Pub Date : 2024-09-28DOI: 10.1016/j.compbiomed.2024.109211
During the COVID-19 pandemic, the analysis of patient data has become a cornerstone for developing effective public health strategies. This study leverages a dataset comprising over 10,000 anonymized patient records from various leading medical institutions to predict COVID-19 patient age groups using a suite of statistical and machine learning techniques. Initially, extensive statistical tests including ANOVA and t-tests were utilized to assess relationships among demographic and symptomatic variables. The study then employed machine learning models such as Decision Tree, Naïve Bayes, KNN, Gradient Boosted Trees, Support Vector Machine, and Random Forest, with rigorous data preprocessing to enhance model accuracy. Further improvements were sought through ensemble methods; bagging, boosting, and stacking. Our findings indicate strong associations between key symptoms and patient age groups, with ensemble methods significantly enhancing model accuracy. Specifically, stacking applied with random forest as a meta leaner exhibited the highest accuracy (0.7054). In addition, the implementation of stacking techniques notably improved the performance of K-Nearest Neighbors (from 0.529 to 0.63) and Naïve Bayes (from 0.554 to 0.622) and demonstrated the most successful prediction method. The study aimed to understand the number of symptoms identified in COVID-19 patients and their association with different age groups. The results can assist doctors and higher authorities in improving treatment strategies. Additionally, several decision-making techniques can be applied during pandemic, tailored to specific age groups, such as resource allocation, medicine availability, vaccine development, and treatment strategies. The integration of these predictive models into clinical settings could support real-time public health responses and targeted intervention strategies.
{"title":"COVID-19 from symptoms to prediction: A statistical and machine learning approach","authors":"","doi":"10.1016/j.compbiomed.2024.109211","DOIUrl":"10.1016/j.compbiomed.2024.109211","url":null,"abstract":"<div><div>During the COVID-19 pandemic, the analysis of patient data has become a cornerstone for developing effective public health strategies. This study leverages a dataset comprising over 10,000 anonymized patient records from various leading medical institutions to predict COVID-19 patient age groups using a suite of statistical and machine learning techniques. Initially, extensive statistical tests including ANOVA and t-tests were utilized to assess relationships among demographic and symptomatic variables. The study then employed machine learning models such as Decision Tree, Naïve Bayes, KNN, Gradient Boosted Trees, Support Vector Machine, and Random Forest, with rigorous data preprocessing to enhance model accuracy. Further improvements were sought through ensemble methods; bagging, boosting, and stacking. Our findings indicate strong associations between key symptoms and patient age groups, with ensemble methods significantly enhancing model accuracy. Specifically, stacking applied with random forest as a meta leaner exhibited the highest accuracy (0.7054). In addition, the implementation of stacking techniques notably improved the performance of K-Nearest Neighbors (from 0.529 to 0.63) and Naïve Bayes (from 0.554 to 0.622) and demonstrated the most successful prediction method. The study aimed to understand the number of symptoms identified in COVID-19 patients and their association with different age groups. The results can assist doctors and higher authorities in improving treatment strategies. Additionally, several decision-making techniques can be applied during pandemic, tailored to specific age groups, such as resource allocation, medicine availability, vaccine development, and treatment strategies. The integration of these predictive models into clinical settings could support real-time public health responses and targeted intervention strategies.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":null,"pages":null},"PeriodicalIF":7.0,"publicationDate":"2024-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142343047","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}
Pub Date : 2024-09-28DOI: 10.1016/j.compbiomed.2024.109168
Liver disease diagnosis is pivotal for effective patient management, and machine learning techniques have shown promise in this domain. In this study, we investigate the impact of Polynomial-SHapley Additive exPlanations analysis on enhancing the performance and interpretability of machine learning models for liver disease classification. Our results demonstrate significant improvements in accuracy, precision, recall, F1_score, and Matthews correlation coefficient across various algorithms when polynomial- SHapley Additive exPlanations analysis is applied. Specifically, the Light Gradient Boosting Machine model achieves exceptional performance with 100 % accuracy in both scenarios. Furthermore, by comparing the results obtained with and without the approach, we observe substantial differences in the performance, highlighting the importance of incorporating Polynomial-SHapley Additive exPlanations analysis for improved model performance. The Polynomial features and SHapley Additive exPlanations values also enhance the interpretability of machine learning models by capturing complex feature interactions, enabling users to gain deeper insights into the underlying mechanisms driving the diagnosis. Moreover, data rebalancing using Synthetic Minority Over-sampling Technique and parameter tuning were employed to optimize the performance of the models. These findings underscore the significance of employing this analytical approach in machine-learning-based diagnostic systems for liver diseases, offering superior performance and enhanced interpretability for informed decision-making in clinical practice.
