Computers in biology and medicine最新文献

{"title":"In silico determination of the temporal viral loads in the saliva and exhaled droplets from the oral cavity","authors":"Qiwei Dong ,&nbsp;Kazuki Kuga ,&nbsp;Nguyen Dang Khoa ,&nbsp;Kazuhide Ito","doi":"10.1016/j.compbiomed.2025.110692","DOIUrl":"10.1016/j.compbiomed.2025.110692","url":null,"abstract":"<div><h3>Background and objective</h3><div>The public health crisis triggered by the severe acute respiratory syndrome-coronavirus-2 (SARS-CoV-2) highlights the importance of the in-depth understanding of viral replication and re-emission mechanisms during coughing.</div></div><div><h3>Methods</h3><div>In this study, we used a Host-cell dynamics (HCD) model to characterize the replication kinetics of SARS-CoV-2 in the saliva of the oral cavity and optimized the fitting parameters based on clinical data to improve the viral load prediction accuracy. The Eulerian wall film model was integrated with the HCD model to quantify the viral load in the exhaled droplets during coughing. Additionally, variations in the oral cavity geometry were considered to determine its impact on the transmission risk of virus-laden droplets.</div></div><div><h3>Results</h3><div>HCD model showed that viral load in the oral cavity rose rapidly and peaked at around 10⁷ copies/mL during the incubation period (days −5 to −1), suggesting it as a major site for early viral replication. Integrated analysis revealed that the viral load of exhaled droplets was highly correlated with that of saliva, implying that a high viral load in the oral region exacerbates the transmission risk in the asymptomatic phase. Moreover, differences in oral cavity structure led to variations in the viral load carried by escaped droplets, thereby affecting the quantitative assessment of transmissibility.</div></div><div><h3>Conclusions</h3><div>This study systematically analyzed the dynamics of SARS-CoV-2 infection in the oral cavity. Our HCD-Eulerian wall film coupling approach provides a quantitative analytical tool to comprehensively assess all processes, from initial infection to inter-individual transmission, revealing the critical roles of the oral cavity in viral replication and droplet escape. These findings offer scientific insights for individual protection, airborne transmission risk assessment, and optimization of public health strategies.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"196 ","pages":"Article 110692"},"PeriodicalIF":7.0,"publicationDate":"2025-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144518597","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":"An LBM-FEM robust and efficient fluid–structure coupling scheme for partitioned numerical simulation of blood flow-aortic valve interaction","authors":"Jolan Lopez,&nbsp;Zhe Li,&nbsp;Guillaume Oger","doi":"10.1016/j.compbiomed.2025.110578","DOIUrl":"10.1016/j.compbiomed.2025.110578","url":null,"abstract":"<div><div>This paper presents a novel partitioned coupling scheme for the numerical simulation of Fluid-Structure Interaction (FSI) problems. The proposed method couples the lattice Boltzmann method for fluid dynamics with the finite element method for solid mechanics using the immersed boundary method. The partitioned framework enables separate time integration of the fluid and solid sub-domains, offering significant flexibility in the coupling process. Numerical stability is enhanced through an interface force prediction technique inspired by the strong coupling scheme of Li et al. (2022) , ensuring both robustness and computational efficiency. This approach effectively handles complex FSI problems, particularly in biomechanics. The scheme has been validated through the three-dimensional flapping flag benchmark test, demonstrating excellent agreement with reference results. Additionally, it has been successfully applied to simulate the interaction between pulsatile blood flows and the deformable leaflets of an artificial aortic valve. Compared with existing numerical and experimental studies, the proposed scheme delivers comparable accuracy while achieving nearly fourfold efficiency improvements over the previous strong coupling method.