Computers in biology and medicine最新文献

{"title":"Peptide classification landscape: An in-depth systematic literature review on peptide types, databases, datasets, predictors architectures and performance","authors":"Muhammad Nabeel Asim ,&nbsp;Tayyaba Asif ,&nbsp;Faiza Mehmood ,&nbsp;Andreas Dengel","doi":"10.1016/j.compbiomed.2025.109821","DOIUrl":"10.1016/j.compbiomed.2025.109821","url":null,"abstract":"<div><div>Peptides are gaining significant attention in diverse fields such as the pharmaceutical market has seen a steady rise in peptide-based therapeutics over the past six decades. Peptides have been utilized in the development of distinct applications including inhibitors of SARS-COV-2 and treatments for conditions like cancer and diabetes. Distinct types of peptides possess unique characteristics, and development of peptide-specific applications require the discrimination of one peptide type from others. To the best of our knowledge, approximately 230 Artificial Intelligence (AI) driven applications have been developed for 22 distinct types of peptides, yet there remains significant room for development of new predictors. A Comprehensive review addresses the critical gap by providing a consolidated platform for the development of AI-driven peptide classification applications. This paper offers several key contributions, including presenting the biological foundations of 22 unique peptide types and categorizes them into four main classes: Regulatory, Therapeutic, Nutritional, and Delivery Peptides. It offers an in-depth overview of 47 databases that have been used to develop peptide classification benchmark datasets. It summarizes details of 288 benchmark datasets that are used in development of diverse types AI-driven peptide classification applications. It provides a detailed summary of 197 sequence representation learning methods and 94 classifiers that have been used to develop 230 distinct AI-driven peptide classification applications. Across 22 distinct types peptide classification tasks related to 288 benchmark datasets, it demonstrates performance values of 230 AI-driven peptide classification applications. It summarizes experimental settings and various evaluation measures that have been employed to assess the performance of AI-driven peptide classification applications. The primary focus of this manuscript is to consolidate scattered information into a single comprehensive platform. This resource will greatly assist researchers who are interested in developing new AI-driven peptide classification applications.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"188 ","pages":"Article 109821"},"PeriodicalIF":7.0,"publicationDate":"2025-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143464360","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":"Uncertainty in cardiovascular digital twins despite non-normal errors in 4D flow MRI: Identifying reliable biomarkers such as ventricular relaxation rate","authors":"Kajsa Tunedal ,&nbsp;Tino Ebbers ,&nbsp;Gunnar Cedersund","doi":"10.1016/j.compbiomed.2025.109878","DOIUrl":"10.1016/j.compbiomed.2025.109878","url":null,"abstract":"<div><div>Cardiovascular digital twins and mechanistic models can be used to obtain new biomarkers from patient-specific hemodynamic data. However, such model-derived biomarkers are only clinically relevant if the uncertainty of the biomarkers is smaller than the variation between timepoints/patients. Unfortunately, this uncertainty is challenging to calculate, as the uncertainty of the underlying hemodynamic data is largely unknown and has several sources that are not additive or normally distributed. This violates normality assumptions of current methods; implying that also biomarkers have an unknown uncertainty. To remedy these problems, we herein present a method, with attached code, for uncertainty calculation of model-derived biomarkers using non-normal data. First, we estimated all sources of uncertainty, both normal and non-normal, in hemodynamic data used to personalize an existing model; the errors in 4D flow MRI-derived stroke volumes were 5–20 % and the blood pressure errors were 0 ± 8 mmHg. Second, we estimated the resulting model-derived biomarker uncertainty for 100 simulated datasets, sampled from the data distributions, by: 1) combining data uncertainties 2) parameter estimation, 3) profile-likelihood. The true biomarker values were found within a 95 % confidence interval in 98 % (median) of the cases. This shows both that our estimated data uncertainty is reasonable, and that we can use profile-likelihood despite the non-normality. Finally, we demonstrated that e.g. ventricular relaxation rate has a smaller uncertainty (∼10 %) than the variation across a clinical cohort (∼40 %), meaning that these biomarkers have clinical potential. Our results take us one step closer to the usage of model-derived biomarkers for cardiovascular patient characterization.