Computer methods and programs in biomedicine最新文献

{"title":"A simulation study of the impact of drug-I_Kr binding mechanisms on biomarkers of proarrhythmic risk reveals a crucial role in reverse use-dependence of action potential duration and a marked influence on the vulnerable window.","authors":"Julio Gomis-Tena, Fernando Escobar, Lucia Romero","doi":"10.1016/j.cmpb.2024.108566","DOIUrl":"https://doi.org/10.1016/j.cmpb.2024.108566","url":null,"abstract":"<p><strong>Background and objective: </strong>In silico human models are being used more and more to predict the potential proarrhythmic risk of compounds. It has been shown that incorporation of the dynamics of drug-hERG channel interactions can have an important impact on the action potential duration (APD) at normal heart rates. Our aim is to investigate the relevance of drug dynamics on other important biomarkers of proarrhythmic risk.</p><p><strong>Methods: </strong>We use the state-of-the-art mathematical models of the cardiac electrophysiological activity to simulate TRIaD biomarkers, namely Triangulation, Reverse use-dependency, electrical Instability of the action potential and Dispersion, together with the vulnerable window to unidirectional block. They were simulated in control conditions and in the presence of an extensive set of 114 in silico I_Kr blockers with different kinetics and affinities to conformational states of the channel and 10 well-known real I_Kr blockers at the concentration leading to a 25 % prolongation of the APD.</p><p><strong>Results: </strong>Our results show that drug binding dynamics to hERG are crucial for the reverse use-dependence of APD, the slope of the APD restitution curve as a function of the root square of the cycle length ranging from 0 to 5.6 ms/ms (2.1 ms/ms in control conditions). The vulnerable window for unidirectional block and the transmural action potential duration dispersion markedly depended on the drug binding mechanisms and kinetics, although to a lesser extent. Virtual drugs led to increments of these two biomarkers from 25 % to 200 %. On the contrary, temporal instability and, beat-to-beat instability, are less dependent on the dynamics of drug binding. The results obtained with the models of real I_Kr blockers are in line with those obtained with the virtual drugs.</p><p><strong>Conclusions: </strong>Our study highlights the importance of considering the drug binding mechanism, as well as the kinetics, to assess the effects of I_Kr blockers. Moreover, adoption of in silico models mimicking these characteristics would contribute to the improvement of the prediction of the proarrhythmic risk of new compounds.</p>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"260 ","pages":"108566"},"PeriodicalIF":4.9,"publicationDate":"2024-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142876309","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":"Influence of vascular embolism level and drug injection rate on thrombolytic therapy of bifurcated femoral vein: Numerical simulation and validation study.","authors":"Xianglei Zhang, Hongyu Cheng, Boyuan Lin, Sisi Li, Hongming Zhou, Mingrui Huang, Jiahao Wu","doi":"10.1016/j.cmpb.2024.108570","DOIUrl":"https://doi.org/10.1016/j.cmpb.2024.108570","url":null,"abstract":"<p><strong>Background and objective: </strong>Deep vein thrombosis (DVT) of the lower limbs is a critical global vascular disease. Accurately assessing and predicting the efficacy of DVT treatment remains a significant challenge due to a lack of understanding of the mechanisms by which the level of patient-specific embolization and the rate of drug injection affect thrombolytic therapy.</p><p><strong>Methods: </strong>In this study, we used the computed tomographic venography (CTV) clinical method to obtain patient-specific parameters, and the flow-solid interaction (FSI) method combined with biochemical response modeling of thrombolysis to analyze patient-specific hemodynamic and biomechanical characteristics and to quantitatively assess the effects of three vessel embolism levels (VEL) versus two drug injection rates (DIR) on bifurcated femoral venous thrombolytic therapy. In addition, we verified the reliability of the simulation results by in vitro thrombolytic therapy experiments.</p><p><strong>Results: </strong>In the bifurcated femoral vein, the state of blood flow, vortex, wall shear stress (WSS), time-averaged wall shear stress (TAWSS), vessel wall pressure, leaflet motion displacement, and valve von Mises stress vary with thrombus size and vessel shape. Venous valves accelerate blood flow, producing a jet phenomenon. From the numerical and experimental results, thrombolytic therapy should select the injection rate according to the severity of the thrombus. Rapid injection restores flow in mild thrombosis, while slow injection ensures gradual drug penetration for serious thrombosis.