Computers in biology and medicine最新文献

{"title":"Automatic detection and characterization of maturational neurobiomarkers identified as nested oscillations in premature newborns using high-density electroencephalography.","authors":"Mahdi Tanbakuchi, Laura Routier, Bahar Saadatmehr, Javad Safaie, Guy Kongolo, Ghida Ghostine, Fabrice Wallois, Sahar Moghimi","doi":"10.1016/j.compbiomed.2024.109477","DOIUrl":"https://doi.org/10.1016/j.compbiomed.2024.109477","url":null,"abstract":"<p><p>Neural development leads to the evolution of electroencephalographic (EEG) characteristics during the third trimester of gestation. Theta activity in coalescence with slow waves (TA-SW) and delta brushes (DB) are key clinical neurobiomarkers in the evaluation of neurodevelopment in infants prior to full-term gestation. Both neurobiomarkers exhibit nested oscillations, a key feature of intrinsic spontaneous oscillatory activity, allowing the investigation of neural interaction development in the underlying circuits. In the present study, we propose an automatic approach for the detection and characterization of neurobiomarkers that (1) leverages high-density EEG (HD-EEG), (2) incorporates temporal dynamics and spatial distributions, and (3) evaluates the characteristics of nested oscillations. This method evaluates both slow and rapid neural activity, along with their cross-frequency coupling. Our results are in good agreement with those of clinical experts, achieving ROC performances and overall accuracies of 91 %/84 % and 83 %/75 % for TA-SW/DB events, respectively. Following detection and validation, we characterized and compared these two neurobiomarkers. Correlation-based spatial clustering showed that DB patterns were more symmetric and diffuse, whereas TA-SW patterns were more localized in the right and left temporal areas. Comparisons revealed (1) greater variability in spatial patterns for DB than for TA-SW, and that (2) while slow-wave coupling to fast oscillations showed similar characteristics for both neurobiomarkers, differences emerged in the amplitude and descending slope of the underlying slow waves. These findings suggested potential differences in the mechanisms underlying their generation, particularly in the modulation of slow oscillations. This approach represents a promising avenue for the quantitative evaluation of EEG signatures pertinent to early neural development in premature neonates.</p>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"185 ","pages":"109477"},"PeriodicalIF":7.0,"publicationDate":"2024-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142791187","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":"Design and validation of Withings ECG Software 2, a tiny neural network based algorithm for detection of atrial fibrillation.","authors":"Paul Edouard, David Campo","doi":"10.1016/j.compbiomed.2024.109407","DOIUrl":"https://doi.org/10.1016/j.compbiomed.2024.109407","url":null,"abstract":"<p><strong>Background: </strong>Atrial Fibrillation (AF) is the most common form of arrhythmia in the world with a prevalence of 1%-2%. AF is also associated with an increased risk of cardiovascular diseases (CVD), such as stroke, heart failure, and coronary artery diseases, making it a leading cause of death. Asymptomatic patients are a common case (30%-40%). This highlights the importance of early diagnosis or screening. Wearable and home devices offer new opportunities in this regard.</p><p><strong>Methods: </strong>We present WECG-SW2, a lightweight algorithm that classifies 30-second lead I ECG strips as 'NSR', 'AF', 'Other' or 'Noise'. By detecting the location of QRS complexes in the signal, the information can be organized into a low dimensionality input which is fed to a tiny Convolutional Neural Network (CNN) with only 3,633 parameters. This approach allows for the algorithm to run directly on the ECG acquisition devices, and improves accuracy by making the most out of the training set.</p><p><strong>Results: </strong>WECG-SW2 was evaluated on a database which combines three clinical studies sponsored by Withings with three hardware devices, as well as the MIT-BIH Arrhythmia Database. On the proprietary clinical database, the sensitivity and specificity of AF detection were 99.63% (95% CI: 99.15-99.84) and 99.85% (95% CI: 99.61-99.94), respectively, based on 4646 strips taken from 1441 participants. On the MIT-BIH Arrhythmia Database, the sensitivity and specificity were 99.87% (95% CI: 99.53, 99.98) and 100% (95% CI: 98.31, 100.0), respectively, across 2624 analyzed segments.</p><p><strong>Conclusion: </strong>WECG-SW2 demonstrates high sensitivity and specificity in the detection of AF using a wide variety of ECG recording hardware. The binary of WECG-SW2 is available upon request to the corresponding author for research purposes.