Pub Date : 2025-02-10DOI: 10.1016/j.cmpb.2025.108646
Rafael Arnay del Arco, Iván Castilla Rodríguez, Marco A. Cabrera Hernández
Background and Objective:
Computerized clinical decision support systems (CDSS) that incorporate the latest scientific evidence are essential for enhancing patient care quality. Such systems typically rely on some kind of model to accurately represent the knowledge required to assess the clinicians. Although the use of complex and computationally demanding simulation models is common in this field, such models limit the potential applications of CDSSs, both in real-time applications and in simulation-in-the-loop optimization tools. This paper presents a case study on Type 1 Diabetes Mellitus (T1DM) to demonstrate the development of surrogate models from health technology assessment models, with the aim of enhancing the potential of CDSSs.
Methods:
The paper details the process of developing machine learning (ML) based surrogate models, including the generation of a dataset for training and testing, and the comparison of different ML techniques. A number of distinct groupings of comorbidities were utilized in the creation of models, which were trained to predict confidence intervals for the time to develop each complication.
Results:
The results of the intersection over union (IoU) analysis between the simulation model output and the surrogate models output for the comorbidities under study were greater than 0.9.
Conclusion:
The study concludes that ML-based surrogate models are a viable solution for real-time clinical decision-making, offering a substantial speedup in execution time compared to traditional simulation models.
{"title":"Improving clinical decision making by creating surrogate models from health technology assessment models: A case study on Type 1 Diabetes Melitus","authors":"Rafael Arnay del Arco, Iván Castilla Rodríguez, Marco A. Cabrera Hernández","doi":"10.1016/j.cmpb.2025.108646","DOIUrl":"10.1016/j.cmpb.2025.108646","url":null,"abstract":"<div><h3>Background and Objective:</h3><div>Computerized clinical decision support systems (CDSS) that incorporate the latest scientific evidence are essential for enhancing patient care quality. Such systems typically rely on some kind of model to accurately represent the knowledge required to assess the clinicians. Although the use of complex and computationally demanding simulation models is common in this field, such models limit the potential applications of CDSSs, both in real-time applications and in simulation-in-the-loop optimization tools. This paper presents a case study on Type 1 Diabetes Mellitus (T1DM) to demonstrate the development of surrogate models from health technology assessment models, with the aim of enhancing the potential of CDSSs.</div></div><div><h3>Methods:</h3><div>The paper details the process of developing machine learning (ML) based surrogate models, including the generation of a dataset for training and testing, and the comparison of different ML techniques. A number of distinct groupings of comorbidities were utilized in the creation of models, which were trained to predict confidence intervals for the time to develop each complication.</div></div><div><h3>Results:</h3><div>The results of the intersection over union (IoU) analysis between the simulation model output and the surrogate models output for the comorbidities under study were greater than 0.9.</div></div><div><h3>Conclusion:</h3><div>The study concludes that ML-based surrogate models are a viable solution for real-time clinical decision-making, offering a substantial speedup in execution time compared to traditional simulation models.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"262 ","pages":"Article 108646"},"PeriodicalIF":4.9,"publicationDate":"2025-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143419941","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 : 2025-02-09DOI: 10.1016/j.cmpb.2025.108657
Christopher Yew Shuen Ang , Mohd Basri Mat Nor , Nur Sazwi Nordin , Thant Zin Kyi , Ailin Razali , Yeong Shiong Chiew
Background
Accurate estimation of resting energy expenditure (REE) is critical for guiding nutritional therapy in critically ill patients. While indirect calorimetry (IC) is the gold standard for REE measurement, it is not routinely feasible in clinical settings due to its complexity and cost. Predictive equations (PEs) offer a simpler alternative but are often inaccurate in critically ill populations. While recent advancements in machine learning (ML) and deep learning (DL) offer potential for improving REE estimation by capturing complex relationships between physiological variables, these approaches have not yet been widely applied or validated in critically ill populations.
Methodology
This prospective study compared the performance of nine commonly used PEs, including the Harris-Benedict (H-B1919), Penn State, and TAH equations, with ML models (XGBoost, Random Forest Regressor [RFR], Support Vector Regression), and DL models (Convolutional Neural Networks [CNN]) in estimating REE in critically ill patients. A dataset of 300 IC measurements from an intensive care unit (ICU) was used, with REE measured by both IC and PEs. The ML/DL models were trained using a combination of static (i.e., age, height, body weight) and dynamic (i.e., minute ventilation, body temperature) variables. A five-fold cross validation was performed to assess the model prediction performance using the root mean square error (RMSE) metric.
Results
Of the PEs analysed, H-B1919 yielded the lowest RMSE at 362 calories. However, the XGBoost and RFR models significantly outperformed all PEs, achieving RMSE values of 199 and 200 calories, respectively. The CNN model demonstrated the poorest performance among ML models, with an RMSE of 250 calories. The inclusion of additional categorical variables such as body mass index (BMI) and body temperature classes slightly reduced RMSE across ML and DL models. Despite data augmentation and imputation techniques, no significant improvements in model performance were observed.