</p><p><strong>Conclusions: </strong>The present study found that the hemodynamic parameters and biomechanical characteristics explored are closely related to the efficacy of thrombolytic therapy. Both hemodynamic parameters and biomechanical characteristics are affected by blood flow velocity. At the same time, the study also revealed the mechanism of the influence of VTE and DIR on bifurcated venous thrombolytic therapy, to provide a scientific basis for clinicians to formulate more precise treatment strategies.</p>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"260 ","pages":"108570"},"PeriodicalIF":4.9,"publicationDate":"2024-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142885257","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":"Robust multi-modal fusion architecture for medical data with knowledge distillation.","authors":"Muyu Wang, Shiyu Fan, Yichen Li, Binyu Gao, Zhongrang Xie, Hui Chen","doi":"10.1016/j.cmpb.2024.108568","DOIUrl":"https://doi.org/10.1016/j.cmpb.2024.108568","url":null,"abstract":"<p><strong>Background: </strong>The fusion of multi-modal data has been shown to significantly enhance the performance of deep learning models, particularly on medical data. However, missing modalities are common in medical data due to patient specificity, which poses a substantial challenge to the application of these models.</p><p><strong>Objective: </strong>This study aimed to develop a novel and efficient multi-modal fusion framework for medical datasets that maintains consistent performance, even in the absence of one or more modalities.</p><p><strong>Methods: </strong>In this paper, we fused three modalities: chest X-ray radiographs, history of present illness text, and tabular data such as demographics and laboratory tests. A multi-modal fusion module based on pooled bottleneck (PB) attention was proposed in conjunction with knowledge distillation (KD) for enhancing model inference in the case of missing modalities. In addition, we introduced a gradient modulation (GM) method to deal with the unbalanced optimization in multi-modal model training. Finally, we designed comparison and ablation experiments to evaluate the fusion effect, the model robustness to missing modalities, and the contribution of each component (PB, KD, and GM). The evaluation experiments were performed on the MIMIC-IV datasets with the task of predicting in-hospital mortality risk. Model performance was assessed using the area under the receiver operating characteristic curve (AUROC) and the area under the precision-recall curve (AUPRC).</p><p><strong>Results: </strong>The proposed multi-modal fusion framework achieved an AUROC of 0.886 and AUPRC of 0.459, significantly surpassing the performance of baseline models. Even when one or two modalities were missing, our model consistently outperformed the reference models. Ablation of each of the three components resulted in varying degrees of performance degradation, highlighting their distinct contributions to the model's overall effectiveness.</p><p><strong>Conclusions: </strong>This innovative multi-modal fusion architecture has demonstrated robustness to missing modalities, and has shown excellent performance in fusing three medical modalities for patient outcome prediction. This study provides a novel idea for addressing the challenge of missing modalities and has the potential be scaled to additional modalities.</p>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"260 ","pages":"108568"},"PeriodicalIF":4.9,"publicationDate":"2024-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142876321","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":"Multimodal autism detection: Deep hybrid model with improved feature level fusion.","authors":"S Vidivelli, P Padmakumari, P Shanthi","doi":"10.1016/j.cmpb.2024.108492","DOIUrl":"https://doi.org/10.1016/j.cmpb.2024.108492","url":null,"abstract":"<p><strong>Objective: </strong>Social communication difficulties are a characteristic of autism spectrum disorder (ASD), a neurodevelopmental condition. The earlier method of diagnosing autism largely relied on error-prone behavioral observation of symptoms. More intelligence approaches are in progress to diagnose the disorder, which still demands improvement in prediction accuracy. Furthermore, computer-aided design systems based on machine learning algorithms are extremely time-consuming and difficult to design. This study used deep learning techniques to develop a novel autism detection model in order to overcome these problems.