</p>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"185 ","pages":"109407"},"PeriodicalIF":7.0,"publicationDate":"2024-12-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142791191","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":"Advancing cancer diagnosis and prognostication through deep learning mastery in breast, colon, and lung histopathology with ResoMergeNet.","authors":"Chukwuebuka Joseph Ejiyi, Zhen Qin, Victor K Agbesi, Ding Yi, Abena A Atwereboannah, Ijeoma A Chikwendu, Oluwatoyosi F Bamisile, Grace-Mercure Bakanina Kissanga, Olusola O Bamisile","doi":"10.1016/j.compbiomed.2024.109494","DOIUrl":"https://doi.org/10.1016/j.compbiomed.2024.109494","url":null,"abstract":"<p><p>Cancer, a global health threat, demands effective diagnostic solutions to combat its impact on public health, particularly for breast, colon, and lung cancers. Early and accurate diagnosis is essential for successful treatment, prompting the rise of Computer-Aided Diagnosis Systems as reliable and cost-effective tools. Histopathology, renowned for its precision in cancer imaging, has become pivotal in the diagnostic landscape of breast, colon, and lung cancers. However, while deep learning models have been widely explored in this domain, they often face challenges in generalizing to diverse clinical settings and in efficiently capturing both local and global feature representations, particularly for multi-class tasks. This underscores the need for models that can reduce biases, improve diagnostic accuracy, and minimize error susceptibility in cancer classification tasks. To this end, we introduce ResoMergeNet (RMN), an advanced deep-learning model designed for both multi-class and binary cancer classification using histopathological images of breast, colon, and lung. ResoMergeNet integrates the Resboost mechanism which enhances feature representation, and the ConvmergeNet mechanism which optimizes feature extraction, leading to improved diagnostic accuracy. Comparative evaluations against state-of-the-art models show ResoMergeNet's superior performance. Validated on the LC-25000 and BreakHis (400× and 40× magnifications) datasets, ResoMergeNet demonstrates outstanding performance, achieving perfect scores of 100 % in accuracy, sensitivity, precision, and F1 score for binary classification. For multi-class classification with five classes from the LC25000 dataset, it maintains an impressive 99.96 % across all performance metrics. When applied to the BreakHis dataset, ResoMergeNet achieved 99.87 % accuracy, 99.75 % sensitivity, 99.78 % precision, and 99.77 % F1 score at 400× magnification. At 40× magnification, it still delivered robust results with 98.85 % accuracy, sensitivity, precision, and F1 score. These results emphasize the efficacy of ResoMergeNet, marking a substantial advancement in diagnostic and prognostic systems for breast, colon, and lung cancers. ResoMergeNet's superior diagnostic accuracy can significantly reduce diagnostic errors, minimize human biases, and expedite clinical workflows, making it a valuable tool for enhancing cancer diagnosis and treatment outcomes.</p>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"185 ","pages":"109494"},"PeriodicalIF":7.0,"publicationDate":"2024-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142784360","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":"Artificial intelligence for identification of candidates for device-aided therapy in Parkinson's disease: DELIST-PD study.","authors":"Eric Freire-Álvarez, Inés Legarda Ramírez, Rocio García-Ramos, Fátima Carrillo, Diego Santos-García, Juan Carlos Gómez-Esteban, Juan Carlos Martínez-Castrillo, Irene Martínez-Torres, Carlos J Madrid-Navarro, María José Pérez-Navarro, Fuensanta Valero-García, Bárbara Vives-Pastor, Laura Muñoz-Delgado, Beatriz Tijero, Carlos Morata Martínez, José M Valls, Ricardo Aler, Inés M Galván, Francisco Escamilla-Sevilla","doi":"10.1016/j.compbiomed.2024.109504","DOIUrl":"https://doi.org/10.1016/j.compbiomed.2024.109504","url":null,"abstract":"<p><strong>Introduction: </strong>In Parkinson's Disease (PD), despite available treatments focusing on symptom alleviation, the effectiveness of conventional therapies decreases over time. This study aims to enhance the identification of candidates for device-aided therapies (DAT) using artificial intelligence (AI), addressing the need for improved treatment selection in advanced PD stages.</p><p><strong>Methods: </strong>This national, multicenter, cross-sectional, observational study involved 1086 PD patients across Spain. Machine learning (ML) algorithms, including CatBoost, support vector machine (SVM), and logistic regression (LR), were evaluated for their ability to identify potential DAT candidates based on clinical and demographic data.