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"188 ","pages":"Article 109878"},"PeriodicalIF":7.0,"publicationDate":"2025-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143464396","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":"EasyCircR: Detection and reconstruction of circular RNAs post-transcriptional regulatory interaction networks","authors":"Antonino Aparo ,&nbsp;Simone Avesani ,&nbsp;Luca Parmigiani ,&nbsp;Sara Napoli ,&nbsp;Francesco Bertoni ,&nbsp;Vincenzo Bonnici ,&nbsp;Luciano Cascione ,&nbsp;Rosalba Giugno","doi":"10.1016/j.compbiomed.2025.109846","DOIUrl":"10.1016/j.compbiomed.2025.109846","url":null,"abstract":"<div><div>Circular RNAs (circRNAs) are regulatory RNAs that play a crucial role in various biological activities and have been identified as potential biomarkers for neurological disorders and cancer. CircRNAs have emerged as significant regulators of gene expression through different mechanisms, including regulation of transcription and splicing, modulation of translation, and post-translational modifications. Additionally, some circRNAs operate as microRNA (miRNA) sponges in the cytoplasm, boosting post-transcriptional expression of target genes by inhibiting miRNA activity. Although existing pipelines can reconstruct circRNAs, identify miRNAs sponged by them, retrieve cascade-regulated mRNAs, and represent the regulatory interactions as complex circRNA-miRNA-mRNA networks, none of the state-of-the-art approaches can discriminate the biological level at which the mRNAs involved in the interactions are regulated, avoiding considering potential target mRNAs not regulated at the post-transcriptional level. EasyCircR is a novel R package that combines circRNA detection and reconstruction with post-transcriptional gene expression analysis (exon-intron split analysis) and miRNA response element prediction. The package enables estimation and visualization of circRNA-miRNA-mRNA interactions through an intuitive Shiny application, leveraging the post-transcriptional regulatory nature of circRNA-miRNA relationship and excluding unrealistic regulatory interactions at the biological level. EasyCircR source code, Docker container and user guide are available at: <span><span>https://github.com/InfOmics/EasyCircR</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"188 ","pages":"Article 109846"},"PeriodicalIF":7.0,"publicationDate":"2025-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143471616","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":"Parametric model of the human pinna based on Bézier curves and concave deformations","authors":"Felix Perfler,&nbsp;Florian Pausch,&nbsp;Katharina Pollack,&nbsp;Nicki Holighaus,&nbsp;Piotr Majdak","doi":"10.1016/j.compbiomed.2025.109817","DOIUrl":"10.1016/j.compbiomed.2025.109817","url":null,"abstract":"<div><div>A parametric representation of the complex biological structure of the human pinna is of considerable interest in applications such as the design of ear prostheses, personalization of spatial hearing, and biometric identification. Here, we describe BezierPPM, a parametric pinna model with parameters closely linked to human ear structures. BezierPPM represents the ear geometry as cubic Beziér curves and includes local modifiers of predefined concave areas. We evaluated BezierPPM by manually registering its parameters to 20 ears selected from various databases of digitized ears. The root-mean-square error between the registered and target geometries was on average 1.5 ± 0.2<!--> <!-->mm, and the 2-mm and 1-mm completeness was 87 ± 4% and 66 ± 5%, respectively. This indicates that BezierPPM was capable of representing human pinnae very well. An in-depth analysis showed that most of the inaccuracies were located on the back side of the ear, an area having a rather low relevance for most target applications. To address potential future applications in machine-learning settings, we used BezierPPM to create a database of synthetic pinna geometries and trained a toy-example neural network to estimate BezierPPM parameters from multi-view images of this database. The estimated parameters resulted in estimated pinna geometries with a mean error of 0.3<!--> <!-->mm, indicating that BezierPPM can accurately describe a wide variety of human pinnae, also in machine-learning settings. In summary, our evaluations demonstrate a high potential of BezierPPM for applications requiring a good representation of the relevant parts of pinna geometry, especially when targeting applications in machine-learning settings.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"188 ","pages":"Article 109817"},"PeriodicalIF":7.0,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143454970","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":"Utilizing 12-lead electrocardiogram and machine learning to retrospectively estimate and prospectively predict atrial fibrillation and stroke risk","authors":"Po-Cheng Chang ,&nbsp;Zhi-Yong Liu ,&nbsp;Yu-Chang Huang ,&nbsp;Jung-Sheng Chen ,&nbsp;Chung-Chuan Chou ,&nbsp;Hung-Ta Wo ,&nbsp;Wen-Chen Lee ,&nbsp;Hao-Tien Liu ,&nbsp;Chun-Chieh Wang ,&nbsp;Ching-Heng Lin ,&nbsp;Pei-Hsuan Tung ,&nbsp;Chang-Fu Kuo ,&nbsp;Ming-Shien Wen","doi":"10.1016/j.compbiomed.2025.109871","DOIUrl":"10.1016/j.compbiomed.2025.109871","url":null,"abstract":"<div><h3>Background</h3><div>The stroke risk in patients with subclinical atrial fibrillation (AF) is underestimated. By identifying patients at high risk of embolic stroke, health-care professionals can make more informed decisions regarding anticoagulation treatment to prevent stroke. The main aim of this study was to forecast the risk of AF both retrospectively and prospectively.