocols were noted.</p><p><strong>Conclusion: </strong>Wearable sensors combined with ML algorithms provide scalable, real-time stress monitoring solutions, emphasizing proactive healthcare management. However, advancing this field requires addressing limitations through interdisciplinary collaboration and focusing on the accessibility and usability of technologies.</p><p><strong>Significance: </strong>This study highlights the transformative role of wearable technologies in predicting stress, with implications for personalized health interventions, mental health support, and enhanced healthcare efficiency.</p>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"198 Pt A","pages":"111166"},"PeriodicalIF":6.3,"publicationDate":"2025-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145250282","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}