Conclusion
ML models, particularly XGBoost and RFR, provide more accurate REE estimations than traditional PEs, highlighting their potential to better capture the complex, non-linear relationships between physiological variables and REE. These models offer a promising alternative for guiding nutritional therapy in clinical settings, though further validation on independent datasets and across diverse patient populations is warranted.
{"title":"Methods for estimating resting energy expenditure in intensive care patients: A comparative study of predictive equations with machine learning and deep learning approaches","authors":"Christopher Yew Shuen Ang , Mohd Basri Mat Nor , Nur Sazwi Nordin , Thant Zin Kyi , Ailin Razali , Yeong Shiong Chiew","doi":"10.1016/j.cmpb.2025.108657","DOIUrl":"10.1016/j.cmpb.2025.108657","url":null,"abstract":"<div><h3>Background</h3><div>Accurate estimation of resting energy expenditure (REE) is critical for guiding nutritional therapy in critically ill patients. While indirect calorimetry (IC) is the gold standard for REE measurement, it is not routinely feasible in clinical settings due to its complexity and cost. Predictive equations (PEs) offer a simpler alternative but are often inaccurate in critically ill populations. While recent advancements in machine learning (ML) and deep learning (DL) offer potential for improving REE estimation by capturing complex relationships between physiological variables, these approaches have not yet been widely applied or validated in critically ill populations.</div></div><div><h3>Methodology</h3><div>This prospective study compared the performance of nine commonly used PEs, including the Harris-Benedict (H-B1919), Penn State, and TAH equations, with ML models (XGBoost, Random Forest Regressor [RFR], Support Vector Regression), and DL models (Convolutional Neural Networks [CNN]) in estimating REE in critically ill patients. A dataset of 300 IC measurements from an intensive care unit (ICU) was used, with REE measured by both IC and PEs. The ML/DL models were trained using a combination of static (i.e., age, height, body weight) and dynamic (i.e., minute ventilation, body temperature) variables. A five-fold cross validation was performed to assess the model prediction performance using the root mean square error (RMSE) metric.</div></div><div><h3>Results</h3><div>Of the PEs analysed, H-B1919 yielded the lowest RMSE at 362 calories. However, the XGBoost and RFR models significantly outperformed all PEs, achieving RMSE values of 199 and 200 calories, respectively. The CNN model demonstrated the poorest performance among ML models, with an RMSE of 250 calories. The inclusion of additional categorical variables such as body mass index (BMI) and body temperature classes slightly reduced RMSE across ML and DL models. Despite data augmentation and imputation techniques, no significant improvements in model performance were observed.</div></div><div><h3>Conclusion</h3><div>ML models, particularly XGBoost and RFR, provide more accurate REE estimations than traditional PEs, highlighting their potential to better capture the complex, non-linear relationships between physiological variables and REE. These models offer a promising alternative for guiding nutritional therapy in clinical settings, though further validation on independent datasets and across diverse patient populations is warranted.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"262 ","pages":"Article 108657"},"PeriodicalIF":4.9,"publicationDate":"2025-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143402668","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 : 2025-02-09DOI: 10.1016/j.cmpb.2025.108656
Diana Marcela Muñoz Sarmiento , Danna Yeisenia Ferreira Cortés , Mariana Caicedo Pérez , Oswaldo Esteban Llanos Eraso , Cindy Vanessa Vargas Ruiz , Cristian David Benavides Riveros , Diana Paola Ahumada Riaño , Carlos Julio Cortés Rodríguez
Background
Understanding how atherosclerosis and angioplasty biomechanically affect the coronary artery wall is crucial for comprehending the pathophysiology of this disease and advancing potential treatments. However, acquiring this information experimentally or in vivo presents challenges. To overcome this, different computational methods have been employed. This research assessed the impact of atherosclerosis and angioplasty on the strains of each coronary artery tunic using the finite element method.
Methods
Anatomical data were used to create two three-dimensional models of the left anterior descending coronary artery: one representing a normal artery and the other with concentric atherosclerosis, which included the surrounding epicardial fat tissue (EFT) and the three arterial tunics (e.g., intima, media, and adventitia). Blood pressure was applied to both models, and angioplasty was performed in the atherosclerotic model. The mean maximum principal and minimum principal strains were obtained for each layer in each case, and the impact of EFT was analyzed by comparing the results of including and omitting it. Furthermore, a sensitivity analysis was conducted for EFT stiffness, EFT volume, and blood pressure.
Results
Noteworthy biomechanical alterations were observed in the atherosclerotic model before and after angioplasty, compared to the healthy state. After angioplasty, strains in the media and adventitia layers increased on average by up to fivefold, whereas the intima layer experienced a comparatively lower impact. Similarly, excluding EFT resulted in an average fourfold increase in strains in the tunics of both the healthy and atherosclerotic models. In addition, in both healthy and atherosclerotic models, a rise in blood pressure caused the most significant increase in arterial tunic strains, followed by reduced EFT stiffness and increased EFT volume, in order of impact.
