Computers in biology and medicine最新文献

{"title":"Comprehensive analysis of damage evolution in human annulus fibrosus: Numerical exploration of mechanical sensitivity to biological age-dependent alteration","authors":"","doi":"10.1016/j.compbiomed.2024.109108","DOIUrl":"10.1016/j.compbiomed.2024.109108","url":null,"abstract":"<div><h3>Background and objective</h3><p>The annulus fibrosus is an essential part of the intervertebral disc, critical for its structural integrity. Mechanical deterioration in this component can lead to complete disc failure, particularly through tears development, with radial tears being the most common. These tears are often the result of both mechanical and biological factors. This study aims to numerically investigate the mechanisms of radial failure in the annulus tissue, taking into account the mechanical and age-dependent biological damage origins. A newly developed microstructure-based model was upgraded to predict damage evolution in the different annulus regions.</p></div><div><h3>Methods</h3><p>The study employs a computational model to predict mechanical failures in various annulus regions, using experimental data for comparison. The model incorporates age-dependent microstructural changes to evaluate the effects of biological aging on the mechanical behavior. It specifically includes a detailed analysis of the temporal changes in circumferential rigidity and failure strain of the annulus.</p></div><div><h3>Results</h3><p>The model demonstrated a strong ability to replicate the experimental responses of the different annulus regions to failure. It revealed that age-related microstructural changes significantly impact the rigidity and failure response of the annulus, particularly in the posterior regions and as well the anterior inner side. These changes increase susceptibility to rupture with aging. A correlation was also observed between the composition of collagen fibers, water content, and the annulus transversal response in both radial and axial directions.</p></div><div><h3>Conclusion</h3><p>The findings challenge previous assumptions, showing that age-dependent microstructural changes have a notable effect on the annulus mechanical properties. The computational model closely aligns with experimental observations, underscoring the determinant role of oriented collagen fibers in radial failure. This study enhances the understanding of annulus failure and provides a foundation for further research on the impact of aging on disc mechanical integrity and failure.</p></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":null,"pages":null},"PeriodicalIF":7.0,"publicationDate":"2024-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142228593","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":"MedConceptsQA: Open source medical concepts QA benchmark","authors":"","doi":"10.1016/j.compbiomed.2024.109089","DOIUrl":"10.1016/j.compbiomed.2024.109089","url":null,"abstract":"<div><h3>Background:</h3><p>Clinical data often includes both standardized medical codes and natural language texts. This highlights the need for Clinical Large Language Models to understand these codes and their differences. We introduce a benchmark for evaluating the understanding of medical codes by various Large Language Models.</p></div><div><h3>Methods:</h3><p>We present MedConceptsQA, a dedicated open source benchmark for medical concepts question answering. The benchmark comprises of questions of various medical concepts across different vocabularies: diagnoses, procedures, and drugs. The questions are categorized into three levels of difficulty: easy, medium, and hard. We conduct evaluations of the benchmark using various Large Language Models.</p></div><div><h3>Results:</h3><p>Our findings show that most of the pre-trained clinical Large Language Models achieved accuracy levels close to random guessing on this benchmark, despite being pre-trained on medical data. However, GPT-4 achieves an absolute average improvement of 9-11% (9% for few-shot learning and 11% for zero-shot learning) compared to Llama3-OpenBioLLM-70B, the clinical Large Language Model that achieved the best results.</p></div><div><h3>Conclusion:</h3><p>Our benchmark serves as a valuable resource for evaluating the abilities of Large Language Models to interpret medical codes and distinguish between medical concepts. We demonstrate that most of the current state-of-the-art clinical Large Language Models achieve random guess performance, whereas GPT-3.5, GPT-4, and Llama3-70B outperform these clinical models, despite their primary focus during pre-training not being on the medical domain. Our benchmark is available at <span><span>https://huggingface.co/datasets/ofir408/MedConceptsQA</span><svg><path></path></svg></span>.</p></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":null,"pages":null},"PeriodicalIF":7.0,"publicationDate":"2024-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0010482524011740/pdfft?md5=fb5f9d095245838f5efa40561b4ea400&pid=1-s2.0-S0010482524011740-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142228594","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Molecular hybridization assisted multi-technique approach for designing USP21 inhibitors to halt catalytic triad-mediated nucleophilic attack and suppress pancreatic ductal adenocarcinoma progression: A molecular dynamics study","authors":"","doi":"10.1016/j.compbiomed.2024.109096","DOIUrl":"10.1016/j.compbiomed.2024.109096","url":null,"abstract":"<div><h3>Aims</h3><p>Pancreatic cancer, the 12th-most common cancer, globally, is highly challenging to treat due to its complex epigenetic, metabolic, and genomic characteristics. In pancreatic ductal adenocarcinoma, USP21 acts as an oncogene by stabilizing the long isoform of Transcription Factor 7, thereby activating the Wnt signaling pathway. This study aims to inhibit activation of this pathway through computer-aided drug discovery. Accordingly, four libraries of compounds were designed to target the USP21's catalytic domain (Cys221, His518, Asp534), responsible for its deubiquitinating activity.