</p><p><strong>Results: </strong>The CatBoost algorithm demonstrated superior performance in identifying DAT candidates, with an area under the curve (AUC) of 0.95, sensitivity of 0.91, and specificity of 0.88. It outperformed other ML models in balanced accuracy and negative predictive value. The model identified 23 key features as predictors for suitability for DAT, highlighting the importance of daily \"off\" time, doses of oral levodopa/day, and PD duration. Considering the 5-2-1 criteria, the algorithm identified a decision threshold for DAT candidates as > 4 times levodopa tablets taken daily and/or ≥1.8 h in daily \"off\" time.</p><p><strong>Conclusion: </strong>The study developed a highly discriminative CatBoost model for identifying PD patients candidates for DAT, potentially improving timely and accurate treatment selection. This AI approach offers a promising tool for neurologists, particularly those less experienced with DAT, to optimize referral to Movement Disorder Units.</p>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"185 ","pages":"109504"},"PeriodicalIF":7.0,"publicationDate":"2024-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142784363","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":"Self-supervised learning via VICReg enables training of EMG pattern recognition using continuous data with unclear labels.","authors":"Shriram Tallam Puranam Raghu, Dawn T MacIsaac, Erik J Scheme","doi":"10.1016/j.compbiomed.2024.109479","DOIUrl":"https://doi.org/10.1016/j.compbiomed.2024.109479","url":null,"abstract":"<p><p>In this study, we investigate the application of self-supervised learning via pre-trained Long Short-Term Memory (LSTM) networks for training surface electromyography pattern recognition models (sEMG-PR) using dynamic data with transitions. While labeling such data poses challenges due to the absence of ground-truth labels during transitions between classes, self-supervised pre-training offers a way to circumvent this issue. We compare the performance of LSTMs trained with either fully-supervised or self-supervised loss to a conventional non-temporal model (LDA) on two data types: segmented ramp data (lacking transition information) and continuous dynamic data inclusive of class transitions. Statistical analysis reveals that the temporal models outperform non-temporal models when trained with continuous dynamic data. Additionally, the proposed VICReg pre-trained temporal model with continuous dynamic data significantly outperformed all other models. Interestingly, when using only ramp data, the LSTM performed worse than the LDA, suggesting potential overfitting due to the absence of sufficient dynamics. This highlights the interplay between data type and model choice. Overall, this work highlights the importance of representative dynamics in training data and the potential for leveraging self-supervised approaches to enhance sEMG-PR models.</p>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"185 ","pages":"109479"},"PeriodicalIF":7.0,"publicationDate":"2024-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142784422","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":"Counting on AR: EEG responses to incongruent information with real-world context.","authors":"Michael Wimmer, Alex Pepicelli, Ben Volmer, Neven ElSayed, Andrew Cunningham, Bruce H Thomas, Gernot R Müller-Putz, Eduardo E Veas","doi":"10.1016/j.compbiomed.2024.109483","DOIUrl":"https://doi.org/10.1016/j.compbiomed.2024.109483","url":null,"abstract":"<p><p>Augmented Reality (AR) technologies enhance the real world by integrating contextual digital information about physical entities. However, inconsistencies between physical reality and digital augmentations, which may arise from errors in the visualized information or the user's mental context, can considerably impact user experience. This work characterizes the brain dynamics associated with processing incongruent information within an AR environment. To study these effects, we designed an interactive paradigm featuring the manipulation of a Rubik's cube serving as a physical referent. Congruent and incongruent information regarding the cube's current status was presented via symbolic (digits) and non-symbolic (graphs) stimuli, thus examining the impact of different means of data representation. The analysis of electroencephalographic signals from 19 participants revealed the presence of centro-parietal N400 and P600 components following the processing of incongruent information, with significantly increased latencies for non-symbolic stimuli. Additionally, we explored the feasibility of exploiting incongruency effects for brain-computer interfaces. Hence, we implemented decoders using linear discriminant analysis, support vector machines, and EEGNet, achieving comparable performances with all methods. Therefore, this work contributes to the design of adaptive AR systems by demonstrating that above-chance detection of incongruent information based on physiological signals is feasible. The successful decoding of incongruency-induced modulations can inform systems about the current mental state of users without making it explicit, aiming for more coherent and contextually appropriate AR interactions.