{"title":"Polynomial-SHAP analysis of liver disease markers for capturing of complex feature interactions in machine learning models","authors":"","doi":"10.1016/j.compbiomed.2024.109168","DOIUrl":"10.1016/j.compbiomed.2024.109168","url":null,"abstract":"<div><div>Liver disease diagnosis is pivotal for effective patient management, and machine learning techniques have shown promise in this domain. In this study, we investigate the impact of Polynomial-SHapley Additive exPlanations analysis on enhancing the performance and interpretability of machine learning models for liver disease classification. Our results demonstrate significant improvements in accuracy, precision, recall, F1_score, and Matthews correlation coefficient across various algorithms when polynomial- SHapley Additive exPlanations analysis is applied. Specifically, the Light Gradient Boosting Machine model achieves exceptional performance with 100 % accuracy in both scenarios. Furthermore, by comparing the results obtained with and without the approach, we observe substantial differences in the performance, highlighting the importance of incorporating Polynomial-SHapley Additive exPlanations analysis for improved model performance. The Polynomial features and SHapley Additive exPlanations values also enhance the interpretability of machine learning models by capturing complex feature interactions, enabling users to gain deeper insights into the underlying mechanisms driving the diagnosis. Moreover, data rebalancing using Synthetic Minority Over-sampling Technique and parameter tuning were employed to optimize the performance of the models. These findings underscore the significance of employing this analytical approach in machine-learning-based diagnostic systems for liver diseases, offering superior performance and enhanced interpretability for informed decision-making in clinical practice.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":null,"pages":null},"PeriodicalIF":7.0,"publicationDate":"2024-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142343051","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}
Pub Date : 2024-09-28DOI: 10.1016/j.compbiomed.2024.109201
Recent advances in machine learning and deep learning have presented new opportunities for learning to localize the origin of ventricular activation from 12-lead electrocardiograms (ECGs), an important step in guiding ablation therapies for ventricular tachycardia. Passively learning from population data is faced with challenges due to significant variations among subjects, and building a patient-specific model raises the open question of where to select pace-mapping data for training. This work introduces BOATMAP, a novel active learning approach designed to provide clinicians with interpretable guidance that progressively assists in locating the origin of ventricular activation from 12-lead ECGs. BOATMAP inverts the input–output relationship in traditional machine learning solutions to this problem and learns the similarity between a target ECG and a paced ECG as a function of the pacing site coordinates. Using Gaussian processes (GP) as a surrogate model, BOATMAP iteratively refines the estimated similarity landscape while providing suggestions to clinicians regarding the next optimal pacing site. Furthermore, it can incorporate constraints to avoid suggesting pacing in non-viable regions such as the core of the myocardial scar. Tested in a realistic simulation environment in various heart geometries and tissue properties, BOATMAP demonstrated the ability to accurately localize the origin of activation, achieving an average localization accuracy of with only pacing sites. BOATMAP offers real-time interpretable guidance for accurate localization and enhancing clinical decision-making.
{"title":"BOATMAP: Bayesian Optimization Active Targeting for Monomorphic Arrhythmia Pace-mapping","authors":"","doi":"10.1016/j.compbiomed.2024.109201","DOIUrl":"10.1016/j.compbiomed.2024.109201","url":null,"abstract":"<div><div>Recent advances in machine learning and deep learning have presented new opportunities for learning to localize the origin of ventricular activation from 12-lead electrocardiograms (ECGs), an important step in guiding ablation therapies for ventricular tachycardia. Passively learning from population data is faced with challenges due to significant variations among subjects, and building a patient-specific model raises the open question of where to select pace-mapping data for training. This work introduces BOATMAP, a novel active learning approach designed to provide clinicians with interpretable guidance that progressively assists in locating the origin of ventricular activation from 12-lead ECGs. BOATMAP inverts the input–output relationship in traditional machine learning solutions to this problem and learns the similarity between a target ECG and a paced ECG as a function of the pacing site coordinates. Using Gaussian processes (GP) as a surrogate model, BOATMAP iteratively refines the estimated similarity landscape while providing suggestions to clinicians regarding the next optimal pacing site. Furthermore, it can incorporate constraints to avoid suggesting pacing in non-viable regions such as the core of the myocardial scar. Tested in a realistic simulation environment in various heart geometries and tissue properties, BOATMAP demonstrated the ability to accurately localize the origin of activation, achieving an average localization accuracy of <span><math><mrow><mn>3</mn><mo>.</mo><mn>9</mn><mo>±</mo><mn>3</mn><mo>.</mo><mn>6</mn><mspace></mspace><mi>mm</mi></mrow></math></span> with only <span><math><mrow><mn>8</mn><mo>.</mo><mn>0</mn><mo>±</mo><mn>4</mn><mo>.</mo><mn>0</mn></mrow></math></span> pacing sites. BOATMAP offers real-time interpretable guidance for accurate localization and enhancing clinical decision-making.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":null,"pages":null},"PeriodicalIF":7.0,"publicationDate":"2024-09-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142343046","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}
Pub Date : 2024-09-27DOI: 10.1016/j.compbiomed.2024.109194
The human aorta undergoes complex morphologic changes that mirror the evolution of disease. Finite element analysis (FEA) enables the prediction of aortic pathologic states, but the absence of a biomechanical understanding hinders the applicability of this computational tool. We incorporate geometric information from computed tomography angiography (CTA) imaging scans into FEA to predict a trajectory of future geometries for four aortic disease patients. Through defining a geometric correspondence between two patient scans separated in time, a patient-specific FEA model can recreate the deformation of the aorta between the two time points, showing that pathologic growth drives morphologic heterogeneity. FEA-derived trajectories in a shape-size geometric feature space, which plots the variance of the shape index versus the inverse square root of aortic surface area ( vs. ), quantitatively demonstrate an increase in . This represents a deviation from physiologic shape changes and parallels the true geometric progression of aortic disease patients.