Conclusion
Coronary artery wall strains are significantly altered by atherosclerosis and angioplasty, leading to cellular growth in the media and adventitia layers and subsequent reobstruction of the lumen after the procedure. EFT strongly influences coronary wall biomechanics, with low EFT stiffness and high volume predicted as risk factors for the development and severity of atherosclerosis. However, all the above may be modulated through interventions targeting epicardial adipose tissue.
{"title":"Finite element analysis predicts a major mechanical role of epicardial adipose tissue in atherosclerotic coronary disease and angioplasty","authors":"Diana Marcela Muñoz Sarmiento , Danna Yeisenia Ferreira Cortés , Mariana Caicedo Pérez , Oswaldo Esteban Llanos Eraso , Cindy Vanessa Vargas Ruiz , Cristian David Benavides Riveros , Diana Paola Ahumada Riaño , Carlos Julio Cortés Rodríguez","doi":"10.1016/j.cmpb.2025.108656","DOIUrl":"10.1016/j.cmpb.2025.108656","url":null,"abstract":"<div><h3>Background</h3><div>Understanding how atherosclerosis and angioplasty biomechanically affect the coronary artery wall is crucial for comprehending the pathophysiology of this disease and advancing potential treatments. However, acquiring this information experimentally or <em>in vivo</em> presents challenges. To overcome this, different computational methods have been employed. This research assessed the impact of atherosclerosis and angioplasty on the strains of each coronary artery tunic using the finite element method.</div></div><div><h3>Methods</h3><div>Anatomical data were used to create two three-dimensional models of the left anterior descending coronary artery: one representing a normal artery and the other with concentric atherosclerosis, which included the surrounding epicardial fat tissue (EFT) and the three arterial tunics (e.g., intima, media, and adventitia). Blood pressure was applied to both models, and angioplasty was performed in the atherosclerotic model. The mean maximum principal and minimum principal strains were obtained for each layer in each case, and the impact of EFT was analyzed by comparing the results of including and omitting it. Furthermore, a sensitivity analysis was conducted for EFT stiffness, EFT volume, and blood pressure.</div></div><div><h3>Results</h3><div>Noteworthy biomechanical alterations were observed in the atherosclerotic model before and after angioplasty, compared to the healthy state. After angioplasty, strains in the media and adventitia layers increased on average by up to fivefold, whereas the intima layer experienced a comparatively lower impact. Similarly, excluding EFT resulted in an average fourfold increase in strains in the tunics of both the healthy and atherosclerotic models. In addition, in both healthy and atherosclerotic models, a rise in blood pressure caused the most significant increase in arterial tunic strains, followed by reduced EFT stiffness and increased EFT volume, in order of impact.</div></div><div><h3>Conclusion</h3><div>Coronary artery wall strains are significantly altered by atherosclerosis and angioplasty, leading to cellular growth in the media and adventitia layers and subsequent reobstruction of the lumen after the procedure. EFT strongly influences coronary wall biomechanics, with low EFT stiffness and high volume predicted as risk factors for the development and severity of atherosclerosis. However, all the above may be modulated through interventions targeting epicardial adipose tissue.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"262 ","pages":"Article 108656"},"PeriodicalIF":4.9,"publicationDate":"2025-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143419942","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 : 2025-02-08DOI: 10.1016/j.cmpb.2025.108639
Enyuan Pan , Yuan Zhong , Ping Li , Yi Yang , Jin Zhou
Medical imaging is crucial for artificial intelligence-based clinician decision-making. However, learning anatomical features from limited samples poses a challenge. To address this issue, recent studies have employed diffusion models to generate medical imaging data, demonstrating the potential for high-quality medical image generation through deep learning. In this paper, we propose a high-quality cervical MRI image generation method called the Cervical Spine MRI Diffusion Probabilistic Model (CSM-DPM). Considering the complexity of neck MRI image data, our method uses a hybrid of standard Gaussian noise and point noise obtained by sampling within 2D Gaussian noise fields to approximate the true distribution of the image data. Meanwhile, the cosine noise schedule is used to make the morphology of the generated vertebral blocks and other focal areas more visually natural and clear. Furthermore, to enhance the noise prediction capabilities of UNet in DDPM, we devise the Asa-ResUNet module, which incorporates an asymmetric attention mechanism. This mechanism includes spatial attention on different ResUNet layers to improve feature extraction and incorporates high-level semantic information. We further enhance the stability and robustness of the Asa-ResUNet by using an exponential weighting strategy (EMA). Experiments demonstrate that our method produces cervical spine MRI images with FID values that are up to 15.79%, 52.61%, and 46.57% lower than those produced by DDPM, DDIM, and F-PNDM, respectively, indicating superior image quality. Segmentation experiments confirm that the generated images can enhance the overall performance of segmentation models when used for training.