</p></div><div><h3>Main methods</h3><p>Utilizing an array of computer-aided drug design methodologies, such as molecular docking, virtual screening, principal component analysis, molecular dynamics simulation, and dynamic cross-correlation matrix, the structural and functional characteristics of the USP21-inhibitor complex were examined. Following the evaluation of the binding affinities, 20 potential ligands were selected, and the best ligand was subjected to additional molecular dynamics simulation study.</p></div><div><h3>Key findings</h3><p>The results indicated that the ligand-bound USP21 exhibited reduced structural fluctuations compared to the unbound form, as evident from RMSD, RMSF, Rg, and SASA graphs. ADMET analysis of the top ligand showed promising pharmacokinetic and pharmacodynamic profiles, good bioavailability, and low toxicity. The stable conformations of the proposed drug when bound to their target cavities indicate a robust binding affinity of −9.3 kcal/mol. The drug exhibits an elevated pKi value of 6.82, a noteworthy pIC₅₀ value of 5.972, and a pKd value of 6.023 proving its high affinity and inhibitory potential towards the target.</p></div><div><h3>Significance</h3><p>In-vitro testing of the top compound (MOLHYB-0436) could lead to its use as a potential treatment for pancreatic cancer.</p></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":null,"pages":null},"PeriodicalIF":7.0,"publicationDate":"2024-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142172449","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":"radMLBench: A dataset collection for benchmarking in radiomics","authors":"","doi":"10.1016/j.compbiomed.2024.109140","DOIUrl":"10.1016/j.compbiomed.2024.109140","url":null,"abstract":"<div><h3>Background</h3><p>New machine learning methods and techniques are frequently introduced in radiomics, but they are often tested on a single dataset, which makes it challenging to assess their true benefit. Currently, there is a lack of a larger, publicly accessible dataset collection on which such assessments could be performed. In this study, a collection of radiomics datasets with binary outcomes in tabular form was curated to allow benchmarking of machine learning methods and techniques.</p></div><div><h3>Methods</h3><p>A variety of journals and online sources were searched to identify tabular radiomics data with binary outcomes, which were then compiled into a homogeneous data collection that is easily accessible via Python. To illustrate the utility of the dataset collection, it was applied to investigate whether feature decorrelation prior to feature selection could improve predictive performance in a radiomics pipeline.</p></div><div><h3>Results</h3><p>A total of 50 radiomic datasets were collected, with sample sizes ranging from 51 to 969 and 101 to 11165 features. Using this data, it was observed that decorrelating features did not yield any significant improvement on average.</p></div><div><h3>Conclusions</h3><p>A large collection of datasets, easily accessible via Python, suitable for benchmarking and evaluating new machine learning techniques and methods was curated. Its utility was exemplified by demonstrating that feature decorrelation prior to feature selection does not, on average, lead to significant performance gains and could be omitted, thereby increasing the robustness and reliability of the radiomics pipeline.</p></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":null,"pages":null},"PeriodicalIF":7.0,"publicationDate":"2024-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0010482524012253/pdfft?md5=324bcab0a7099fccedc55b9754e883c7&pid=1-s2.0-S0010482524012253-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142172447","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"FvFold: A model to predict antibody Fv structure using protein language model with residual network and Rosetta minimization","authors":"","doi":"10.1016/j.compbiomed.2024.109128","DOIUrl":"10.1016/j.compbiomed.2024.109128","url":null,"abstract":"<div><p>The immune system depends on antibodies (Abs) to recognize and attach to a wide range of antigens, playing a pivotal role in immunity. The precise prediction of the variable fragment (Fv) region of antibodies is vital for the progress of therapeutic and commercial applications, particularly in the treatment of diseases such as cancer. Although deep learning models exist for accurate antibody structure prediction, challenges persist, particularly in modeling complementarity-determining regions (CDRs) and the overall antibody Fv structures. Introducing the FvFold model, a deep learning approach harnessing the capabilities of the ProtT5-XL-UniRef50 protein language model which is capable of predicting accurate antibody Fv structure. Through evaluations on various benchmarks, our model outperforms existing models, demonstrating superior accuracy by achieving lower Root Mean Square Deviation (RMSD) in almost all loops and Orientational Coordinate Distance (OCD) values in the RosettaAntibody benchmark, Therapeutic benchmark and IgFold benchmark compared to the previous top-performing model.