Computer methods and programs in biomedicine最新文献

{"title":"Convolutional long short-term memory neural network integrated with classifier in classifying type of asynchrony breathing in mechanically ventilated patients","authors":"Nur Sa'adah Muhamad Sauki ,&nbsp;Nor Salwa Damanhuri ,&nbsp;Nor Azlan Othman ,&nbsp;Yeong Shiong Chiew ,&nbsp;Belinda Chong Chiew Meng ,&nbsp;Mohd Basri Mat Nor ,&nbsp;J․Geoffrey Chase","doi":"10.1016/j.cmpb.2025.108680","DOIUrl":"10.1016/j.cmpb.2025.108680","url":null,"abstract":"<div><h3>Background and objective</h3><div>Asynchronous breathing (AB) occurs when a mechanically ventilated patient's breathing does not align with the mechanical ventilator (MV). Asynchrony can negatively impact recovery and outcome, and/or hinder MV management. A model-based method to accurately classify different AB types could automate detection and have a measurable clinical impact.</div></div><div><h3>Methods</h3><div>This study presents an approach using a 1-dimensional (1D) of airway pressure data as an input to the convolutional long short-term memory neural network (CNN-LSTM) with a classifier method to classify AB types into three categories: 1) reverse Triggering (RT); 2) premature cycling (PC); and 3) normal breathing (NB), which cover normal breathing and 2 primary forms of AB. Three types of classifier are integrated with the CNN-LSTM model which are random forest (RF), support vector machine (SVM) and logistic regression (LR).</div><div>Clinical data inputs include measured airway pressure from 7 MV patients in IIUM Hospital ICU under informed consent with a total of 4500 breaths. Model performance is first assessed in a k-fold cross-validation assessing accuracy in comparison to the proposed CNN-LSTM integrated with each type of classifier. Then, confusion matrices are used to summarize classification performance for the CNN without classifier, CNN-LSTM without classifier, and CNN-LSTM with each of the 3 classifiers (RF, SVM, LR).</div></div><div><h3>Results and discussion</h3><div>The 1D CNN-LSTM with classifier method achieves 100 % accuracy using 5-fold cross validation. The confusion matrix results showed that the combined CNN-LSTM model with classifier performed better, demostrating higher accuracy, sensitivity, specificity, and F1 score, all exceeding 83.5 % across all three breathing categories. The CNN model without classifier and CNN-LSTM model without classifier displayed comparatively lower performance, with average values of F1 score below 71.8 % for all three breathing categories.</div></div><div><h3>Conclusion</h3><div>The results validate the effectiveness of the CNN-LSTM neural network model with classifier in accurately detecting and classifying the different categories of AB and NB. Overall, this model-based approach has the potential to precisely classify the type of AB and differentiate normal breathing. With this developed model, a better MV management can be provided at the bedside, and these results justify prospective clinical testing.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"263 ","pages":"Article 108680"},"PeriodicalIF":4.9,"publicationDate":"2025-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143471676","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":"In silico tuning of binding selectivity for new SARS-CoV-2 main protease inhibitors","authors":"Feng Wang ,&nbsp;Vladislav Vasilyev","doi":"10.1016/j.cmpb.2025.108678","DOIUrl":"10.1016/j.cmpb.2025.108678","url":null,"abstract":"<div><div>Rapid identification of effective SARS-CoV-2 inhibitors is essential for managing the ongoing pandemic and preparing for future outbreaks. This study aims to develop an efficient computational framework to accelerate pre-screening and optimization of inhibitors through functional group modifications of FDA-approved drugs, Adrafinil and Baicalein, targeting the SARS-CoV-2 main protease (MPro). We introduce MDBinding, a computational drug optimization program designed to enhance the inhibitor screening process by integrating molecular dynamics (MD) simulations. MDBinding systematically identifies inhibitors with improved binding affinities to MPro through functional group modifications, refining lead compound design. Combined with the previously developed PerQMConf module, MDBinding provides a robust in silico framework for rapid drug discovery. This approach significantly reduces the time and cost of inhibitor development while identifying promising candidates for experimental validation. The findings highlight the potential of MDBinding to accelerate antiviral drug discovery and improve the efficiency of computational drug design.