{"title":"Hybrid-noise generative diffusion probabilistic model for cervical spine MRI image generation","authors":"Enyuan Pan , Yuan Zhong , Ping Li , Yi Yang , Jin Zhou","doi":"10.1016/j.cmpb.2025.108639","DOIUrl":"10.1016/j.cmpb.2025.108639","url":null,"abstract":"<div><div>Medical imaging is crucial for artificial intelligence-based clinician decision-making. However, learning anatomical features from limited samples poses a challenge. To address this issue, recent studies have employed diffusion models to generate medical imaging data, demonstrating the potential for high-quality medical image generation through deep learning. In this paper, we propose a high-quality cervical MRI image generation method called the Cervical Spine MRI Diffusion Probabilistic Model (CSM-DPM). Considering the complexity of neck MRI image data, our method uses a hybrid of standard Gaussian noise and point noise obtained by sampling within 2D Gaussian noise fields to approximate the true distribution of the image data. Meanwhile, the cosine noise schedule is used to make the morphology of the generated vertebral blocks and other focal areas more visually natural and clear. Furthermore, to enhance the noise prediction capabilities of UNet in DDPM, we devise the Asa-ResUNet module, which incorporates an asymmetric attention mechanism. This mechanism includes spatial attention on different ResUNet layers to improve feature extraction and incorporates high-level semantic information. We further enhance the stability and robustness of the Asa-ResUNet by using an exponential weighting strategy (EMA). Experiments demonstrate that our method produces cervical spine MRI images with FID values that are up to 15.79%, 52.61%, and 46.57% lower than those produced by DDPM, DDIM, and F-PNDM, respectively, indicating superior image quality. Segmentation experiments confirm that the generated images can enhance the overall performance of segmentation models when used for training.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"262 ","pages":"Article 108639"},"PeriodicalIF":4.9,"publicationDate":"2025-02-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143387802","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 : 2025-02-08DOI: 10.1016/j.cmpb.2025.108652
Madhav Acharya , Ravinesh C Deo , Prabal Datta Barua , Aruna Devi , Xiaohui Tao
Background and objective
Deep learning models have gained widespread adoption in healthcare for accurate diagnosis through the analysis of brain signals. Neurodegenerative disorders like Alzheimer's Disease (AD) and Frontotemporal Dementia (FD) are increasingly prevalent due to age-related brain volume reduction. Despite advances, existing models often lack comprehensive multi-class classification capabilities and are computationally expensive. This study addresses these gaps by proposing EEGConvNeXt, a novel convolutional neural network (CNN) model for detecting AD and FD using electroencephalogram (EEG) signals with high accuracy.
Materials and method
In this research, we employ an open-access EEG signal public dataset containing three distinct classes: AD, FD, and control subjects. We then constructed a newly proposed EEGConvNeXt model comprised of a 2-dimensional CNN algorithm that firstly converts the EEG signals into power spectrogram-based images. Secondly, these images were used as input for the proposed EEGConvNeXt model for automated classification of AD, FD, and a control outcome. The proposed EEGConvNeXt model is therefore a lightweight model that contributes to a new image classification CNN structure based on the transformer model with four primary stages: a stem, a main model, downsampling, and an output stem.
Results
The EEGConvNeXt model achieved a classification accuracy of ∼95.70% for three-class detection (AD, FD, and control), validated using a hold-out strategy. Binary classification cases, such as AD versus FD and FD versus control, achieved accuracies exceeding 98%, demonstrating the model's robustness across scenarios.
Conclusions
The proposed EEGConvNeXt model demonstrates high classification performance with a lightweight architecture suitable for deployment in resource-constrained settings. While the study establishes a novel framework for AD and FD detection, limitations include reliance on a relatively small dataset and the need for further validation on diverse populations. Future research should focus on expanding datasets, optimizing architecture, and exploring additional neurological disorders to enhance the model's utility in clinical applications.
{"title":"EEGConvNeXt: A novel convolutional neural network model for automated detection of Alzheimer's Disease and Frontotemporal Dementia using EEG signals","authors":"Madhav Acharya , Ravinesh C Deo , Prabal Datta Barua , Aruna Devi , Xiaohui Tao","doi":"10.1016/j.cmpb.2025.108652","DOIUrl":"10.1016/j.cmpb.2025.108652","url":null,"abstract":"<div><h3>Background and objective</h3><div>Deep learning models have gained widespread adoption in healthcare for accurate diagnosis through the analysis of brain signals. Neurodegenerative disorders like Alzheimer's Disease (AD) and Frontotemporal Dementia (FD) are increasingly prevalent due to age-related brain volume reduction. Despite advances, existing models often lack comprehensive multi-class classification capabilities and are computationally expensive. This study addresses these gaps by proposing EEGConvNeXt, a novel convolutional neural network (CNN) model for detecting AD and FD using electroencephalogram (EEG) signals with high accuracy.</div></div><div><h3>Materials and method</h3><div>In this research, we employ an open-access EEG signal public dataset containing three distinct classes: AD, FD, and control subjects. We then constructed a newly proposed EEGConvNeXt model comprised of a 2-dimensional CNN algorithm that firstly converts the EEG signals into power spectrogram-based images. Secondly, these images were used as input for the proposed EEGConvNeXt model for automated classification of AD, FD, and a control outcome. The proposed EEGConvNeXt model is therefore a lightweight model that contributes to a new image classification CNN structure based on the transformer model with four primary stages: a stem, a main model, downsampling, and an output stem.</div></div><div><h3>Results</h3><div>The EEGConvNeXt model achieved a classification accuracy of ∼95.70% for three-class detection (AD, FD, and control), validated using a hold-out strategy. Binary classification cases, such as AD versus FD and FD versus control, achieved accuracies exceeding 98%, demonstrating the model's robustness across scenarios.</div></div><div><h3>Conclusions</h3><div>The proposed EEGConvNeXt model demonstrates high classification performance with a lightweight architecture suitable for deployment in resource-constrained settings. While the study establishes a novel framework for AD and FD detection, limitations include reliance on a relatively small dataset and the need for further validation on diverse populations. Future research should focus on expanding datasets, optimizing architecture, and exploring additional neurological disorders to enhance the model's utility in clinical applications.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"262 ","pages":"Article 108652"},"PeriodicalIF":4.9,"publicationDate":"2025-02-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143379299","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 : 2025-02-07DOI: 10.1016/j.cmpb.2025.108648
Ke Zhang , Yufang Chen , Chenglong Feng , Xinhao Xiang , Xiaoqing Zhang , Ying Dai , Wenxin Niu
Background and Objective
Patients with spinal cord injury (SCI), are prone to pressure injury (PI) in the soft tissues of buttocks. Early prediction of PI holds the potential to reduce the occurrence and progression of PI. This study proposes a machine learning model to predict soft tissue stress/strain and evaluate PI risk in SCI patients.