</div></div><div><h3>Methods</h3><div>The research used a dataset of patients who had received a standard 12-lead electrocardiogram (ECG) at the seven branches of Chang Gung Memorial Hospital between October 2007 and December 2019. Using convolutional neural network (CNN) ECG models, the study classified the risk of AF development both retrospectively and prospectively in 1,776,968 patients by analyzing their 12-lead ECG. The study also examined the risk of stroke, hospitalization for heart failure (HF), myocardial infarction (MI), and death among patients with predicted AF versus that of those with normal sinus rhythm.</div></div><div><h3>Results</h3><div>The CNN models could be used to accurately diagnose AF, assess the risk of past AF episodes, and predict the risk of future AF episodes with high accuracy, as shown by areas under the receiver operating characteristic curve of 0.99, 0.86, and 0.85, respectively. Patients who were estimated to have had past AF or predicted to have future AF were at a higher risk of developing stroke, HF hospitalization, MI, and mortality. The ECGs of patients with predicted AF tended to exhibit lower R-wave amplitudes and flattened T waves. Additionally, we observed that the QRS complexes in leads V1, aVL, and aVR were highly weighted in predicting AF in the CNN models.</div></div><div><h3>Conclusions</h3><div>The CNN models were effective for estimating the past and future risk of AF by analyzing 12-lead ECG. Patients with predicted AF had a higher risk of developing stroke, hospitalization for HF, MI, and death. By using this AF prediction model, physicians may be able to identify patients who should be screened for AF and taking action to prevent stroke and manage cardiovascular risk.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"188 ","pages":"Article 109871"},"PeriodicalIF":7.0,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143454968","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":"Modular dynamics paradigm in biosystems multilevel modeling: Software design and PBPK/PD validation","authors":"Manuel Prado-Velasco","doi":"10.1016/j.compbiomed.2025.109856","DOIUrl":"10.1016/j.compbiomed.2025.109856","url":null,"abstract":"<div><h3>Objective:</h3><div>The development of mechanistic-based modeling and simulation (M&amp;S) tools is essential for advancing our understanding of biological systems. This study presents a novel M&amp;S software tool, Cyborgs Simulator (CybSim), which employs a novel modular modeling paradigm on top of an acausal object-oriented modeling language (OOML)-defined architecture. This paradigm avoids the imposition of hard links between biosystem components and the mechanisms that drive their dynamics, thus facilitating the evolution of the biological model with newly discovered mechanisms.</div></div><div><h3>Methods:</h3><div>Following an examination of the fundamental principles underlying the formal definition of mechanistic models in the field of biosciences, which provides the rationale for the modular dynamics paradigm, a conceptual framework and subsequent computational design of CybSim that supports it are presented. In addition, the description includes pertinent features of CybSim, such as the multi-modeling approach, the separation of biosystems from artificial (machine) components, and their connection to algorithmic blocks. The reliability and accuracy of CybSim are evaluated through the construction and comparison of the predictions of two physiologically based pharmacokinetics (PBPK) models with their published references, in other M&amp;S tools.</div></div><div><h3>Results:</h3><div>The logarithmic absolute errors of bacterial count predictions were below 2 % in almost all scenarios of the aditoprim model in pigs (reference model in Berkeley Madonna 8.3.23), while the mean absolute prediction errors calculated as a function of time were similar to the numerical precision of the integrators (<span><math><mrow><mn>1</mn><msup><mrow><mn>0</mn></mrow><mrow><mo>−</mo><mn>8</mn></mrow></msup><mo>−</mo><mn>1</mn><msup><mrow><mn>0</mn></mrow><mrow><mo>−</mo><mn>7</mn></mrow></msup></mrow></math></span> in all scenarios of the caffeine model in humans (reference model in mrgsolve 1.5.1). PBPK/PD models in CybSim required only one flow-limited tissue for all mechanistic configurations, demonstrating the reliability of the modular modeling paradigm. The validation of CybSim included other essential features such as the incorporation of a module for accessing and predicting of biological–physiological data, an algorithmic system that includes metric blocks and pharmacodynamics, and an artificial systems module.