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"262 ","pages":"Article 108678"},"PeriodicalIF":4.9,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143474710","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":"Causal associations between scapular morphology and shoulder condition estimated with Bayesian statistics","authors":"Pezhman Eghbali ,&nbsp;Osman Berk Satir ,&nbsp;Fabio Becce ,&nbsp;Patrick Goetti ,&nbsp;Philippe Büchler ,&nbsp;Dominique P. Pioletti ,&nbsp;Alexandre Terrier","doi":"10.1016/j.cmpb.2025.108666","DOIUrl":"10.1016/j.cmpb.2025.108666","url":null,"abstract":"<div><h3>Background and Objective:</h3><div>While there is a reported correlation between shoulder condition and scapular morphology, the precise impact of typical anatomical variables remains a subject of ongoing debate. This study aimed to evaluate this causal association, by emphasizing the importance of scientific modeling before statistical analysis.</div></div><div><h3>Methods:</h3><div>We examined the effect of scapular anatomy on shoulder condition, and conditioning on sex, age, height, and weight. We considered the two most common pathologies: primary osteoarthritis (OA) and cuff tear arthropathy (CTA). We combined the other pathologies into a single category (OTH) and included a control category (CTRL) of adult subjects without pathology. We represented acromion and glenoid morphology by acromion angle (AA), acromion posterior angle (APA), acromion tilt angle (ATA), glenoid inclination angle (GIA), and glenoid version angle (GVA). GVA was negative for posterior orientation. These variables were automatically calculated from CT scans of 396 subjects in the 4 shoulder condition groups by a deep learning model. We applied do-calculus to assess the identifiability of the causal associations and used a multinomial logistic regression Bayesian model to estimate them. To isolate the effect of each anatomical variable on each shoulder condition, we increased it from -2 to 2 z-score while constraining all other variables to their average value, and reported the effect on shoulder condition probability as percentage points (pp) for females and males.</div></div><div><h3>Results:</h3><div>Increasing AA reduced the probability of OA by 44 pp for females and 17 pp for males while increasing the probability of CTA by 36 pp for females and 33 pp for males. Increasing APA raised the probability of OA by 15 pp for females and 4 pp for males and increased the probability of CTA by 12 pp for females and 4 pp for males. Increasing ATA increased the probability of OA by 15 pp for females but decreased it by 25 pp for males, while also raising the probability of CTA by 11 pp for females and 21 pp for males. Increasing GIA decreased the probability of OA by 55 pp for females and 23 pp for males while increasing the probability of CTA by 45 pp for females and 31 pp for males. GVA (more anterior), decreased the probability of OA by 33 pp for females and 63 pp for males. The effects of APA and ATA were less important compared to the other variables. Overall, morphological effects were more pronounced for females than for males, except for GVA’s impact on OA.</div></div><div><h3>Conclusions:</h3><div>We developed a Bayesian causal model to answer interventional questions about the scapular anatomy’s effect on shoulder condition. Our results, consistent with clinical knowledge, hold promise for aiding in early pathology detection and optimizing surgical planning within clinical settings.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"263 ","pages":"Article 108666"},"PeriodicalIF":4.9,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143479055","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":"MInfer: Bridging MetaboAnalyst and Jacobian analysis for metabolomic networks","authors":"Jana Schwarzerova ,&nbsp;Erdő Gabor Mate ,&nbsp;Jakub Idkowiak ,&nbsp;Dominika Olesova ,&nbsp;Ales Kvasnicka ,&nbsp;Dana Dobesova ,&nbsp;David Friedecky ,&nbsp;Valentyna Provaznik ,&nbsp;Jozef Skarda ,&nbsp;Wolfram Weckwerth ,&nbsp;Thomas Nägele","doi":"10.1016/j.cmpb.2025.108672","DOIUrl":"10.1016/j.cmpb.2025.108672","url":null,"abstract":"<div><h3>Background and Objective</h3><div>Metabolomic interaction networks provide critical insights into the dynamic relationships between metabolites and their regulatory mechanisms. This study introduces MInfer, a novel computational framework that integrates outputs from MetaboAnalyst, a widely used metabolomic analysis tool, with Jacobian analysis to enhance the derivation and interpretation of these networks.