Methods
Based on the standard database from parametric models of buttock, the biomechanical response of soft tissues and risk factors affecting PI were analyzed. A comprehensive assessment of multiple machine-learning methods was performed to predict the risk of PI, the selected optimal model is explained locally and globally using Shapley additive explanations (SHAP).
Results
The proposed hybrid model for predicting PI consists of a backpropagation neural network and Extreme Gradient Boosting, performed the coefficient of determination (R2) of 0.977.
Conclusion
The model exhibits accurate performance which may be considered as the ideal method for predicting PI. Furthermore, it can be used with other health-monitoring equipment to improve the quality of patients with SCI or other dysfunctional diseases.
{"title":"Machine learning based finite element analysis for personalized prediction of pressure injury risk in patients with spinal cord injury","authors":"Ke Zhang , Yufang Chen , Chenglong Feng , Xinhao Xiang , Xiaoqing Zhang , Ying Dai , Wenxin Niu","doi":"10.1016/j.cmpb.2025.108648","DOIUrl":"10.1016/j.cmpb.2025.108648","url":null,"abstract":"<div><h3>Background and Objective</h3><div>Patients with spinal cord injury (SCI), are prone to pressure injury (PI) in the soft tissues of buttocks. Early prediction of PI holds the potential to reduce the occurrence and progression of PI. This study proposes a machine learning model to predict soft tissue stress/strain and evaluate PI risk in SCI patients.</div></div><div><h3>Methods</h3><div>Based on the standard database from parametric models of buttock, the biomechanical response of soft tissues and risk factors affecting PI were analyzed. A comprehensive assessment of multiple machine-learning methods was performed to predict the risk of PI, the selected optimal model is explained locally and globally using Shapley additive explanations (SHAP).</div></div><div><h3>Results</h3><div>The proposed hybrid model for predicting PI consists of a backpropagation neural network and Extreme Gradient Boosting, performed the coefficient of determination (R<sup>2</sup>) of 0.977.</div></div><div><h3>Conclusion</h3><div>The model exhibits accurate performance which may be considered as the ideal method for predicting PI. Furthermore, it can be used with other health-monitoring equipment to improve the quality of patients with SCI or other dysfunctional diseases.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"261 ","pages":"Article 108648"},"PeriodicalIF":4.9,"publicationDate":"2025-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143350072","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}
Integrating multimodal data, such as pathology images and genomics, is crucial for understanding cancer heterogeneity, personalized treatment complexity, and enhancing survival prediction. However, most current prognostic methods are limited to a single domain of histopathology or genomics, inevitably reducing their potential for accurate patient outcome prediction. Despite advancements in the concurrent analysis of pathology and genomic data, existing approaches inadequately address the intricate intermodal relationships.
Methods:
This paper introduces the CPathomic method for multimodal data-based survival prediction. By leveraging whole slide pathology images to guide local pathological features, the method effectively mitigates significant intermodal differences through a cross-modal representational contrastive learning module. Furthermore, it facilitates interactive learning between different modalities through cross-modal and gated attention modules.
Results:
The extensive experiments on five public TCGA datasets demonstrate that CPathomic framework effectively bridges modality gaps, consistently outperforming alternative multimodal survival prediction methods.
Conclusion:
The model we propose, CPathomic, unveils the potential of contrastive learning and cross-modal attention in the representation and fusion of multimodal data, enhancing the performance of patient survival prediction.