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"196 ","pages":"Article 110578"},"PeriodicalIF":7.0,"publicationDate":"2025-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144518580","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":"Multifaceted evolution focused on maximal exploitation of domain knowledge for the consensus inference of Gene Regulatory Networks","authors":"Adrián Segura-Ortiz ,&nbsp;Karen Giménez-Orenga ,&nbsp;José García-Nieto ,&nbsp;Elisa Oltra ,&nbsp;José F. Aldana-Montes","doi":"10.1016/j.compbiomed.2025.110632","DOIUrl":"10.1016/j.compbiomed.2025.110632","url":null,"abstract":"<div><div>The inference of gene regulatory networks (GRNs) is a fundamental challenge in systems biology, aiming to decipher gene interactions from expression data. However, traditional inference techniques exhibit disparities in their results and a clear preference for specific datasets. To address this issue, we present BIO-INSIGHT (Biologically Informed Optimizer - INtegrating Software to Infer GRNs by Holistic Thinking), a parallel asynchronous many-objective evolutionary algorithm that optimizes the consensus among multiple inference methods guided by biologically relevant objectives. BIO-INSIGHT has been evaluated on an academic benchmark of 106 GRNs, comparing its performance against MO-GENECI and other consensus strategies. The results show a statistically significant improvement in AUROC and AUPR, demonstrating that biologically guided optimization outperforms primarily mathematical approaches. Additionally, BIO-INSIGHT was applied to gene expression data from patients with fibromyalgia, myalgic encephalomyelitis, and co-diagnosis of both diseases. The inferred networks revealed regulatory interactions specific to each condition, suggesting its clinical utility in biomarker identification and potential therapeutic targets. The robustness and ingenuity of BIO-INSIGHT consolidate its potential as an innovative tool for GRN inference, enabling the generation of more accurate and biologically feasible networks. The source code is hosted in a public GitHub repository under the MIT license: <span><span>https://github.com/AdrianSeguraOrtiz/BIO-INSIGHT</span><svg><path></path></svg></span>. Moreover, to facilitate its reproducibility and usage, the software associated with this implementation has been packaged into a Python library available on PyPI: <span><span>https://pypi.org/project/GENECI/3.0.1/</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"196 ","pages":"Article 110632"},"PeriodicalIF":7.0,"publicationDate":"2025-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144516902","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":"Boost Protein Language Model with Injected Structure Information Through Parameter Efficient Fine-tuning","authors":"Zixun Zhang ,&nbsp;Yuzhe Zhou ,&nbsp;Jiayou Zheng ,&nbsp;Chunmei Feng ,&nbsp;Shuguang Cui ,&nbsp;Sheng Wang ,&nbsp;Zhen Li","doi":"10.1016/j.compbiomed.2025.110607","DOIUrl":"10.1016/j.compbiomed.2025.110607","url":null,"abstract":"<div><div>Large-scale Protein Language Models (PLMs), such as the Evolutionary Scale Modeling (ESM) family, have significantly advanced our understanding of protein structures and functions. These models have shown immense potential in biomedical applications, including drug discovery, protein design, and understanding disease mechanisms at the molecular level. However, PLMs are typically pre-trained on residue sequences alone, with limited incorporation of structural information, presenting opportunities for further enhancement. In this paper, we propose Structure Information Injecting Tuning (SI-Tuning), a parameter-efficient fine-tuning method, to integrate structural information into PLMs. SI-Tuning maintains the original model parameters in a frozen state while optimizing task-specific vectors for input embedding and attention maps. Structural features, including dihedral angles and distance maps, are used to derive this vector, injecting the structural information that improves model performance in downstream tasks. Extensive experiments on 650M ESM-2 demonstrate the effectiveness of our SI-Tuning across multiple downstream tasks. Specifically, our SI-Tuning achieves an accuracy of 93.95% on DeepLoc binary classification, and 76.05% on Metal Ion Binding, outperforming SaProt, a large-scale pre-trained PLM with structural modeling. SI-Tuning effectively enhances the performance of PLMs by incorporating structural information in a parameter-efficient manner. Our method not only advances downstream task performance, but also offers significant computational efficiency, making it a valuable strategy for applying large-scale PLM to broad biomedical downstream applications. Code is available at <span><span>https://github.com/Nocturne0256/SI-tuning</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"195 ","pages":"Article 110607"},"PeriodicalIF":7.0,"publicationDate":"2025-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144517269","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":"Unveiling the associations between self-reported morbidities and the constitutional-Chinese medicine questionnaire in the Taiwan Biobank: A cross-sectional association study","authors":"Dai-Yin Chen ,&nbsp;Chih-Sheng Chen ,&nbsp;Tse-Yen Yang","doi":"10.1016/j.compbiomed.2025.110684","DOIUrl":"10.1016/j.compbiomed.2025.110684","url":null,"abstract":"<div><div>Constitutional medicine was a transition from evidence-based medicine to precision medicine following the origin of Chinese medicine. The Constitutional CM Questionnaire (CM-CQ) commonly considers the various phenotypes observed as phenomes. However, the comprehensive associations between diseases and the phenotype of the questionnaire remained uncertain. Using the Taiwan Biobank pilot data, we conducted a community-based cross-sectional study of approximately 10,000 people. We separately evaluated the associations between general self-reported diseases and 44 items of CM-CQ questions using the binomial logistic regression model. Some chronic diseases must be predicted or shown to be associated with the self-declared condition of some CM-CQ questions with significant associations (Bonferroni adjusted p-value equal to 0.001) of all CM-CQ pre-existing diseases. Each CM-CQ question from Taiwan Biobank has shown a less significant overall effect on each disease, and the probability ratios generally approach a risk of less than two times. In addition, some diseases such as high blood pressure, gout, and diabetes, especially these common diseases, show increasing trends in the importance threshold and probability ratios (more than twice the risk). CM-CQ is regarded as an alteration in Chinese medical clinical characteristics. The final response concluded that biological databases provided evidence to clarify the association between Chinese medicine, different forms of illness, and the self-declared diseases of modern medicine, and the risk of diseases was assessed separately through each question. The exploratory questionnaire and self-reported conditions for the Chinese Medicine initiative clarified the associations between biobanks and community studies.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"195 ","pages":"Article 110684"},"PeriodicalIF":7.0,"publicationDate":"2025-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144517369","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":"U-Net-based architecture with attention mechanisms and Bayesian Optimization for brain tumor segmentation using MR images","authors":"K. Ramalakshmi ,&nbsp;L. Krishna Kumari","doi":"10.1016/j.compbiomed.2025.110677","DOIUrl":"10.1016/j.compbiomed.2025.110677","url":null,"abstract":"<div><div>As technological innovation in computers has advanced, radiologists may now diagnose brain tumors (BT) with the use of artificial intelligence (AI). In the medical field, early disease identification enables further therapies, where the use of AI systems is essential for time and money savings. The difficulties presented by various forms of Magnetic Resonance (MR) imaging for BT detection are frequently not addressed by conventional techniques. To get around frequent problems with traditional tumor detection approaches, deep learning techniques have been expanded. Thus, for BT segmentation utilizing MR images, a U-Net-based architecture combined with Attention Mechanisms has been developed in this work. Moreover, by fine-tuning essential variables, Hyperparameter Optimization (HPO) is used using the Bayesian Optimization Algorithm to strengthen the segmentation model's performance. Tumor regions are pinpointed for segmentation using Region-Adaptive Thresholding technique, and the segmentation results are validated against ground truth annotated images to assess the performance of the suggested model. Experiments are conducted using the LGG, Healthcare, and BraTS 2021 MRI brain tumor datasets. Lastly, the importance of the suggested model has been demonstrated through comparing several metrics, such as IoU, accuracy, and DICE Score, with current state-of-the-art methods. The U-Net-based method gained a higher DICE score of 0.89687 in the segmentation of MRI-BT.