</div></div><div><h3>Methods</h3><div>MInfer combines the comprehensive data processing capabilities of MetaboAnalyst with the mathematical modeling power of Jacobian analysis. This framework was applied to various metabolomic datasets, employing advanced statistical tests to construct interaction networks and identify key metabolic pathways.</div></div><div><h3>Results</h3><div>The application of MInfer revealed significant metabolic pathways and potential regulatory mechanisms across multiple datasets. The framework demonstrated high precision, sensitivity, and specificity in identifying interactions, enabling robust network interpretations.</div></div><div><h3>Conclusions</h3><div>MInfer enhances the interpretation of metabolomic data by providing detailed interaction networks and uncovering key regulatory insights. This tool holds significant potential for advancing the study of complex biological systems.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"263 ","pages":"Article 108672"},"PeriodicalIF":4.9,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143473905","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 Markov Chain methodology for care pathway mapping using health insurance data, a study case on pediatric TBI","authors":"Viktor-Jan De Deken,&nbsp;Wilfried Cools,&nbsp;Helena Van Deynse,&nbsp;Koen Putman,&nbsp;Kurt Barbé","doi":"10.1016/j.cmpb.2025.108659","DOIUrl":"10.1016/j.cmpb.2025.108659","url":null,"abstract":"<div><h3>Background</h3><div>Care pathways are increasingly used in healthcare systems globally to guide patient care and improve outcomes. These pathways offer a structured approach to managing patient care processes, potentially reducing costs and enhancing efficiency. However, the dynamic and complex nature of healthcare presents challenges in analyzing and improving these pathways, particularly due to the unique and varied patient journeys. This study focuses on the use of administrative data to map care pathways for pediatric Traumatic Brain Injury (TBI) patients, a population significantly impacted by high mortality and disability rates.</div></div><div><h3>Objective</h3><div>The objective of this research is to map and analyze care pathways using a novel methodology inspired by Hidden Markov chains. The study aims to overcome challenges in analyzing the dynamic and complex nature of the healthcare processes, particularly in a heterogeneous patient population. By using administrative data, the goal is to provide valuable insights into care pathways of these patients.</div></div><div><h3>Methods</h3><div>The study utilizes a study case dataset comprising of 4074 children admitted to Belgian hospitals for TBI in 2016, with administrative data encompassing healthcare services up to one-year post-TBI. The proposed methodology involves representing care pathways as Hidden Markov chains, where the transition between states is determined by the current medical treatment. Hierarchical clustering based on similarity of care paths, volume, and median timepoint is applied to identify subpopulations.</div></div><div><h3>Results</h3><div>Hierarchical clustering reveals distinct clusters, each characterized by unique care pathways. The clusters show variations in the length of care pathways, proportion of mild to severe cases, and vary with unique treatment events. Visualization of these pathways provides a comprehensive understanding of the treatment patterns within each cluster.</div></div><div><h3>Conclusion</h3><div>The study introduces a novel methodology for mapping care pathways. Uncovering these different care pathways enhances the understanding of the variation in care and might lead to improving the quality of care received by patients.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"263 ","pages":"Article 108659"},"PeriodicalIF":4.9,"publicationDate":"2025-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143454643","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":"Towards clinical prediction with transparency: An explainable AI approach to survival modelling in residential aged care","authors":"Teo Susnjak,&nbsp;Elise Griffin","doi":"10.1016/j.cmpb.2025.108653","DOIUrl":"10.1016/j.cmpb.2025.108653","url":null,"abstract":"<div><h3>Background and Objective:</h3><div>Scalable, flexible and highly interpretable tools for predicting mortality in residential aged care facilities for the purpose of informing and optimizing palliative care decisions, do not exist. This study is the first and most comprehensive work applying machine learning to address this need while seeking to offer a transformative approach to integrating AI into palliative care decision-making. The objective is to predict survival in elderly individuals six months post-admission to residential aged care facilities with patient-level interpretability for transparency and support for clinical decision-making for palliative care options.