{"title":"Cross-modal alignment and contrastive learning for enhanced cancer survival prediction","authors":"Tengfei Li , Xuezhong Zhou , Jingyan Xue , Lili Zeng , Qiang Zhu , Ruiping Wang , Haibin Yu , Jianan Xia","doi":"10.1016/j.cmpb.2025.108633","DOIUrl":"10.1016/j.cmpb.2025.108633","url":null,"abstract":"<div><h3>Background and Objective:</h3><div>Integrating multimodal data, such as pathology images and genomics, is crucial for understanding cancer heterogeneity, personalized treatment complexity, and enhancing survival prediction. However, most current prognostic methods are limited to a single domain of histopathology or genomics, inevitably reducing their potential for accurate patient outcome prediction. Despite advancements in the concurrent analysis of pathology and genomic data, existing approaches inadequately address the intricate intermodal relationships.</div></div><div><h3>Methods:</h3><div>This paper introduces the CPathomic method for multimodal data-based survival prediction. By leveraging whole slide pathology images to guide local pathological features, the method effectively mitigates significant intermodal differences through a cross-modal representational contrastive learning module. Furthermore, it facilitates interactive learning between different modalities through cross-modal and gated attention modules.</div></div><div><h3>Results:</h3><div>The extensive experiments on five public TCGA datasets demonstrate that CPathomic framework effectively bridges modality gaps, consistently outperforming alternative multimodal survival prediction methods.</div></div><div><h3>Conclusion:</h3><div>The model we propose, CPathomic, unveils the potential of contrastive learning and cross-modal attention in the representation and fusion of multimodal data, enhancing the performance of patient survival prediction.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"263 ","pages":"Article 108633"},"PeriodicalIF":4.9,"publicationDate":"2025-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143418850","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 : 2025-02-06DOI: 10.1016/j.cmpb.2025.108624
Robbe D’hondt , Klest Dedja , Sofie Aerts , Bart Van Wijmeersch , Tomas Kalincik , Stephen Reddel , Eva Kubala Havrdova , Alessandra Lugaresi , Bianca Weinstock-Guttman , Saloua Mrabet , Patrice Lalive , Allan G. Kermode , Serkan Ozakbas , Francesco Patti , Alexandre Prat , Valentina Tomassini , Izanne Roos , Raed Alroughani , Oliver Gerlach , Samia J. Khoury , Celine Vens
Background:
Prognostic machine learning research in multiple sclerosis has been mainly focusing on black-box models predicting whether a patients’ disability will progress in a fixed number of years. However, as this is a binary yes/no question, it cannot take individual disease severity into account. Therefore, in this work we propose to model the time to disease progression instead. Additionally, we use explainable machine learning techniques to make the model outputs more interpretable.
Methods:
A preprocessed subset of 29,201 patients of the international data registry MSBase was used. Disability was assessed in terms of the Expanded Disability Status Scale (EDSS). We predict the time to significant and confirmed disability progression using random survival forests, a machine learning model for survival analysis. Performance is evaluated on a time-dependent area under the receiver operating characteristic and the precision–recall curves. Importantly, predictions are then explained using SHAP and Bellatrex, two explainability toolboxes, and lead to both global (population-wide) as well as local (patient visit-specific) insights.
Results:
On the task of predicting progression in 2 years, the random survival forest achieves state-of-the-art performance, comparable to previous work employing a random forest. However, here the random survival forest has the added advantage of being able to predict progression over a longer time horizon, with AUROC for the first 10 years after baseline. Explainability techniques further validated the model by extracting clinically valid insights from the predictions made by the model. For example, a clear decline in the per-visit probability of progression is observed in more recent years since 2012, likely reflecting globally increasing use of more effective MS therapies.
Conclusion:
The binary classification models found in the literature can be extended to a time-to-event setting without loss of performance, thus allowing a more comprehensive prediction of patient prognosis. Furthermore, explainability techniques proved to be key to reach a better understanding of the model and increase validation of its behaviour.
{"title":"Explainable time-to-progression predictions in multiple sclerosis","authors":"Robbe D’hondt , Klest Dedja , Sofie Aerts , Bart Van Wijmeersch , Tomas Kalincik , Stephen Reddel , Eva Kubala Havrdova , Alessandra Lugaresi , Bianca Weinstock-Guttman , Saloua Mrabet , Patrice Lalive , Allan G. Kermode , Serkan Ozakbas , Francesco Patti , Alexandre Prat , Valentina Tomassini , Izanne Roos , Raed Alroughani , Oliver Gerlach , Samia J. Khoury , Celine Vens","doi":"10.1016/j.cmpb.2025.108624","DOIUrl":"10.1016/j.cmpb.2025.108624","url":null,"abstract":"<div><h3>Background:</h3><div>Prognostic machine learning research in multiple sclerosis has been mainly focusing on black-box models predicting whether a patients’ disability will progress in a fixed number of years. However, as this is a binary yes/no question, it cannot take individual disease severity into account. Therefore, in this work we propose to model the time to disease progression instead. Additionally, we use explainable machine learning techniques to make the model outputs more interpretable.