人体主动脉会发生复杂的形态变化，这些变化反映了疾病的演变过程。有限元分析（FEA）可以预测主动脉的病理状态，但由于缺乏对生物力学的了解，这种计算工具的适用性受到了阻碍。我们将计算机断层扫描（CTA）成像扫描的几何信息纳入有限元分析，预测四名主动脉疾病患者未来的几何轨迹。通过定义时间上相隔的两个患者扫描之间的几何对应关系，患者特定的有限元分析模型可以重现两个时间点之间的主动脉变形，显示病理生长驱动了形态异质性。形状大小几何特征空间中的有限元分析衍生轨迹绘制了形状指数方差与主动脉表面积反平方根的关系（δS vs. [公式：见正文]），定量显示了δS的增加。这表明主动脉形状偏离了生理变化，与主动脉疾病患者的真实几何进展相似。
{"title":"Temporal geometric mapping defines morphoelastic growth model of Type B aortic dissection evolution","authors":"","doi":"10.1016/j.compbiomed.2024.109194","DOIUrl":"10.1016/j.compbiomed.2024.109194","url":null,"abstract":"<div><div>The human aorta undergoes complex morphologic changes that mirror the evolution of disease. Finite element analysis (FEA) enables the prediction of aortic pathologic states, but the absence of a biomechanical understanding hinders the applicability of this computational tool. We incorporate geometric information from computed tomography angiography (CTA) imaging scans into FEA to predict a trajectory of future geometries for four aortic disease patients. Through defining a geometric correspondence between two patient scans separated in time, a patient-specific FEA model can recreate the deformation of the aorta between the two time points, showing that pathologic growth drives morphologic heterogeneity. FEA-derived trajectories in a shape-size geometric feature space, which plots the variance of the shape index versus the inverse square root of aortic surface area (<span><math><mrow><mi>δ</mi><mi>S</mi></mrow></math></span> vs. <span><math><msup><mrow><msqrt><mrow><msub><mrow><mi>A</mi></mrow><mrow><mi>T</mi></mrow></msub></mrow></msqrt></mrow><mrow><mo>−</mo><mn>1</mn></mrow></msup></math></span>), quantitatively demonstrate an increase in <span><math><mrow><mi>δ</mi><mi>S</mi></mrow></math></span>. This represents a deviation from physiologic shape changes and parallels the true geometric progression of aortic disease patients.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":null,"pages":null},"PeriodicalIF":7.0,"publicationDate":"2024-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142343055","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}
Pub Date : 2024-09-27DOI: 10.1016/j.compbiomed.2024.109182
Polyp segmentation remains challenging for two reasons: (a) the size and shape of colon polyps are variable and diverse; (b) the distinction between polyps and mucosa is not obvious. To solve the above two challenging problems and enhance the generalization ability of segmentation method, we propose the Localized Transformer Fusion with Balanced Constraint (BCL-Former) for Polyp Segmentation. In BCL-Former, the Strip Local Enhancement module (SLE module) is proposed to capture the enhanced local features. The Progressive Feature Fusion module (PFF module) is presented to make the feature aggregation smoother and eliminate the difference between high-level and low-level features. Moreover, the Tversky-based Appropriate Constrained Loss (TacLoss) is proposed to achieve the balance and constraint between True Positives and False Negatives, improving the ability to generalize across datasets. Extensive experiments are conducted on four benchmark datasets. Results show that our proposed method achieves state-of-the-art performance in both segmentation precision and generalization ability. Also, the proposed method is 5%–8% faster than the benchmark method in training and inference. The code is available at: https://github.com/sjc-lbj/BCL-Former.