</p><p><strong>Methods: </strong>Preprocessing, Features extraction, Improved Feature level Fusion, and Detection are the phases of the suggested autism detection methodology. First, both input modalities will be preprocessed so they are ready for the next stages to be processed. In this case, the facial picture is preprocessed utilizing the Gabor filtering technique, while the input EEG data is preprocessed through Wiener filtering. Subsequently, features are extracted from the modalities, from the EEG signal data, features like Common Spatial Pattern (CSP), Improved Singular Spectrum Entropy, and correlation dimension, are extracted. From the face image, features like the Improved Active Appearance model, Gray-Level Co-occurrence matrix (GLCM) features and Proposed Shape Local Binary Texture (SLBT), as well are retrieved. Following extraction, enhanced feature-level fusion is performed to fuse the features. Ultimately, the combined features are fed into the hybrid model to complete the diagnosis. Models such as Convolutional Neural Networks (CNN) and Bidirectional Gated Recurrent Units (Bi-GRU) are part of the hybrid model.</p><p><strong>Results: </strong>The suggested MADDHM model achieved an accuracy of about 91.03 % regarding EEG and 91.67 % regarding face analysis meanwhile, SVM=87.49 %, DNN=88.59 %, Bi-GRU=90.02 %, LSTM=87.49 % and CNN=82.02 %.</p><p><strong>Conclusion: </strong>As a result, the suggested methodology provides encouraging outcomes and opens up possibilities for early autism detection. The development of such models is not only a technical achievement but also a step forward in providing timely interventions for individuals with ASD.</p>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"260 ","pages":"108492"},"PeriodicalIF":4.9,"publicationDate":"2024-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142863257","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 PACTUS: A gamified electronic device for stroke rehabilitation.","authors":"Juan J Sánchez-Gil, Aurora Sáez-Manzano, Rafael López-Luque, Juan-José Ochoa-Sepúlveda, Eduardo Cañete-Carmona","doi":"10.1016/j.cmpb.2024.108563","DOIUrl":"https://doi.org/10.1016/j.cmpb.2024.108563","url":null,"abstract":"<p><strong>Background and objective: </strong>Stroke remains a significant global concern, particularly as populations age and the incidence of stroke rises. Approximately one third of stroke survivors experience loss of autonomy, often leading to a decreased participation in rehabilitation due to economic, emotional, and social barriers. In response to these challenges, this study introduces PACTUS, an innovative gamified device designed for the rehabilitation of cognitive and motor functions in the upper limbs of patients with post-stroke. PACTUS aims to improve patient motivation and enable precise monitoring of rehabilitation progress by both therapists and patients.</p><p><strong>Methods: </strong>Developed in collaboration with the Institute of Neurosciences at the Red Cross Hospital in Cordoba, the device underwent a pilot pre-test phase with two neurological patients. An observational study was also conducted involving 30 volunteers, including healthy individuals and patients with various neurological disorders, to evaluate the safety, feasibility, acceptability, and potential utility of PACTUS in a broader clinical context.</p><p><strong>Results: </strong>Preliminary findings suggest that PACTUS is a promising tool for stroke rehabilitation, offering a safe and cost-effective method to ensure accurate upper limb movement.</p><p><strong>Conclusions: </strong>Feedback from both patients and therapists highlighted areas of improvement and underscored the device's capacity to adapt to different rehabilitation stages, affirming its broad application potential across diverse neurological conditions.</p>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"260 ","pages":"108563"},"PeriodicalIF":4.9,"publicationDate":"2024-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142871567","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":"Development and validation of an explainable model of brain injury in premature infants: A prospective cohort study.","authors":"Zhijie He, Ruiqi Zhang, Pengfei Qu, Yuxuan Meng, Jinrui Jia, Zhibo Wang, Peng Wang, Yu Ni, Li Shan, Mingzhi Liao, Yajun Li","doi":"10.1016/j.cmpb.2024.108559","DOIUrl":"https://doi.org/10.1016/j.cmpb.2024.108559","url":null,"abstract":"<p><strong>Background: </strong>Preterm brain injury (PBI) is a prevalent complication in preterm infants, leading to the destruction of critical structural and functional brain connections and placing a significant burden on families. The timely detection of PBI is of paramount importance for the prevention and treatment of the condition. However, the absence of specific clinical manifestations in the early stages of PBI renders it susceptible to misdiagnosis and missed diagnoses. Moreover, once it occurs, there is no specific treatment available. The aim of this study was to develop and validate a machine learning (ML) based interpretable model for the early detection of PBI, as well as the assessment of patient-wide and individual risk factors for this disease.