</div></div><div><h3>Methods:</h3><div>A preprocessed subset of 29,201 patients of the international data registry MSBase was used. Disability was assessed in terms of the Expanded Disability Status Scale (EDSS). We predict the time to significant and confirmed disability progression using random survival forests, a machine learning model for survival analysis. Performance is evaluated on a time-dependent area under the receiver operating characteristic and the precision–recall curves. Importantly, predictions are then explained using SHAP and Bellatrex, two explainability toolboxes, and lead to both global (population-wide) as well as local (patient visit-specific) insights.</div></div><div><h3>Results:</h3><div>On the task of predicting progression in 2 years, the random survival forest achieves state-of-the-art performance, comparable to previous work employing a random forest. However, here the random survival forest has the added advantage of being able to predict progression over a longer time horizon, with AUROC <span><math><mrow><mo>></mo><mn>60</mn><mtext>%</mtext></mrow></math></span> for the first 10 years after baseline. Explainability techniques further validated the model by extracting clinically valid insights from the predictions made by the model. For example, a clear decline in the per-visit probability of progression is observed in more recent years since 2012, likely reflecting globally increasing use of more effective MS therapies.</div></div><div><h3>Conclusion:</h3><div>The binary classification models found in the literature can be extended to a time-to-event setting without loss of performance, thus allowing a more comprehensive prediction of patient prognosis. Furthermore, explainability techniques proved to be key to reach a better understanding of the model and increase validation of its behaviour.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"263 ","pages":"Article 108624"},"PeriodicalIF":4.9,"publicationDate":"2025-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143418849","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 : 2025-02-06DOI: 10.1016/j.cmpb.2025.108637
Nannan Cao , Qilin Li , Kangkang Sun , Heng Zhang , Jiangyi Ding , Ziyi Wang , Wei Chen , Liugang Gao , Jiawei Sun , Kai Xie , Xinye Ni
<div><h3>Objective</h3><div>This research developed an innovative Mask-based Swin Transformer network (MBST) to enhance the quality of 4D cone-beam computed tomography (4D-CBCT) reconstruction. The network is trained on 4D-CBCT reconstructed under limited scanning conditions, enabling its application to a broad range of 4D-CBCT reconstruction scenarios, including those with high scanning speeds.</div></div><div><h3>Methods</h3><div>4D imaging data from 20 patients with thoracic tumors were used to train and evaluate the deep learning model. 15 cases were used for training, and 5 cases were employed for simulation testing. The Feldkamp–Davis–Kress algorithm was employed to simulate 4D-CBCT from downsampled 4D-CT data to mitigate the uncertainties associated with respiratory motion between treatment fractions, and the 4D-CT data served as the ground truth for training. The study reconstructed 4D-CBCT images under 11 different scanning intervals including full angle acquisition at 1°, 2°, 3°, 4°, 5°, 6°, 12°, 18°, 24° intervals, and 1/3 full angles acquisition at 5°, 10° inrevals respectively for capturing 4D-CBCT projections. The test results were quantitatively evaluated using the structural similarity index measure (SSIM), peak signal-to-noise ratio (PSNR), mean error (ME), and mean absolute error (MAE), and image quality was qualitatively assessed. Real clinical patients who were not included in the training were tested to evaluate the network's ability to generalize. Moreover, the proposed method was compared with other deep learning approaches, and statistical analyses were performed.</div></div><div><h3>Results</h3><div>Simulation data assessment revealed that with small projection acquisition interval, such as the 4°interval, the 4D-CBCT images optimized by MBST showed a considerable improvement over the original 4D-CBCT images in terms of SSIM (42.3% increase) and PSNR (10.8 dB increase), and the ME and MAE values approached 0. The improvements were statistically significant (<em>P</em> < 0.001). Compared with other deep learning methods, MBST demonstrated superior performance with improvements of 1.4% in SSIM and 1.21 dB in PSNR and a reduction of 0.94 in MAE. With large projection intervals, such as the 24°interval, MBST outperformed other deep learning methods. Specifically, its SSIM, PSNR, and MAE increased by 3.8%, 0.81 dB, and 10.34, respectively, compared with those of other deep learning methods, and the improvements were statistically significant (P < 0.01). In addition, MBST could reconstruct bone tissue and optimize the quality of 4D-CBCT images even when the number of projections was small (12°, 18°, 24°intervals). Clinical data evaluation revealed that after optimization by MBST, the SSIM, PSNR, ME, and MAE of 4D-CBCT compared with those of 4D-CT registration improved from the original 22.8%, 15.49 dB, −345.5, and 432.2 to 81.5%, 27.93 dB, −53.79, and 73.77, respectively. Moreover, MBST exhibited the most pronounced impro