{"title":"BCL-Former: Localized Transformer Fusion with Balanced Constraint for polyp image segmentation","authors":"","doi":"10.1016/j.compbiomed.2024.109182","DOIUrl":"10.1016/j.compbiomed.2024.109182","url":null,"abstract":"<div><div>Polyp segmentation remains challenging for two reasons: (a) the size and shape of colon polyps are variable and diverse; (b) the distinction between polyps and mucosa is not obvious. To solve the above two challenging problems and enhance the generalization ability of segmentation method, we propose the Localized Transformer Fusion with Balanced Constraint (BCL-Former) for Polyp Segmentation. In BCL-Former, the Strip Local Enhancement module (SLE module) is proposed to capture the enhanced local features. The Progressive Feature Fusion module (PFF module) is presented to make the feature aggregation smoother and eliminate the difference between high-level and low-level features. Moreover, the Tversky-based Appropriate Constrained Loss (TacLoss) is proposed to achieve the balance and constraint between True Positives and False Negatives, improving the ability to generalize across datasets. Extensive experiments are conducted on four benchmark datasets. Results show that our proposed method achieves state-of-the-art performance in both segmentation precision and generalization ability. Also, the proposed method is 5%–8% faster than the benchmark method in training and inference. The code is available at: <span><span>https://github.com/sjc-lbj/BCL-Former</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":null,"pages":null},"PeriodicalIF":7.0,"publicationDate":"2024-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142343045","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}
Pub Date : 2024-09-27DOI: 10.1016/j.compbiomed.2024.109185
<div><h3>Objective</h3><div>Develop a time-dependent deep learning model to accurately predict the prognosis of pediatric glioma patients, which can assist clinicians in making precise treatment decisions and reducing patient risk.</div></div><div><h3>Study design</h3><div>The study involved pediatric glioma patients from the Surveillance, Epidemiology, and End Results (SEER) Registry (2000–2018) and Tangdu Hospital in China (2010–2018) within specific time frames. For training, we selected two neural network-based algorithms (DeepSurv, neural multi-task logistic regression [N-MTLR]) and one ensemble learning-based algorithm (random survival forest [RSF]). Additionally, a multivariable Cox proportional hazard (CoxPH) model was developed for comparison purposes. The SEER dataset was randomly divided into 80 % for training and 20 % for testing, while the Tangdu Hospital dataset served as an external validation cohort. Super-parameters were fine-tuned through 1000 repeated random searches and 5-fold cross-validation on the training cohort. Model performance was assessed using the concordance index (C-index), Brier score, and Integrated Brier Score (IBS). Furthermore, the accuracy of predicting survival at 1, 3, and 5 years was evaluated using receiver operating characteristic (ROC) curves, calibration curves, and the area under the ROC curves (AUC). The generalization ability of the model was assessed using the C-index of the Tangdu Hospital data, ROC curves for 1, 3, and 5 years, and AUC values. Lastly, decision curve analysis (DCA) curves for 1, 3, and 5-year time frames are provided to assess the net benefits across different models.</div></div><div><h3>Results</h3><div>A total of 9532 patients with pediatric glioma were included in this study, comprising 9274 patients from the SEER database and 258 patients from Tangdu Hospital in China. The average age at diagnosis was 9.4 ± 6.2 years, and the average survival time was 96 ± 66 months. Through comprehensive performance comparison, the DeepSurv model demonstrated the highest effectiveness, with a C-index of 0.881 on the training cohort. Furthermore, it exhibited excellent accuracy in predicting the 1-year, 3-year, and 5-year survival rates (AUC: 0.903–0.939). Notably, the DeepSurv model also achieved remarkable performance and accuracy on the Chinese dataset (C-index: 0.782, AUC: 0.761–0.852). Comprehensive analysis of DeepSurv, N-MTLR, and RSF revealed that tumor stage, radiotherapy, histological type, tumor size, chemotherapy, age, and surgical method are all significant factors influencing the prognosis of pediatric glioma. Finally, an online version of the pediatric glioma survival predictor based on the DeepSurv model has been established and can be accessed through <span><span>https://pediatricglioma-tangdu.streamlit.app</span><svg><path></path></svg></span>.</div></div><div><h3>Conclusions</h3><div>The DeepSurv model exhibits exceptional efficacy in predicting the survival of pediatric gli