</p>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"185 ","pages":"109483"},"PeriodicalIF":7.0,"publicationDate":"2024-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142784365","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":"Deep learning-based overall survival prediction in patients with glioblastoma: An automatic end-to-end workflow using pre-resection basic structural multiparametric MRIs.","authors":"Zi Yang, Aroosa Zamarud, Neelan J Marianayagam, David J Park, Ulas Yener, Scott G Soltys, Steven D Chang, Antonio Meola, Hao Jiang, Weiguo Lu, Xuejun Gu","doi":"10.1016/j.compbiomed.2024.109436","DOIUrl":"https://doi.org/10.1016/j.compbiomed.2024.109436","url":null,"abstract":"<p><strong>Purpose: </strong>Accurate and automated early survival prediction is critical for patients with glioblastoma (GBM) as their poor prognosis requires timely treatment decision-making. To address this need, we developed a deep learning (DL)-based end-to-end workflow for GBM overall survival (OS) prediction using pre-resection basic structural multiparametric magnetic resonance images (Bas-mpMRI) with a multi-institutional public dataset and evaluated it with an independent dataset of patients on a prospective institutional clinical trial.</p><p><strong>Materials and methods: </strong>The proposed end-to-end workflow includes a skull-stripping model, a GBM sub-region segmentation model and an ensemble learning-based OS prediction model. The segmentation model utilizes skull-stripped Bas-mpMRIs to segment three GBM sub-regions. The segmented GBM is fed into the contrastive learning-based OS prediction model to classify the patients into different survival groups. Our datasets include both a multi-institutional public dataset from Medical Image Computing and Computer Assisted Intervention (MICCAI) Brain Tumor Segmentation (BraTS) challenge 2020 with 235 patients, and an institutional dataset from a 5-fraction SRS clinical trial with 19 GBM patients. Each data entry consists of pre-operative Bas-mpMRIs, survival days and patient ages. Basic clinical characteristics are also available for SRS clinical trial data. The multi-institutional public dataset was used for workflow establishing (90% of data) and initial validation (10% of data). The validated workflow was then evaluated on the institutional clinical trial data.</p><p><strong>Results: </strong>Our proposed OS prediction workflow achieved an area under the curve (AUC) of 0.86 on the public dataset and 0.72 on the institutional clinical trial dataset to classify patients into 2 OS classes as long-survivors (>12 months) and short-survivors (<12 months), despite the large variation in Bas-mpMRI protocols. In addition, as part of the intermediate results, the proposed workflow can also provide detailed GBM sub-regions auto-segmentation with a whole tumor Dice score of 0.91.</p><p><strong>Conclusion: </strong>Our study demonstrates the feasibility of employing this DL-based end-to-end workflow to predict the OS of patients with GBM using only the pre-resection Bas-mpMRIs. This DL-based workflow can be potentially applied to assist timely clinical decision-making.</p>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"185 ","pages":"109436"},"PeriodicalIF":7.0,"publicationDate":"2024-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142784367","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":"Going Smaller: Attention-based models for automated melanoma diagnosis.","authors":"Sana Nazari, Rafael Garcia","doi":"10.1016/j.compbiomed.2024.109492","DOIUrl":"https://doi.org/10.1016/j.compbiomed.2024.109492","url":null,"abstract":"<p><p>Computational approaches offer a valuable tool to aid with the early diagnosis of melanoma by increasing both the speed and accuracy of doctors' decisions. The latest and best-performing approaches often rely on large ensemble models, with the number of trained parameters exceeding 600 million. However, this large parameter count presents considerable challenges in terms of computational demands and practical application. Addressing this gap, our work introduces a suite of attention-based convolutional neural network (CNN) architectures tailored to the nuanced classification of melanoma. These innovative models, founded on the EfficientNet-B3 backbone, are characterized by their significantly reduced size. This study highlights the feasibility of deploying powerful, yet compact, diagnostic models in practical settings, such as smartphone-based dermoscopy, and in doing so revolutionizing point-of-care diagnostics and extending the reach of advanced medical technologies to remote and under-resourced areas. It presents a comparative analysis of these novel models with the top three prize winners of the International Skin Imaging Collaboration (ISIC) 2020 challenge using two independent test sets. The results for our architectures outperformed the second and third-placed winners and achieved comparable results to the first-placed winner. These models demonstrated a delicate balance between efficiency and accuracy, holding their ground against larger models in performance metrics while operating on up to 98% less number of parameters and showcasing their potential for real-time application in resource-limited environments.