</div></div><div><h3>Methods:</h3><div>Data from 11,944 residents across 40 facilities, with a novel combination of 18 features was used to develop predictive models, comparing standard approaches like Cox Proportional Hazards, Ridge and Lasso Regression with machine learning algorithms, Gradient Boosting (GB) and Random Survival Forest. Model calibration was performed together with ROC and a suite of evaluation metrics to analyze results. Explainable AI (XAI) tools were used to demonstrate both the cohort-level and patient-level model interpretability to enable transparency in the clinical usage of the models. TRIPOD reporting guidelines were followed, with model parameters and code provided publicly.</div></div><div><h3>Results:</h3><div>GB was the top performer with a Dynamic AUROC of 0.746 and a Concordance Index of 0.716 for six-month survival prediction. Explainable AI tools provided insights into key features such as comorbidities, cognitive impairment, and nutritional status, revealing their impact on survival outcomes and interactions that inform clinical decision-making. The calibrated model showed near-optimal performance with adjustable clinically relevant thresholds. The integration of XAI tools proved effective in enhancing the transparency and trustworthiness of predictions, offering actionable insights that support informed and ethically responsible end-of-life (EoL) care decisions in aged care settings.</div></div><div><h3>Conclusion:</h3><div>This study successfully applied machine learning to create viable survival models for aged care residents, demonstrating their usability for clinical settings via a suite of interpretable tools. The findings support the introduction into clinical trials of machine learning with explainable AI tools in geriatric medicine for mortality prediction to enhance the quality of EoL care and informed discussions regarding palliative care.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"263 ","pages":"Article 108653"},"PeriodicalIF":4.9,"publicationDate":"2025-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143427667","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":"A novel endoscopic posterior cervical decompression and interbody fusion technique: Feasibility and biomechanical analysis","authors":"Guangnan Yang ,&nbsp;Yiwei Ding ,&nbsp;Jiang Liu ,&nbsp;Rigbat Rozi ,&nbsp;Zhili Ding ,&nbsp;Tusheng Li ,&nbsp;Qiang Jiang ,&nbsp;Hanshuo Zhang ,&nbsp;Jingbo Ma ,&nbsp;Jiaheng Han ,&nbsp;Yu Ding","doi":"10.1016/j.cmpb.2025.108676","DOIUrl":"10.1016/j.cmpb.2025.108676","url":null,"abstract":"<div><h3>Background and objective</h3><div>Cervical decompression and fusion, the primary surgical techniques for treating degenerative cervical myelopathy, is traditionally performed using interbody fusion through an anterior approach. There are no reported cases of cage placement performed via a posterior cervical approach under endoscopy. This study investigates a novel posterior interbody fusion technique using a newly designed split cage and validates its feasibility through computer simulations.</div></div><div><h3>Methods</h3><div>Anatomical parameters of the posterior cervical safe area (PCSA) were analyzed, and a split interbody fusion cage was designed based on the anatomical parameters for endoscopic posterior cervical decompression and interbody fusion (Endo-PCDIF) surgery. Based on a validated intact C3-C7 cervical model, decompression-alone and Endo-PCDIF models were established via simulating operations, and comparisons were conducted among these models regarding the range of motions (ROMs), displacement, and stress distribution under the different motion conditions.</div></div><div><h3>Results</h3><div>PCSA is surrounded by the dural sac, nerve roots, vertebral artery, and pedicle. Ideal operating space for Endo-PCDIF was achieved by grinding the partial osseous structure. After performing decompression-alone, ROMs at the operational segment increased significantly compared to the pre-operation (80%, 12%, 34%, 24%, 25%, and 10%). Endo-PCDIF reduced ROMs at the operational segment by 49%, 32%, 46%, 42%, 52%, and 39% compared to the decompression-alone. The split cage exhibited minimal displacement and no abnormal stress distribution was observed.