{"title":"Development and validation of a deep learning-based survival prediction model for pediatric glioma patients: A retrospective study using the SEER database and Chinese data","authors":"","doi":"10.1016/j.compbiomed.2024.109185","DOIUrl":"10.1016/j.compbiomed.2024.109185","url":null,"abstract":"<div><h3>Objective</h3><div>Develop a time-dependent deep learning model to accurately predict the prognosis of pediatric glioma patients, which can assist clinicians in making precise treatment decisions and reducing patient risk.</div></div><div><h3>Study design</h3><div>The study involved pediatric glioma patients from the Surveillance, Epidemiology, and End Results (SEER) Registry (2000–2018) and Tangdu Hospital in China (2010–2018) within specific time frames. For training, we selected two neural network-based algorithms (DeepSurv, neural multi-task logistic regression [N-MTLR]) and one ensemble learning-based algorithm (random survival forest [RSF]). Additionally, a multivariable Cox proportional hazard (CoxPH) model was developed for comparison purposes. The SEER dataset was randomly divided into 80 % for training and 20 % for testing, while the Tangdu Hospital dataset served as an external validation cohort. Super-parameters were fine-tuned through 1000 repeated random searches and 5-fold cross-validation on the training cohort. Model performance was assessed using the concordance index (C-index), Brier score, and Integrated Brier Score (IBS). Furthermore, the accuracy of predicting survival at 1, 3, and 5 years was evaluated using receiver operating characteristic (ROC) curves, calibration curves, and the area under the ROC curves (AUC). The generalization ability of the model was assessed using the C-index of the Tangdu Hospital data, ROC curves for 1, 3, and 5 years, and AUC values. Lastly, decision curve analysis (DCA) curves for 1, 3, and 5-year time frames are provided to assess the net benefits across different models.</div></div><div><h3>Results</h3><div>A total of 9532 patients with pediatric glioma were included in this study, comprising 9274 patients from the SEER database and 258 patients from Tangdu Hospital in China. The average age at diagnosis was 9.4 ± 6.2 years, and the average survival time was 96 ± 66 months. Through comprehensive performance comparison, the DeepSurv model demonstrated the highest effectiveness, with a C-index of 0.881 on the training cohort. Furthermore, it exhibited excellent accuracy in predicting the 1-year, 3-year, and 5-year survival rates (AUC: 0.903–0.939). Notably, the DeepSurv model also achieved remarkable performance and accuracy on the Chinese dataset (C-index: 0.782, AUC: 0.761–0.852). Comprehensive analysis of DeepSurv, N-MTLR, and RSF revealed that tumor stage, radiotherapy, histological type, tumor size, chemotherapy, age, and surgical method are all significant factors influencing the prognosis of pediatric glioma. Finally, an online version of the pediatric glioma survival predictor based on the DeepSurv model has been established and can be accessed through <span><span>https://pediatricglioma-tangdu.streamlit.app</span><svg><path></path></svg></span>.</div></div><div><h3>Conclusions</h3><div>The DeepSurv model exhibits exceptional efficacy in predicting the survival of pediatric gli","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":null,"pages":null},"PeriodicalIF":7.0,"publicationDate":"2024-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142343048","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}
Pub Date : 2024-09-27DOI: 10.1016/j.compbiomed.2024.109117
This paper presents a bond graph model for the dynamics of sit-to-stand (SiTSt) and stand-to-sit (StTSi) motions. It is hypothesized that, for these motions, the central nervous system (CNS) controls the trajectory of the centre of mass of the body (COMB). The model comprises two identical submodels: one submodel emulates the working of the CNS, and the other represents the human body. Reference trajectories of the COMB determined through experimentation are input to the submodel representing the working of CNS, which automatically determines the required joint angle trajectories. Based on the required and actual joint angle trajectories, proportional integral derivative controllers at the joints (j-PID) provide the required joint torques to actuate the human body submodel. Simulation results show that during SiTSt or StTSi motions, the centre of mass of the human body submodel follows the commanded trajectories. The joint angle trajectories from the submodel representing the working of CNS closely follow the respective experimental joint angle trajectories. Also, for each motion, joint angles, torques and powers are presented, which agree with earlier studies. These findings provide adequate confidence in proposed hypothesis and indicate the potential of developed model for other biomechanical investigations of SiTSt and StTSi motions.