</div></div><div><h3>Conclusion:</h3><div>The study confirms that the modular dynamics paradigm can be implemented under modern acausal OOML M&amp;S tools to facilitate the discovery and addition of new mechanistic knowledge in biosystems models. CybSim is a novel graphical modular modeling tool for biosystems that incorporates this paradigm and has been validated under several scenarios for the PBPK modeling approach.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"188 ","pages":"Article 109856"},"PeriodicalIF":7.0,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143464339","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 predictive study on HCV using automated machine learning models","authors":"Serbun Ufuk Değer,&nbsp;Hakan Can","doi":"10.1016/j.compbiomed.2025.109897","DOIUrl":"10.1016/j.compbiomed.2025.109897","url":null,"abstract":"<div><div>Hepatitis C virus (HCV) infection represents a significant contributor to chronic liver disease on a global scale. The prompt identification and management of HCV are imperative in order to avert complications and to maintain control over the disease. Nowadays, medical decision support systems that incorporate advanced diagnostic methods and effective treatment strategies are of great importance in order to make significant progress in the fight against HCV. Medical decision support systems have undergone a major evolution with the development of computer technologies. In the 2010s, the integration of big data and artificial intelligence technologies into medical decision support systems enabled rapid analysis of patient data. This has created significant synergies in the diagnostic and therapeutic approaches to various diseases. The ever-increasing volume of data on HCV infection offers opportunities to use machine learning techniques to diagnose and predict liver disorders. Although the implementation of machine learning necessitates a degree of proficiency in computer science, which frequently poses a challenge for healthcare practitioners, automated machine learning (AutoML) tools markedly mitigate this obstacle. Such tools empower users to construct highly effective machine learning models without requiring extensive technical expertise. In our investigation concerning HCV prediction, additional features were incorporated into the dataset sourced from the UCI Machine Learning Repository, and class imbalances were rectified. In our study on HCV prediction, which was conducted to address this deficiency, new features were added to the dataset obtained from the UCI Machine Learning Repository to address the deficiencies and inter-class imbalances were corrected. After this process, modeling was performed using 7 AutoML tools and high accuracy rates ranging from 99.29 % to 100 % were obtained. As an important result of this paper, these models may be regarded as a supplementary method for doctors in predicting Hepatitis C and its associated diseases.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"188 ","pages":"Article 109897"},"PeriodicalIF":7.0,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143454974","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 novel computer-aided energy decision-making system improves patient treatment by microwave ablation of thyroid nodule","authors":"Rui Du ,&nbsp;Ranchao Wang ,&nbsp;Hu Xu ,&nbsp;Yuhao Xu ,&nbsp;Zhengdong Fei ,&nbsp;Yifeng Luo ,&nbsp;Xiaolan Zhu ,&nbsp;Yuefeng Li","doi":"10.1016/j.compbiomed.2025.109823","DOIUrl":"10.1016/j.compbiomed.2025.109823","url":null,"abstract":"<div><div>The current basis of microwave ablation (MWA) energy use for thyroid nodules (TN) is inadequate, leading to tissue carbonization, which is strongly associated with complications and poor prognosis. This study aims to devise a novel energy decision-making system to improve the subjective use of energy in current MWA procedures. Data from 916 subjects (1364 TN) across three medical centers were collected. In the first two sets, the single-stitch ablation needle energy (ANE) was calculated by analyzing MWA procedure videos. The causes of TN over-ablation (carbonization) were examined, and the relationship between well-ablated TN and ANE was explored based on TN attributes (volume and Young's modulus). Three-dimensional (3D) reconstruction of TN was performed, and a computer-aided model was constructed to optimize the distribution of the ANE field within the 3D-TN. Subsequently, a novel energy decision-making system was developed and tested. The third set was used for external validation. The cause of TN carbonization was found to be related to the overload of ANE with corrected Young's modulus and the selection of mismatched ablation needle power (ANP). A precise ANE model (Model 1) based on well-ablated TN and a needle-placement model (Model 2) based on the 3D-TN and ANP were subsequently constructed. The coupled new energy decision-making system (Model 1 + 2) demonstrated strong clinical generalization capabilities. In conclusion, this novel energy decision-making system can effectively improve the use of MWA energy, significantly promoting the precise treatment of TN.