</p><p><strong>Methods: </strong>This study utilized a cohort of premature infants provided by Northwest Women's and Children's Hospital in China, comprising medical records of 650 premature infants, spanning from 2019 to 2021. PBI were identified based on cranial magnetic resonance imaging (MRI). Fourteen machine learning models were employed with stratified 10-fold cross-validation method used to evaluate model performance. The Shapley Additive Explanations (SHAP) method was applied for model interpretation. Feature selection methods were used to determine the final model which was validated on the independent test set. Subsequently, risk factors for the entire cohort and individual patients were assessed.</p><p><strong>Results: </strong>Among the fourteen machine learning models, the CatBoost model demonstrated the best discriminative ability. Following feature selection, the final model was constructed using seven features, designated as PBIPred (Preterm Brain Injury Predictor). PBIPred exhibited strong performance in both 10-fold cross-validation and independent test set (AUC = 0.8229) for accurately predicting PBI. The screening for risk factors in the cohort and individuals identified the following variables as positive risk factors for PBI: Mechanical ventilation (MV), Weight, Anemia of prematurity (AOP), Respiratory distress syndrome (RDS), Albumin (ALB), and White blood cell (WBC).</p><p><strong>Availability and implementation: </strong>The PBIPred webserver and PBIPred tool were developed for clinical diagnosis and large-scale local medical record data prediction. They can be accessed freely at http://pbipred.liaolab.net and https://github.com/chikit2077/PBIPred, respectively.</p>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"260 ","pages":"108559"},"PeriodicalIF":4.9,"publicationDate":"2024-12-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142871568","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":"Improving real-time detection of laryngeal lesions in endoscopic images using a decoupled super-resolution enhanced YOLO.","authors":"Chiara Baldini, Lucia Migliorelli, Daniele Berardini, Muhammad Adeel Azam, Claudio Sampieri, Alessandro Ioppi, Rakesh Srivastava, Giorgio Peretti, Leonardo S Mattos","doi":"10.1016/j.cmpb.2024.108539","DOIUrl":"https://doi.org/10.1016/j.cmpb.2024.108539","url":null,"abstract":"<p><strong>Background and objective: </strong>Laryngeal Cancer (LC) constitutes approximately one third of head and neck cancers. Detecting early-stage lesions in this anatomical region is crucial for achieving a high survival rate. However, it poses significant diagnostic challenges owing to the varied appearance of lesions and the need for precise characterization for appropriate clinical management. Conventional diagnostic approaches rely heavily on endoscopic examination, which often requires expert interpretation and may be limited by subjective assessment. Deep learning (DL) approaches offer promising opportunities for automating lesion detection, but their efficacy in handling multi-modal imaging data and accurately localizing small lesions remains a subject of investigation. Furthermore, the clinical domain may largely benefit from the deployment of efficient DL methods that can ensure equitable access to advanced technologies, regardless of the availability of resources that can often be limited. In this study, a DL-based approach, named SRE-YOLO, was introduced to provide real-time assistance to less-experienced personnel during laryngeal assessment, by automatically detecting lesions at different scales from endoscopic White Light (WL) and Narrow-Band Imaging (NBI) images.</p><p><strong>Methods: </strong>During the training, the SRE-YOLO integrates a YOLOv8 nano (YOLOv8n) baseline with a Super-Resolution (SR) branch to enhance lesion detection. This last component is decoupled during inference to preserve the low computational demand of the YOLOv8n baseline. The evaluation was conducted on a multi-center dataset, encompassing diverse laryngeal pathologies and acquisition modalities.</p><p><strong>Results: </strong>The SRE-YOLO method improved the Average Precision (AP_@IoU=0.5) in lesion detection by 5% with respect to the YOLOv8n baseline, while maintaining the inference speed of 58.8 Frames Per Second (FPS). Comparative analyses against state-of-the-art DL methods highlighted the efficacy of the SRE-YOLO approach in balancing detection accuracy, computational efficiency, and real-time applicability.</p><p><strong>Conclusions: </strong>This research underscores the potential of SRE-YOLO in developing efficient DL-driven decision support systems for real-time detection of laryngeal lesions at different scales from both WL and NBI endoscopic data.