</div></div><div><h3>Conclusions</h3><div>PCSA is a crucial surgical pathway for operation at ventral area of dural sac during posterior cervical endoscopy. Endo-PCDIF effectively maintained stability at the operational segment and reduced the biomechanical influence result in adjacent segments.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"262 ","pages":"Article 108676"},"PeriodicalIF":4.9,"publicationDate":"2025-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143444335","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":"Nonlinear dose-response relationship in tDCS-induced brain network synchrony: A resting-state whole-brain model analysis","authors":"Hongyuan Shao ,&nbsp;Guanghua Gu ,&nbsp;Xiaonan Guo ,&nbsp;Xiaoli Li ,&nbsp;Dong Cui","doi":"10.1016/j.cmpb.2025.108675","DOIUrl":"10.1016/j.cmpb.2025.108675","url":null,"abstract":"<div><h3>Background</h3><div>Transcranial Direct Current Stimulation (tDCS) is a non-invasive neuroregulation technique that influences brain dynamics, widely used to enhance cognitive abilities, treat neurological disorders, and aid rehabilitation. With the advancement of computational neuroscience, dynamic modeling analysis has become an important tool for understanding the mechanisms of tDCS.</div></div><div><h3>Methods</h3><div>In this study, we constructed a resting-state whole-brain model, similar to the human brain. By simulating tDCS, we analyzed its effects at different intensities on the whole-brain model. We used various electrophysiological measures to assess the impact of tDCS on brain functional networks and electrophysiological characteristics. In addition, we analyzed the network structures influenced by different tDCS intensities using graph theory measures and the small-world index. Finally, we analyzed the factors that could influence the observed phenomena.</div></div><div><h3>Results</h3><div>The results indicate that within a certain range, tDCS can enhance the synchronicity of brain functional networks; however, excessive intensity results in a significant reduction in the benefits. We observed that electrical stimulation induces complex electrophysiological activities across widespread brain regions through network propagation. Networks influenced by low tDCS intensity achieve optimal states in graph theory metrics. Conversely, high tDCS intensity damages network structures, reducing information transmission efficiency. Finally, we found that these phenomena are closely related to the unique physiological structure of the human brain.</div></div><div><h3>Conclusions</h3><div>This study demonstrates a nonlinear dose-response relationship, revealing that network synchrony achieves optimal states only at appropriate tDCS intensities. This research provides theoretical support for the clinical application of tDCS and scientific guidance for selecting the most effective stimulation protocols.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"263 ","pages":"Article 108675"},"PeriodicalIF":4.9,"publicationDate":"2025-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143454642","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":"MIRA: Myocardial insulin resistance app for clinical practice","authors":"Queralt Martín-Saladich ,&nbsp;Rafael Simó ,&nbsp;José Raul Herance ,&nbsp;Miguel A. González Ballester","doi":"10.1016/j.cmpb.2025.108674","DOIUrl":"10.1016/j.cmpb.2025.108674","url":null,"abstract":"<div><h3>Background and Objective</h3><div>Type 2 diabetes (T2D) is a prevalent disease characterized by insulin resistance (IR), leading to energy disruptions in myocardial cells and increasing cardiovascular (CV) risk. Current diagnostic methods are either systemic, thus lacking tissue-specific information, or invasive. The hyperinsulinemic euglycemic clamp (HEC) combined with [¹⁸F]FDG-PET images, only used in clinical trials, allow to assess regional IR and identify phenotypes within T2D, linking myocardial IR to higher CV risk. However, phenotyping is not easily accessible, creating a need for alternative assessment tools. Thus, we propose a myocardial IR model to address these gaps and improve T2D management.