{"title":"Dynamics of sit-to-stand and stand-to-sit motions based on the trajectory control of the centre of mass of the body: A bond graph approach","authors":"","doi":"10.1016/j.compbiomed.2024.109117","DOIUrl":"10.1016/j.compbiomed.2024.109117","url":null,"abstract":"<div><div>This paper presents a bond graph model for the dynamics of sit-to-stand (SiTSt) and stand-to-sit (StTSi) motions. It is hypothesized that, for these motions, the central nervous system (CNS) controls the trajectory of the centre of mass of the body (COMB). The model comprises two identical submodels: one submodel emulates the working of the CNS, and the other represents the human body. Reference trajectories of the COMB determined through experimentation are input to the submodel representing the working of CNS, which automatically determines the required joint angle trajectories. Based on the required and actual joint angle trajectories, proportional integral derivative controllers at the joints (j-PID) provide the required joint torques to actuate the human body submodel. Simulation results show that during SiTSt or StTSi motions, the centre of mass of the human body submodel follows the commanded trajectories. The joint angle trajectories from the submodel representing the working of CNS closely follow the respective experimental joint angle trajectories. Also, for each motion, joint angles, torques and powers are presented, which agree with earlier studies. These findings provide adequate confidence in proposed hypothesis and indicate the potential of developed model for other biomechanical investigations of SiTSt and StTSi motions.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":null,"pages":null},"PeriodicalIF":7.0,"publicationDate":"2024-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142322595","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}
Pub Date : 2024-09-27DOI: 10.1016/j.compbiomed.2024.109198
The spleen constantly clears altered red blood cells (RBCs) from the circulation, tuning the balance between RBC formation (erythropoiesis) and removal. The retention and elimination of RBCs occur predominantly in the open circulation of the spleen, where RBCs must cross submicron-wide inter-endothelial slits (IES). Several experimental and computational studies have illustrated the role of IES in filtrating the biomechanically and morphologically altered RBCs based on a rigid wall assumption. However, these studies also reported that when the size of IES is close to the lower end of clinically observed sizes (less than 0.5 ), an unphysiologically large pressure difference across the IES is required to drive the passage of normal RBCs, sparking debates on the feasibility of the rigid wall assumption. In this work, We propose two deformable IES models, namely the passive model and the active model, aiming to explore the impact of the deformability of IES on the filtration function of the spleen. In the passive model, we implement the worm-like string model to depict the IES’s deformation as it interacts with blood plasma and allows RBC to traverse. In contrast, the active model involved regulating the IES deformation based on the local pressure surrounding the slit. To demonstrate the validity of the deformable model, we simulate the filtration of RBCs with varied size and stiffness by IES under three scenarios: (1) a single RBC traversing a single slit; (2) a suspension of RBCs traversing an array of slits, mimicking in vitro spleen-on-a-chip experiments; (3) RBC suspension passing through the 3D spleen filtration unit known as’the splenon’. Our simulation results of RBC passing through a single slit show that the deformable IES model offers more accurate predictions of the critical cell surface area to volume ratio that dictate the removal of aged RBCs from circulation compared to prior rigid-wall models. Our biophysical models of the spleen-on-a-chip indicate a hierarchy of filtration function stringency: rigid model passive model active model, providing a possible explanation of the filtration function of IES. We also illustrate that the biophysical model of ‘the splenon’ enables us to replicate the ex vivo experiments involving spleen filtration of malaria-infected RBCs. Taken together, our simulation findings indicate that the deformable IES model could serve as a mesoscopic representation of spleen filtration function closer to physiological reality, addressing questions beyond the scope of current experimental and computational models and enhancing our understanding of the fundamental flow dynamics and mechanical clearance processes within in the human spleen.
{"title":"Red blood cell passage through deformable interendothelial slits in the spleen: Insights into splenic filtration and hemodynamics","authors":"","doi":"10.1016/j.compbiomed.2024.109198","DOIUrl":"10.1016/j.compbiomed.2024.109198","url":null,"abstract":"<div><div>The spleen constantly clears altered red blood cells (RBCs) from the circulation, tuning the balance between RBC formation (erythropoiesis) and removal. The retention and elimination of RBCs occur predominantly in the open circulation of the spleen, where RBCs must cross submicron-wide inter-endothelial slits (IES). Several experimental and computational studies have illustrated the role of IES in filtrating the biomechanically and morphologically altered RBCs based on a rigid wall assumption. However, these studies also reported that when the size of IES is close to the lower end of clinically observed sizes (less than 0.5 <span><math><mrow><mi>μ</mi><mi>m</mi></mrow></math></span>), an unphysiologically large pressure difference across the IES is required to drive the passage of normal RBCs, sparking debates on the feasibility of the rigid wall assumption. In this work, We propose two deformable IES models, namely the passive model and the active model, aiming to explore the impact of the deformability of IES on the filtration function of the spleen. In the passive model, we implement the worm-like string model to depict the IES’s deformation as it interacts with blood plasma and allows RBC to traverse. In contrast, the active model involved regulating the IES deformation based on the local pressure surrounding the slit. To demonstrate the validity of the deformable model, we simulate the filtration of RBCs with varied size and stiffness by IES under three scenarios: (1) a single RBC traversing a single slit; (2) a suspension of RBCs traversing an array of slits, mimicking <em>in vitro</em> spleen-on-a-chip experiments; (3) RBC suspension passing through the 3D spleen filtration unit known as’the splenon’. Our simulation results of RBC passing through a single slit show that the deformable IES model offers more accurate predictions of the critical cell surface area to volume ratio that dictate the removal of aged RBCs from circulation compared to prior rigid-wall models. Our biophysical models of the spleen-on-a-chip indicate a hierarchy of filtration function stringency: rigid model <span><math><mo>></mo></math></span> passive model <span><math><mo>></mo></math></span> active model, providing a possible explanation of the filtration function of IES. We also illustrate that the biophysical model of ‘the splenon’ enables us to replicate the <em>ex vivo</em> experiments involving spleen filtration of malaria-infected RBCs. Taken together, our simulation findings indicate that the deformable IES model could serve as a mesoscopic representation of spleen filtration function closer to physiological reality, addressing questions beyond the scope of current experimental and computational models and enhancing our understanding of the fundamental flow dynamics and mechanical clearance processes within in the human spleen.