</p>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"260 ","pages":"108539"},"PeriodicalIF":4.9,"publicationDate":"2024-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142845812","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":"CMR-BENet: A confidence map refinement boundary enhancement network for left ventricular myocardium segmentation.","authors":"Qi Yu, Hongxia Ning, Jinzhu Yang, Chen Li, Yiqiu Qi, Mingjun Qu, Honghe Li, Song Sun, Peng Cao, Chaolu Feng","doi":"10.1016/j.cmpb.2024.108544","DOIUrl":"https://doi.org/10.1016/j.cmpb.2024.108544","url":null,"abstract":"<p><strong>Background and objective: </strong>Left ventricular myocardium segmentation is of great significance for clinical diagnosis, treatment, and prognosis. However, myocardium segmentation is challenging as the medical image quality is disturbed by various factors such as motion, artifacts, and noise. Its accuracy largely depends on the accurate identification of edges and structures. Most existing encoder-decoder based segmentation methods capture limited contextual information and ignore the awareness of myocardial shape and structure, often producing unsatisfactory boundary segmentation results in noisy scenes. Moreover, these methods fail to assess the reliability of the predictions, which is crucial for clinical decisions and applications in medical tasks. Therefore, this study explores how to effectively combine contextual information with myocardial edge structure and confidence maps to improve segmentation performance in an end-to-end network.</p><p><strong>Methods: </strong>In this paper, we propose an end-to-end confidence map refinement boundary enhancement network (CMR-BENet) for left ventricular myocardium segmentation. CMR-BENet has three components: a layer semantic-aware module (LSA), an edge information enhancement module (EIE), and a confidence map-based refinement module (CMR). Specifically, LSA first adaptively fuses high- and low-level semantic information across hierarchical layers to mitigate the bias of single-layer features affected by noise. EIE then improves the edge and structure recognition by designing the edge and mask guidance module (EMG) and the edge structure-aware module (ESA). Finally, CMR provides a simple and efficient way to estimate confidence maps and effectively combines the encoder features to refine the segmentation results.</p><p><strong>Results: </strong>Experiments on two echocardiography datasets and one cardiac MRI dataset show that the proposed CMR-BENet outperforms its rivals in the left ventricular myocardium segmentation task with Dice (DI) of 87.71%, 79.33%, and 89.11%, respectively.</p><p><strong>Conclusion: </strong>This paper utilizes edge information to characterize the shape and structure of the myocardium and introduces learnable confidence maps to evaluate and refine the segmentation results. Our findings provide strong support and reference for physicians in diagnosis and treatment.</p>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"260 ","pages":"108544"},"PeriodicalIF":4.9,"publicationDate":"2024-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142876320","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 predictive models for perioperative major adverse cardiovascular events in patients with stable coronary artery disease undergoing noncardiac surgery.","authors":"Liang Shen, YunPeng Jin, AXiang Pan, Kai Wang, RunZe Ye, YangKai Lin, Safraz Anwar, WeiCong Xia, Min Zhou, XiaoGang Guo","doi":"10.1016/j.cmpb.2024.108561","DOIUrl":"https://doi.org/10.1016/j.cmpb.2024.108561","url":null,"abstract":"&lt;p&gt;&lt;strong&gt;Background and objective: &lt;/strong&gt;Accurate prediction of perioperative major adverse cardiovascular events (MACEs) is crucial, as it not only aids clinicians in comprehensively assessing patients' surgical risks and tailoring personalized surgical and perioperative management plans, but also for information-based shared decision-making with patients and efficient allocation of medical resources. This study developed and validated a machine learning (ML) model using accessible preoperative clinical data to predict perioperative MACEs in stable coronary artery disease (SCAD) patients undergoing noncardiac surgery (NCS).