</p>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"185 ","pages":"109492"},"PeriodicalIF":7.0,"publicationDate":"2024-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142784399","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":"Predicting cancer content in tiles of lung squamous cell carcinoma tumours with validation against pathologist labels.","authors":"Salma Dammak, Matthew J Cecchini, Jennifer Coats, Katherina Baranova, Aaron D Ward","doi":"10.1016/j.compbiomed.2024.109489","DOIUrl":"https://doi.org/10.1016/j.compbiomed.2024.109489","url":null,"abstract":"<p><strong>Background: </strong>A growing body of research is using deep learning to explore the relationship between treatment biomarkers for lung cancer patients and cancer tissue morphology on digitized whole slide images (WSIs) of tumour resections. However, these WSIs typically contain non-cancer tissue, introducing noise during model training. As digital pathology models typically start with splitting WSIs into tiles, we propose a model that can be used to exclude non-cancer tiles from the WSIs of lung squamous cell carcinoma (SqCC) tumours.</p><p><strong>Methods: </strong>We obtained 116 WSIs of tumours from 35 different centres from the Cancer Genome Atlas. A pathologist completed or reviewed cancer contours in four regions of interest (ROIs) within each WSIs. We then split the ROIs into tiles labelled with the percentage of cancer tissue within them and trained VGG16 to predict this value, and then we calculated regression error. To measure classification performance and visualize the classification results, we thresholded the predictions and calculated the area under the receiver operating characteristic curve (AUC).</p><p><strong>Results: </strong>The model's median regression error was 4% with a standard deviation of 35%. At a cancer threshold of 50%, the model had an AUC of 0.83. False positives tended to be in tissues that surround cancer, tiles with <50% cancer, and areas with high immune activity. False negatives tended to be microtomy defects.</p><p><strong>Conclusions: </strong>With further validation for each specific research application, the model we describe in this paper could facilitate the development of more effective research pipelines for predicting treatment biomarkers for lung SqCC.</p>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"185 ","pages":"109489"},"PeriodicalIF":7.0,"publicationDate":"2024-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142784410","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":"Progress on the development of prediction tools for detecting disease causing mutations in proteins.","authors":"M Michael Gromiha, Medha Pandey, A Kulandaisamy, Divya Sharma, Fathima Ridha","doi":"10.1016/j.compbiomed.2024.109510","DOIUrl":"https://doi.org/10.1016/j.compbiomed.2024.109510","url":null,"abstract":"<p><p>Proteins are involved in a variety of functions in living organisms. The mutation of amino acid residues in a protein alters its structure, stability, binding, and function, with some mutations leading to diseases. Understanding the influence of mutations on protein structure and function help to gain deep insights on the molecular mechanism of diseases and devising therapeutic strategies. Hence, several generic and disease-specific methods have been proposed to reveal pathogenic effects on mutations. In this review, we focus on the development of prediction methods for identifying disease causing mutations in proteins. We briefly outline the existing databases for disease-causing mutations, followed by a discussion on sequence- and structure-based features used for prediction. Further, we discuss computational tools based on machine learning, deep learning and large language models for detecting disease-causing mutations. Specifically, we emphasize the advances in predicting hotspots and mutations for targets involved in cancer, neurodegenerative and infectious diseases as well as in membrane proteins. The computational resources including databases and algorithms understanding/predicting the effect of mutations will be listed. Moreover, limitations of existing methods and possible improvements will be discussed.</p>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"185 ","pages":"109510"},"PeriodicalIF":7.0,"publicationDate":"2024-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142784421","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}