</p></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":null,"pages":null},"PeriodicalIF":7.0,"publicationDate":"2024-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142172448","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":"Prediction of Expanded Disability Status Scale in patients with MS using deep learning","authors":"","doi":"10.1016/j.compbiomed.2024.109143","DOIUrl":"10.1016/j.compbiomed.2024.109143","url":null,"abstract":"<div><p>Multiple sclerosis (MS) is a chronic neurological condition that leads to significant disability in patients. Accurate prediction of disease progression, specifically the Expanded Disability Status Scale (EDSS), is crucial for personalizing treatment and improving patient outcomes. This study aims to develop a robust deep neural network framework to predict EDSS in MS patients using MRI scans. Our model demonstrates high accuracy and reliability in both lesion segmentation and disability classification tasks. For segmentation, the model achieves a Dice Coefficient of 0.87, a Jaccard Index of 0.79, sensitivity of 0.85, and specificity of 0.88. In classification, it attains an overall accuracy of 91.2 %, with a precision of 0.89, recall of 0.88, and an F1-Score of 0.885. Ablation studies highlight the significant impact of integrating T2-weighted and FLAIR images, improving accuracy from 85.7 % (T1-weighted alone) to 93.4 %. Comparative analysis with state-of-the-art methods demonstrates our model's superiority, outperforming Method A and Method B in both accuracy and F1-Score. Despite these advancements, challenges such as data quality, sample size, and computational complexity remain. Future research should focus on standardizing imaging protocols, incorporating larger and more diverse datasets, and optimizing model efficiency. Advancing deep learning architectures and utilizing multimodal data can enhance predictive power and facilitate real-time clinical applications. Our study significantly contributes to refining MS treatment strategies by providing a comprehensive evaluation of our model's performance and addressing key limitations. Accurate disability predictions enable personalized treatments, early interventions, and improved patient outcomes, thus enhancing the quality of life for individuals affected by MS.</p></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":null,"pages":null},"PeriodicalIF":7.0,"publicationDate":"2024-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142171665","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":"Quantifying decision support level of explainable automatic classification of diagnoses in Spanish medical records","authors":"","doi":"10.1016/j.compbiomed.2024.109127","DOIUrl":"10.1016/j.compbiomed.2024.109127","url":null,"abstract":"<div><h3>Background and Objective:</h3><p>In the realm of automatic Electronic Health Records (EHR) classification according to the International Classification of Diseases (ICD) there is a notable gap of non-black box approaches and more in Spanish, which is also frequently ignored in clinical language classification. An additional gap in explainability pertains to the lack of standardized metrics for evaluating the degree of explainability offered by distinct techniques.</p></div><div><h3>Methods:</h3><p>We address the classification of Spanish electronic health records, using methods to explain the predictions and improve the decision support level. We also propose Leberage a novel metric to quantify the decision support level of the explainable predictions.</p><p>We aim to assess the explanatory ability derived from three model-independent methods based on different theoretical frameworks: SHapley Additive exPlanations (SHAP), Local Interpretable Model-agnostic Explanations (LIME), and Integrated Gradients (IG). We develop a system based on longformers that can process long documents and then use the explainability methods to extract the relevant segments of text in the EHR that motivated each ICD. We then measure the outcome of the different explainability methods by implementing a novel metric.</p></div><div><h3>Results:</h3><p>Our results beat those that carry out the same task by 7%. In terms of explainability degree LIME appears as a stronger technique compared to IG and SHAP.</p></div><div><h3>Discussion:</h3><p>Our research reveals that the explored techniques are useful for explaining the output of black box models as the longformer. In addition, the proposed metric emerges as a good choice to quantify the contribution of explainability techniques.</p></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":null,"pages":null},"PeriodicalIF":7.0,"publicationDate":"2024-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S0010482524012125/pdfft?md5=bf52b292be72d43175e0167ed85f8f1a&pid=1-s2.0-S0010482524012125-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142171664","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Automatic motion artifact detection in electrodermal activity signals using 1D U-net architecture","authors":"","doi":"10.1016/j.compbiomed.2024.109139","DOIUrl":"10.1016/j.compbiomed.2024.109139","url":null,"abstract":"<div><p>We developed a method for automated detection of motion and noise artifacts (MNA) in electrodermal activity (EDA) signals, based on a one-dimensional U-Net architecture. EDA has been widely employed in diverse applications to assess sympathetic functions. However, EDA signals can be easily corrupted by MNA, which frequently occur in wearable systems, particularly those used for ambulatory recording. MNA can lead to false decisions, resulting in inaccurate assessment and diagnosis. Several approaches have been proposed for MNA detection; however, questions remain regarding the generalizability and the feasibility of implementation of the algorithms in real-time