&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Methods: &lt;/strong&gt;We collected data from 9171 adult SCAD patients who underwent NCS and extracted 64 preoperative variables. First, the optimal data imputation, resampling, and feature selection methods were compared and selected to deal with missing data values and imbalances. Then, nine independent machine learning models (logistic regression (LR), support vector machine, Gaussian Naive Bayes (GNB), random forest, gradient boosting decision tree (GBDT), extreme gradient boosting (XGBoost), light gradient boosting machine, categorical boosting (CatBoost), and deep neural network) and a stacking ensemble model were constructed and compared with the validated Revised Cardiac Risk Index's (RCRI) model for predictive performance, which was evaluated using the area under the receiver operating characteristic curve (AUROC), the area under the precision-recall curve (AUPRC), calibration curve, and decision curve analysis (DCA). To reduce overfitting and enhance robustness, we performed hyperparameter tuning and 5-fold cross-validation. Finally, the Shapley additive interpretation (SHAP) method and a partial dependence plot (PDP) were used to determine the optimal ML model.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Results: &lt;/strong&gt;Of the 9,171 patients, 514 (5.6 %) developed MACEs. 24 significant preoperative features were selected for model development and evaluation. All ML models performed well, with AUROC above 0.88 and AUPRC above 0.39, outperforming the AUROC (0.716) and AUPRC (0.185) of RCRI (P &lt; 0.001). The best independent model was XGBoost (AUROC = 0.898, AUPRC = 0.479). The calibration curve accurately predicted the risk of MACEs (Brier score = 0.040), and the DCA results showed that XGBoost had a high net benefit for predicting MACEs. The top-ranked stacking ensemble model, consisting of CatBoost, GBDT, GNB, and LR, proved to be the best (AUROC 0.894, AUPRC 0.485). We identified the top 20 most important features using the mean absolute SHAP values and depicted their effects on model predictions using PDP.&lt;/p&gt;&lt;p&gt;&lt;strong&gt;Conclusions: &lt;/strong&gt;This study combined missing-value imputation, feature screening, unbalanced data processing, and advanced machine learning methods to successfully develop and verify the first ML-based perioperative MACEs prediction model for patients with SCAD, which is more accurate than RCRI and enables ","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"260 ","pages":"108561"},"PeriodicalIF":4.9,"publicationDate":"2024-12-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142871569","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":"M-health with cardiac rehabilitation improves functional capacity: A systematic review with meta-analysis.","authors":"Alessandro Pierucci, Nathália Soares de Almeida, Ítalo Ribeiro Lemes, Vinicíus Flávio Milanez, Crystian Bitencourt Oliveira, Lizziane Kretli Winkelströter, Marilda Aparecida Milanez Morgado de Abreu, Wilson Romero Nakagaki, Ana Clara Campagnolo Gonçalves Toledo","doi":"10.1016/j.cmpb.2024.108551","DOIUrl":"https://doi.org/10.1016/j.cmpb.2024.108551","url":null,"abstract":"<p><strong>Background and objective: </strong>In this systematic review and meta-analysis, we compared the effectiveness of the combined m-health and a cardiac rehabilitation program (CRP) and of CRP alone on functional capacity, adherence to CRP, and management of cardiovascular risk factors in cardiac patients.</p><p><strong>Methods: </strong>Medline, EMBASE, Central, PEDro, and SPORTDiscus were searched, from inception until July 2020, for randomized controlled trials (RCTs) comparing the m-health with CRP combination with CRP alone for adults with heart disease. The PEDro scale and GRADE approach was used to assess methodological and overall quality, respectively. Pooled estimates were calculated using a random-effects model to obtain the mean difference (MD) or standardized mean difference (SMD), and their respective 95 % confidence intervals (95 %CIs).</p><p><strong>Results: </strong>Twenty-two RCTs were eligible. The median risk-of-bias was 6.5/10. CRP with the m-Health intervention was more effective than CRP alone in improving VO₂peak (MD: 1.02 95 %CI 0.50 -1.54) at short-term, and at medium-term follow-up (MD: 0.97, 95 %CI: 0.04 - 1.90. Similarly, CRP and m-Health were superior to CRP alone in increasing self-reported physical activity at short-term (SMD: 0.98, 95 %CI: 0.65 - 1.32] but not at medium-term follow-up (SMD: 0.18, 95 %CI:0.01 to 0.36). Furthermore, supervision of CRP with the m-Health intervention at short-term follow-up and M-Health and semi-supervised CRP - medium-term were more effective in improving VO₂peak respectively (MD: 1.01, 95 %CI: 0.38‒1.64), (MD: 1.49, 95 %CI: 0.09, 2.89), and self-reported physical activity than supervised CRP at short-term (SMD: 0.98, 95 %CI: 0.65‒1.32) medium-term follow-ups (MD: 0.29 95 %CI: 0.12, 0.45].</p><p><strong>Conclusion: </strong>Our review found high-quality evidence that m-health interventions combined with CRP was more effective than CRP alone in improving cardiorespiratory fitness, at the short and medium terms follow-up.</p>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"260 ","pages":"108551"},"PeriodicalIF":4.9,"publicationDate":"2024-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142863076","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}