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"195 ","pages":"Article 110677"},"PeriodicalIF":7.0,"publicationDate":"2025-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144517270","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":"Unraveling chaotic motor patterns of elite and sub-elite wrestlers in snap-down technique using multidimensional recurrence quantification analysis of muscle activity","authors":"Kazem Esfandiarian-Nasab ,&nbsp;Mansour Eslami ,&nbsp;Fateme Salari-Esker ,&nbsp;Rohollah Yousefpour","doi":"10.1016/j.compbiomed.2025.110673","DOIUrl":"10.1016/j.compbiomed.2025.110673","url":null,"abstract":"<div><div>Success in competitive sports depends on athletes' ability to consistently perform complex motor patterns, requiring both stability and adaptability. Rapid adjustments are crucial in freestyle wrestling because of unpredictable opponent actions. Previous research has noted elite wrestlers' adaptability, but traditional linear analyses miss the chaotic, nonlinear dynamics of these movements. This study used multidimensional recurrence ruantification analysis (MDRQA) to explore repeatability, stability, and adaptability in recurrent patterns of neuromuscular coordination among elite and sub-elite wrestlers. Electromyography (EMG) signals from the triceps, biceps, anterior deltoid, and latissimus dorsi in the dominant upper limb were recorded during seven successful snap-down techniques. Determinism (%DET) and laminarity (%LAM) assessed repeatability and stability, whereas the entropy of diagonal (EntL) and vertical (EntV) recurrence patterns measured the complexity and adaptability. Elite wrestlers showed significantly higher %DET and %LAM values, indicating greater motor pattern consistency. Higher EntL and EntV values demonstrate increased complexity and adaptability in neuromuscular control, suggesting the use of chaotic dynamics for optimal performance. This study highlights the importance of nonlinear approaches, such as MDRQA, in understanding athletes' motor control. These insights can inform training programs to enhance athletes' consistency, adaptability, and complexity, ultimately improving their performance in unpredictable environments.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"196 ","pages":"Article 110673"},"PeriodicalIF":7.0,"publicationDate":"2025-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144516901","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":"Empowering heart attack treatment for women through machine learning and optimization techniques","authors":"Doaa Sami Khafaga ,&nbsp;Marwa M. Eid ,&nbsp;El-Sayed M. El-kenawy ,&nbsp;Ehsaneh Khodadadi ,&nbsp;Amel Ali Alhussan ,&nbsp;Nima Khodadadi","doi":"10.1016/j.compbiomed.2025.110597","DOIUrl":"10.1016/j.compbiomed.2025.110597","url":null,"abstract":"<div><div>Heart attack detection and treatment in women remain significantly under-optimized due to differences in symptom presentation and physiological characteristics compared to men, leading to delayed or incorrect diagnoses. Addressing this gap, this study introduces an optimized ensemble learning approach that leverages a novel voting classifier combining the Waterwheel Plant Algorithm (WWPA) with Stochastic Fractal Search (SFS). The proposed WWPA+SFS model is designed to enhance the accuracy of heart attack classification in women by integrating multiple machine learning classifiers, including Gaussian Naive Bayes, Random Forest, Logistic Regression, Stochastic Gradient Descent Classifier, Support Vector Classifier, Decision Tree, and k-nearest Neighbors. A comprehensive clinical dataset comprising 303 patient records and 14 features—covering demographic data, exercise-induced angina, chest pain type, major vessel count, cholesterol levels, fasting blood sugar, and resting electrocardiographic results—was used for evaluation. The model’s performance was validated using 10-fold cross-validation, Analysis of Variance (ANOVA), and the Wilcoxon Signed Rank Test, benchmarking it against other optimization-based classifiers such as Grey Wolf Optimization (GWO), Whale Optimization Algorithm (WOA), Particle Swarm Optimization (PSO), and Genetic Algorithm (GA). The proposed WWPA+SFS model achieved the highest classification accuracy (97.01%) and demonstrated low variance across multiple trials. These results underline the robustness and effectiveness of the proposed method in optimizing diagnostic models for women’s cardiovascular care, potentially reducing misdiagnosis rates, lowering healthcare costs, and contributing to personalized treatment advancements in clinical practice.