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"188 ","pages":"Article 109823"},"PeriodicalIF":7.0,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143454973","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":"Utilizing natural language processing for precision prevention of mental health disorders among youth: A systematic review","authors":"Sheriff Tolulope Ibrahim ,&nbsp;Madeline Li ,&nbsp;Jamin Patel ,&nbsp;Tarun Reddy Katapally","doi":"10.1016/j.compbiomed.2025.109859","DOIUrl":"10.1016/j.compbiomed.2025.109859","url":null,"abstract":"<div><h3>Background</h3><div>The global mental health crisis has created barriers to youth mental healthcare, leaving many disorders unaddressed. Precision prevention, which identifies individual risks, offers the potential for tailored interventions. While natural language processing (NLP) has shown promise in the early detection of mental health disorders, no review has examined its role in youth mental health detection. We hypothesize that NLP can improve early detection and personalized care in mental healthcare among youth.</div></div><div><h3>Methodology</h3><div>After screening 1197 articles from 5 databases, 12 papers were included covering six categories: (1) mental health disorders, (2) data sources, (3) NLP objective for mental health detection, (4) annotation and validation techniques, (5) linguistic markers, and (6) performance and evaluation. Study quality was assessed using Hawker's checklist for disparate study designs.</div></div><div><h3>Results</h3><div>Most studies focused on suicide risk (42 %), depression (25 %), and stress (17 %). Social media (42 %) and interviews (33 %) were the most common data sources, with linguistic inquiry and word count and support vector machines frequently used for analysis. While most studies were exploratory, one implemented a real-time tool for detecting mental health risks. Validation methods, including precision and recall metrics, showed strong predictive performance.</div></div><div><h3>Conclusions</h3><div>This review highlights the potential of NLP in youth mental health detection, addressing challenges such as bias, data quality, and ethical concerns. Future research should refine NLP models using diverse, multimodal datasets, addressing data imbalance, and improving real-time detection. Exploring transformer-based models and ensuring ethical, inclusive data handling will be key to advancing NLP-driven interventions.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"188 ","pages":"Article 109859"},"PeriodicalIF":7.0,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143454969","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":"Preserving medical information from doctor’s prescription ensuring relation among the terminology","authors":"Apurba Datta ,&nbsp;Md. Mehedi Hasan ,&nbsp;Niaz Mahmud ,&nbsp;Bilkis Jamal Ferdosi ,&nbsp;Rafiqul Islam ,&nbsp;Ziaur Rahman ,&nbsp;Sk. Tanzir Mehedi","doi":"10.1016/j.compbiomed.2025.109812","DOIUrl":"10.1016/j.compbiomed.2025.109812","url":null,"abstract":"<div><div>Healthcare is a fundamental human right, yet accessing proper healthcare remains a significant challenge. Many patients still rely on physical documents, requiring them to carry all relevant medical records during consultations. Existing methods for extracting data from medical prescriptions have primarily focused on recognizing medication names using manual image annotation or binarization techniques. These approaches often fail to capture detailed prescription information, struggle with multilingual text, and lack the ability to structure medicine-related data comprehensively. To address these limitations, we propose an advanced Electronic Health Record (EHR) system that provides a secure and accessible digital platform for storing and managing patients’ medical histories. Our study implements the best Region of Interest (ROI) detection model using the You Only Look Once (YOLO) framework, achieving 99.6% detection accuracy. The extracted ROI is processed using the best Optical Character Recognition (OCR) technique to digitize prescription data, which is then organized into a structured format within a central database. Furthermore, the system integrates a spell correction algorithm with a 96% accuracy rate to rectify misspelled medication names. Beyond text extraction, the system links corrected medication names with dosages, instructions, and manufacturer information, combining generic and brand details to ensure precise and comprehensive healthcare data management. This integrated solution enhances medication data organization, facilitates better healthcare delivery, and improves patient outcomes by streamlining prescription handling and ensuring accurate medication administration. Our EHR system bridges the gap between physical and digital records, advancing an efficient and reliable healthcare ecosystem.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":"188 ","pages":"Article 109812"},"PeriodicalIF":7.0,"publicationDate":"2025-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143446034","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}