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":null,"pages":null},"PeriodicalIF":7.0,"publicationDate":"2024-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142343052","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}
Pub Date : 2024-09-27DOI: 10.1016/j.compbiomed.2024.109169
An Electromyography (EMG) based pattern recognition system constitutes various steps of signal processing and control engineering from signal acquisition to real-time control. Efficient control of external devices largely depends on the signal processing steps executed before the final output. This work presents a new approach to signal processing using Motor Unit Action Potential (MUAP) based signal decomposition and segmentation. An MUAP is a neurological response during muscle contraction. Due to the higher contact area of surface electrodes, MUAPs from multiple muscles are captured. An MUAP generated from a single muscle usually has identical waveshapes and similar discharging rates and usually lasts for 8–15 ms. These are known as primary MUAPs. The proposed algorithm identifies and uses the primary observed MUAPs for feature extraction and classification. Firstly, noise signals are eliminated by a determined noise margin, which also separates the active muscle movement signals. Next, a novel MUAP identification algorithm is implemented to detect the MUAP trains. Then, identified primary MUAPs are used to make segments with variable widths to extract feature vectors. Based on the correlation score of all the primary MUAPs, the segmentation is performed, which results in segmentation width varying from 110–200 ms. The achieved segmentation width is lesser than the conventional overlapping and non-overlapping methods — the proposed approach results in a 20 to 50% reduction in the segmentation width. Four different classifiers are tested during the machine learning stage to investigate the performance of the proposed approach. The obtained feature sets are then used to train the Linear Discriminant Analysis (LDA), K-Nearest Neighbor (kNN), Decision Tree (DT), and Random Forest (RF) classifiers. The classifiers are tested with precision, recall, score, and accuracy. The kNN and DT classifiers performed better than the LDA and RF classifiers. The maximum precision and recall are 100% while the maximum achieved accuracy is 98.56%. The comparative results show higher accuracy even at lower segmentation widths than the conventional constant window scheme. The kNN and DT classifiers provide a 5% to 15% increment in accuracy compared to the constant window segmentation-based approach.
{"title":"An efficient approach for EMG controlled pattern recognition system based on MUAP identification and segregation","authors":"","doi":"10.1016/j.compbiomed.2024.109169","DOIUrl":"10.1016/j.compbiomed.2024.109169","url":null,"abstract":"<div><div>An Electromyography (EMG) based pattern recognition system constitutes various steps of signal processing and control engineering from signal acquisition to real-time control. Efficient control of external devices largely depends on the signal processing steps executed before the final output. This work presents a new approach to signal processing using Motor Unit Action Potential (MUAP) based signal decomposition and segmentation. An MUAP is a neurological response during muscle contraction. Due to the higher contact area of surface electrodes, MUAPs from multiple muscles are captured. An MUAP generated from a single muscle usually has identical waveshapes and similar discharging rates and usually lasts for 8–15 ms. These are known as primary MUAPs. The proposed algorithm identifies and uses the primary observed MUAPs for feature extraction and classification. Firstly, noise signals are eliminated by a determined noise margin, which also separates the active muscle movement signals. Next, a novel MUAP identification algorithm is implemented to detect the MUAP trains. Then, identified primary MUAPs are used to make segments with variable widths to extract feature vectors. Based on the correlation score of all the primary MUAPs, the segmentation is performed, which results in segmentation width varying from 110–200 ms. The achieved segmentation width is lesser than the conventional overlapping and non-overlapping methods — the proposed approach results in a 20 to 50% reduction in the segmentation width. Four different classifiers are tested during the machine learning stage to investigate the performance of the proposed approach. The obtained feature sets are then used to train the Linear Discriminant Analysis (LDA), K-Nearest Neighbor (kNN), Decision Tree (DT), and Random Forest (RF) classifiers. The classifiers are tested with precision, recall, <span><math><msub><mrow><mi>F</mi></mrow><mrow><mn>1</mn></mrow></msub></math></span> score, and accuracy. The kNN and DT classifiers performed better than the LDA and RF classifiers. The maximum precision and recall are 100% while the maximum achieved accuracy is 98.56%. The comparative results show higher accuracy even at lower segmentation widths than the conventional constant window scheme. The kNN and DT classifiers provide a 5% to 15% increment in accuracy compared to the constant window segmentation-based approach.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":null,"pages":null},"PeriodicalIF":7.0,"publicationDate":"2024-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142343044","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}
Pub Date : 2024-09-27DOI: 10.1016/j.compbiomed.2024.109210
Background
Over the past decade, the realm of immunotherapy-based combination therapy has witnessed rapid growth for renal cell carcinoma (RCC), however, success has been constrained thus far. This limitation primarily stems from the absence of biomarkers essential for identifying patients likely to derive benefits from such treatments.