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"195 ","pages":"Article 110597"},"PeriodicalIF":7.0,"publicationDate":"2025-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144517268","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":"Enhancing weakly supervised data augmentation networks for thyroid nodule assessment using traditional and doppler ultrasound images","authors":"Chadaporn Keatmanee ,&nbsp;Dittapong Songsaeng ,&nbsp;Songphon Klabwong ,&nbsp;Yoichi Nakaguro ,&nbsp;Alisa Kunapinun ,&nbsp;Mongkol Ekpanyapong ,&nbsp;Matthew N. Dailey","doi":"10.1016/j.compbiomed.2025.110553","DOIUrl":"10.1016/j.compbiomed.2025.110553","url":null,"abstract":"<div><div>Thyroid ultrasound (US) is an essential tool for detecting and characterizing thyroid nodules. In this study, we propose an innovative approach to enhance thyroid nodule assessment by integrating Doppler US images with grayscale US images through weakly supervised data augmentation networks (WSDAN). Our method reduces background noise by replacing inefficient augmentation strategies, such as random cropping, with an advanced technique guided by bounding boxes derived from Doppler US images. This targeted augmentation significantly improves model performance in both classification and localization of thyroid nodules. The training dataset comprises 1288 paired grayscale and Doppler US images, with an additional 190 pairs used for three-fold cross-validation. To evaluate the model’s efficacy, we tested it on a separate set of 190 grayscale US images. Compared to five state-of-the-art models and the original WSDAN, our Enhanced WSDAN model achieved superior performance. For classification, it reached an accuracy of 91%. For localization, it achieved Dice and Jaccard indices of 75% and 87%, respectively, demonstrating its potential as a valuable clinical tool.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"196 ","pages":"Article 110553"},"PeriodicalIF":7.0,"publicationDate":"2025-06-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144518579","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":"A hybrid approach for EEG motor imagery classification using adaptive margin disparity and knowledge transfer in convolutional neural networks","authors":"Senthil Vadivelan.D ,&nbsp;Prabhu Sethuramalingam","doi":"10.1016/j.compbiomed.2025.110675","DOIUrl":"10.1016/j.compbiomed.2025.110675","url":null,"abstract":"<div><div>– Motor Imagery (MI) using Electroencephalography (EEG) is essential in Brain-Computer Interface (BCI) technology, enabling interaction with external devices by interpreting brain signals. Recent advancements in Convolutional Neural Networks (CNNs) have significantly improved EEG classification tasks; however, traditional CNN-based methods rely on fixed convolution modes and kernel sizes, limiting their ability to capture diverse temporal and spatial features from one-dimensional EEG-MI signals. This paper introduces the Adaptive Margin Disparity with Knowledge Transfer 2D Model (AMD-KT2D), a novel framework designed to enhance EEG-MI classification. The process begins by transforming EEG-MI signals into 2D time-frequency representations using the Optimized Short-Time Fourier Transform (OptSTFT), which optimizes windowing functions and time-frequency resolution to preserve dynamic temporal and spatial features. The AMD-KT2D framework integrates a guide-learner architecture where Improved ResNet50 (IResNet50), pre-trained on a large-scale dataset, extracts high-level spatial-temporal features, while a Customized 2D Convolutional Neural Network (C2DCNN) captures multi-scale features. To ensure feature alignment and knowledge transfer, the Adaptive Margin Disparity Discrepancy (AMDD) loss function minimizes domain disparity, facilitating multi-scale feature learning in C2DCNN. The optimized learner model then classifies EEG-MI images into left and right-hand movement motor imagery classes. Experimental results on the real-world EEG-MI dataset collected using the Emotiv Epoc Flex system demonstrated that AMD-KT2D achieved a classification accuracy of 96.75 % for subject-dependent and 92.17 % for subject-independent, showcasing its effectiveness in leveraging domain adaptation, knowledge transfer, and multi-scale feature learning for advanced EEG-based BCI applications.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"195 ","pages":"Article 110675"},"PeriodicalIF":7.0,"publicationDate":"2025-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144510688","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}