especially those involving deep learning approaches. In this work, we propose a deep learning approach based on a one-dimensional U-Net architecture using spectrograms of EDA for MNA detection. We developed our method using four distinct datasets, including two independent testing datasets, with a total of 9602 128-s EDA segments from 104 subjects. Our proposed scheme, including data augmentation, spectrogram computation, and 1D U-Net, yielded balanced accuracies of 80.0 ± 13.7 % and 75.0 ± 14.0 % for the two independent test datasets; these results are better than or comparable to those of other five state-of-the-art methods. Additionally, the computation time of our feature computation and machine learning classification was significantly lower than that of other methods (<em>p</em> &lt; .001). The model requires only 0.28 MB of memory, which is far smaller than the two deep learning approaches (4.93 and 54.59 MB) which were used as comparisons to our study. Our model can be implemented in real-time in embedded systems, even with limited memory and an inefficient microprocessor, without compromising the accuracy of MNA detection.</p></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":null,"pages":null},"PeriodicalIF":7.0,"publicationDate":"2024-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142171666","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":"Symptom mapping and personalized care for depression, anxiety and stress: A data-driven AI approach","authors":"","doi":"10.1016/j.compbiomed.2024.109146","DOIUrl":"10.1016/j.compbiomed.2024.109146","url":null,"abstract":"<div><h3>Background</h3><p>Depression, anxiety, and stress disorders have significant and widespread impacts worldwide, affecting millions of individuals and their communities. According to the World Health Organization, depression impacts the daily lives of more than 300 million people, making it one of the most important diseases globally. Treatment for these mental disorders (MD) typically involves medication and psychotherapies, but also incorporates technological resources like Artificial Intelligence (AI) to indicate personalized therapies and care. While various AI approaches have been applied in the context of MD in the literature, they often focus solely on aiding diagnosis.</p></div><div><h3>Objective</h3><p>This research proposes an AI approach for mapping symptoms and assisting in the personalized care of depression, anxiety, and stress.</p></div><div><h3>Methods</h3><p>Symptom mapping utilizes data mining (DM) techniques to generate rules representing knowledge extracted from data of 242 patients collected using the Depression, Anxiety, and Stress Scale (DASS-21). This knowledge elucidates how symptoms impact the severity degrees of considered MDs. Subsequently, the generated rules are employed to construct a Fuzzy Inference System (FIS) for inferring the severities of MDs based on patient symptoms and personal data.</p></div><div><h3>Results and conclusions</h3><p>The results achieved in the DM (accuracy ≥92.98 %, sensibility ≥86.02 %, specificity ≥97.32 %, and kappa statistic ≥87.98 %), indicating consistent patterns, along with the results produced by the FIS, demonstrate the potential of the proposed approach to assist health professionals in rapidly predicting symptoms of depression, anxiety, and stress, thereby facilitating outpatient screening and emergency care. Furthermore, it can improve the association of symptoms, referral to specialized care, therapeutic proposals, and even investigations of other diseases unrelated to MD.</p></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":null,"pages":null},"PeriodicalIF":7.0,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142168214","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":"Machine learning-based classification of Parkinson's disease using acoustic features: Insights from multilingual speech tasks","authors":"","doi":"10.1016/j.compbiomed.2024.109078","DOIUrl":"10.1016/j.compbiomed.2024.109078","url":null,"abstract":"<div><p>This study advances the automation of Parkinson's disease (PD) diagnosis by analyzing speech characteristics, leveraging a comprehensive approach that integrates a voting-based machine learning model. Given the growing prevalence of PD, especially among the elderly population, continuous and efficient diagnosis is of paramount importance. Conventional monitoring methods suffer from limitations related to time, cost, and accessibility, underscoring the need for the development of automated diagnostic tools. In this paper, we present a robust model for classifying speech patterns in Korean PD patients, addressing a significant research gap. Our model employs straightforward preprocessing techniques and a voting-based machine learning approach, demonstrating superior performance, particularly when training data is limited. Furthermore, we emphasize the effectiveness of the eGeMAPSv2 feature set in PD analysis and introduce new features that substantially enhance classification accuracy. The proposed model, achieving an accuracy of 84.73 % and an area under the ROC (AUC) score of 92.18 % on a dataset comprising 100 Korean PD patients and 100 healthy controls, offers a practical solution for automated diagnosis applications, such as smartphone apps. Future research endeavors will concentrate on enhancing the model's performance and delving deeper into the relationship between high-importance features and PD.</p></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":null,"pages":null},"PeriodicalIF":7.0,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142168245","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}