</div></div><div><h3>Methods</h3><div>The study included forty-two patients with T2D who enrolled in a clinical trial (NCT02248311) and who underwent biochemical analyses, anthropometric measurements and [¹⁸F]FDG PET/CT imaging before and after HEC with. Patients were phenotyped into mIR and mIS according to poor or good uptake after HEC, respectively. The proposed predictive model was based on stepwise regression including feature selection to provide an estimate of myocardial IS and thus IR=1/IS by using biochemical parameters in T2D. A software application, the myocardial IR app (MIRA), was developed using MATLAB.</div></div><div><h3>Results</h3><div>MIRA was developed as a myocardial IR estimator (R²=0.97, p=7.1 × 10^–7, error=1.24) for patients with T2D. Moreover, since HEC is not allowed in rutinary clinical practice, the application includes a prediction of the expected myocardial HEC [¹⁸F]FDG uptake from baseline uptake (r=0.52, p=5 × 10^–4, R²=0.60). The app also yields the patient's phenotype, either mIR or mIS, according to poor or good uptake after HEC. Enhanced CV risk exposure due to altered T2D biomarkers and associated to mIR is also provided with highlighted features.</div></div><div><h3>Conclusions</h3><div>We hereby present MIRA, a myocardial IR calculation app to manage myocardial-specific affectation in T2D, as well as to provide with patient phenotyping and CV risk assessment.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"263 ","pages":"Article 108674"},"PeriodicalIF":4.9,"publicationDate":"2025-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143445255","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":"3D velocity and pressure field reconstruction in the cardiac left ventricle via physics informed neural network from echocardiography guided by 3D color Doppler","authors":"Hong Shen Wong ,&nbsp;Wei Xuan Chan ,&nbsp;Wenbin Mao ,&nbsp;Choon Hwai Yap","doi":"10.1016/j.cmpb.2025.108671","DOIUrl":"10.1016/j.cmpb.2025.108671","url":null,"abstract":"<div><div>Fluid dynamics of the heart chamber can provide critical biological cues for understanding cardiac health and disease and have the potential for supporting diagnosis and prognosis. However, directly acquiring fluid dynamics information from clinical imaging remains challenging, as they are often noisy and have limited resolution, preventing accurate detailed fluid dynamics analysis. Image-based flow simulations offer high detail but are typically difficult to align with clinical velocity measurements, and as a result, may not accurately depict true fluid dynamics. Inverse-computing velocity fields from images via intra-ventricular flow mapping (VFM) has been reported, but it can become inaccurate when faced with missing or noisy measurement data, which is common with modalities such as ultrasound. Here, we propose a physics-informed neural network (PINN) framework that can accurately reconstruct detailed 3D flow fields of the cardiac left ventricle within a localized time window, using supervision from color Doppler measurements, despite their low resolution and signal-to-noise ratio. This framework couples PINN solvers at consecutive time frames with discrete temporal numerical differentiation and is thus named the \"Coupled Sequential Frame PINN\" or CSF-PINN. We used image-based flow simulations of fetal and adult hearts to generate synthetic color Doppler velocity data at different spatial and temporal resolution for testing the framework. Results show that CSF-PINN can accurately predict high levels of fluid dynamics details, including flow patterns, intraventricular pressure gradients, vorticity structures, and energy losses. CSF-PINN outperforms vanilla PINN in both accuracy and computational efficiency, however, its accuracy is more limited for velocity-gradient-dependent parameters, such as vorticity and wall shear stress (WSS) magnitude. CSF-PINN's accuracy is maintained even when color Doppler velocity data are spatially and temporally sparse and noisy, and when complex motions of the mitral valve are modelled. These are scenarios in which previous methodologies, including image-based flow simulations and VFM, have struggled. Additionally, we propose a scheme for advancing fluid dynamics predictions to subsequent time windows by using training from the previous time window to initialize networks for the subsequent window, further minimizing errors.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"263 ","pages":"Article 108671"},"PeriodicalIF":4.9,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143473903","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}