Methods
In this study, the immunotherapy-based combination associated score (IBCS) was established using single-sample gene set enrichment analysis (ssGSEA) based on the genes identified in the key modules extracted by weighted correlation network analysis (WGCNA) in the IMmotion151 dataset, a randomized, global phase III trial.
Results
High IBCS patients showed better responses to immunotherapy-based combinations and had longer progression-free survival (PFS). Further transcriptomic analysis revealed that IBCS was negatively correlated to TIDE score, identifying a subset of RCC patients characterized by enrichment of T-effector and moderate cell-cycle/angiogenesis gene expression. Our analysis of hub genes unveiled a novel molecule that could potentially serve as a target antigen in RCC. Validation through multiplex immunofluorescence assays on tissue microarrays (TMAs) containing 180 samples confirmed the pivotal role of this hub gene in immunoregulation. Furthermore, we developed an independent risk score model, which is significant for prognostic evaluation and patient stratification. Notably, we devised a forecasting nomogram using this risk score model, surpassing the IMDC score (a widely accepted risk score for predicting survival in patients undergoing VEGF-targeted therapy) in prognostic accuracy for patients treated with immunotherapy-based combinations.
Conclusion
This study has collectively developed an immunotherapy-based combination associated score, pinpointed effective biomarkers for prognostic and responsiveness of kidney cancer patients to immunotherapy-based combinations, and delved into their potential biological mechanisms, offering promising targets for further exploration.
{"title":"The immunotherapy-based combination associated score as a robust predictor for outcome and response to combination of immunotherapy and VEGF inhibitors in renal cell carcinoma","authors":"","doi":"10.1016/j.compbiomed.2024.109210","DOIUrl":"10.1016/j.compbiomed.2024.109210","url":null,"abstract":"<div><h3>Background</h3><div>Over the past decade, the realm of immunotherapy-based combination therapy has witnessed rapid growth for renal cell carcinoma (RCC), however, success has been constrained thus far. This limitation primarily stems from the absence of biomarkers essential for identifying patients likely to derive benefits from such treatments.</div></div><div><h3>Methods</h3><div>In this study, the immunotherapy-based combination associated score (IBCS) was established using single-sample gene set enrichment analysis (ssGSEA) based on the genes identified in the key modules extracted by weighted correlation network analysis (WGCNA) in the IMmotion151 dataset, a randomized, global phase III trial.</div></div><div><h3>Results</h3><div>High IBCS patients showed better responses to immunotherapy-based combinations and had longer progression-free survival (PFS). Further transcriptomic analysis revealed that IBCS was negatively correlated to TIDE score, identifying a subset of RCC patients characterized by enrichment of T-effector and moderate cell-cycle/angiogenesis gene expression. Our analysis of hub genes unveiled a novel molecule that could potentially serve as a target antigen in RCC. Validation through multiplex immunofluorescence assays on tissue microarrays (TMAs) containing 180 samples confirmed the pivotal role of this hub gene in immunoregulation. Furthermore, we developed an independent risk score model, which is significant for prognostic evaluation and patient stratification. Notably, we devised a forecasting nomogram using this risk score model, surpassing the IMDC score (a widely accepted risk score for predicting survival in patients undergoing VEGF-targeted therapy) in prognostic accuracy for patients treated with immunotherapy-based combinations.</div></div><div><h3>Conclusion</h3><div>This study has collectively developed an immunotherapy-based combination associated score, pinpointed effective biomarkers for prognostic and responsiveness of kidney cancer patients to immunotherapy-based combinations, and delved into their potential biological mechanisms, offering promising targets for further exploration.</div></div>","PeriodicalId":10578,"journal":{"name":"Computers in biology and medicine","volume":null,"pages":null},"PeriodicalIF":7.0,"publicationDate":"2024-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142343056","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}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号