{"title":"MBST-Driven 4D-CBCT reconstruction: Leveraging swin transformer and masking for robust performance","authors":"Nannan Cao , Qilin Li , Kangkang Sun , Heng Zhang , Jiangyi Ding , Ziyi Wang , Wei Chen , Liugang Gao , Jiawei Sun , Kai Xie , Xinye Ni","doi":"10.1016/j.cmpb.2025.108637","DOIUrl":"10.1016/j.cmpb.2025.108637","url":null,"abstract":"<div><h3>Objective</h3><div>This research developed an innovative Mask-based Swin Transformer network (MBST) to enhance the quality of 4D cone-beam computed tomography (4D-CBCT) reconstruction. The network is trained on 4D-CBCT reconstructed under limited scanning conditions, enabling its application to a broad range of 4D-CBCT reconstruction scenarios, including those with high scanning speeds.</div></div><div><h3>Methods</h3><div>4D imaging data from 20 patients with thoracic tumors were used to train and evaluate the deep learning model. 15 cases were used for training, and 5 cases were employed for simulation testing. The Feldkamp–Davis–Kress algorithm was employed to simulate 4D-CBCT from downsampled 4D-CT data to mitigate the uncertainties associated with respiratory motion between treatment fractions, and the 4D-CT data served as the ground truth for training. The study reconstructed 4D-CBCT images under 11 different scanning intervals including full angle acquisition at 1°, 2°, 3°, 4°, 5°, 6°, 12°, 18°, 24° intervals, and 1/3 full angles acquisition at 5°, 10° inrevals respectively for capturing 4D-CBCT projections. The test results were quantitatively evaluated using the structural similarity index measure (SSIM), peak signal-to-noise ratio (PSNR), mean error (ME), and mean absolute error (MAE), and image quality was qualitatively assessed. Real clinical patients who were not included in the training were tested to evaluate the network's ability to generalize. Moreover, the proposed method was compared with other deep learning approaches, and statistical analyses were performed.</div></div><div><h3>Results</h3><div>Simulation data assessment revealed that with small projection acquisition interval, such as the 4°interval, the 4D-CBCT images optimized by MBST showed a considerable improvement over the original 4D-CBCT images in terms of SSIM (42.3% increase) and PSNR (10.8 dB increase), and the ME and MAE values approached 0. The improvements were statistically significant (<em>P</em> < 0.001). Compared with other deep learning methods, MBST demonstrated superior performance with improvements of 1.4% in SSIM and 1.21 dB in PSNR and a reduction of 0.94 in MAE. With large projection intervals, such as the 24°interval, MBST outperformed other deep learning methods. Specifically, its SSIM, PSNR, and MAE increased by 3.8%, 0.81 dB, and 10.34, respectively, compared with those of other deep learning methods, and the improvements were statistically significant (P < 0.01). In addition, MBST could reconstruct bone tissue and optimize the quality of 4D-CBCT images even when the number of projections was small (12°, 18°, 24°intervals). Clinical data evaluation revealed that after optimization by MBST, the SSIM, PSNR, ME, and MAE of 4D-CBCT compared with those of 4D-CT registration improved from the original 22.8%, 15.49 dB, −345.5, and 432.2 to 81.5%, 27.93 dB, −53.79, and 73.77, respectively. Moreover, MBST exhibited the most pronounced impro","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"262 ","pages":"Article 108637"},"PeriodicalIF":4.9,"publicationDate":"2025-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143379300","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 : 2025-02-06DOI: 10.1016/j.cmpb.2025.108654
Ming-Feng Tsai , Yu-Chang Chu , Wen-Teng Yao , Chia-Meng Yu , Yu-Fan Chen , Shu-Tien Huang , Liong-Rung Liu , Lang-Hua Chiu , Yueh-Hung Lin , Chin-Yi Yang , Kung-Chen Ho , Chieh-Ming Yu , Wen-Chen Huang , Sheng-Yun Ou , Kwang-Yi Tung , Fei-Hung Hung , Hung-Wen Chiu
Background and Objective
Few studies have evaluated peripheral artery disease (PAD) in patients with lower extremity wounds by a convolutional neural network (CNN)-based deep learning algorithm. We aimed to establish a framework for PAD detection, peripheral arterial occlusive disease (PAOD) detection, and PAD classification in patients with lower extremity wounds by the AlexNet, GoogleNet, and ResNet101V2 algorithms.
Methods
Our proposed framework was based on a CNN-based AlexNet, GoogleNet, or ResNet 101V2 model devoted to performing optimized detection and classification of PAD in patients with lower extremity wounds. We also evaluated the performance of the plastic and reconstructive surgeons (PRS) and general practitioner (GP).
Results
Compared to the performance of AlexNet or GoogleNet, a slight increase in ResNet101V2-based performance of PAD detection, PAOD detection, and PAD classification with original images was observed. A similar observation was found for PAD detection, PAOD detection, and PAD classification with background-removal or cropped images. GP group had a lower performance for PAD and PAOD detection than did the three models with original images, while a similar performance for PAD detection was observed in PRS group and the 3 models.
Conclusions
We proposed a promising framework using CNN-based deep learning based on objective ankle-brachial index (ABI) values and image preprocessing to characterize PAD detection, PAOD detection, and PAD classification for lower extremity wounds, which provides an easily implemented and objective and reliable computational tool for physicians to automatically identify and classify PAD.
{"title":"Deep-learning-based diagnosis framework for ankle-brachial index defined peripheral arterial disease of lower extremity wound: Comparison with physicians","authors":"Ming-Feng Tsai , Yu-Chang Chu , Wen-Teng Yao , Chia-Meng Yu , Yu-Fan Chen , Shu-Tien Huang , Liong-Rung Liu , Lang-Hua Chiu , Yueh-Hung Lin , Chin-Yi Yang , Kung-Chen Ho , Chieh-Ming Yu , Wen-Chen Huang , Sheng-Yun Ou , Kwang-Yi Tung , Fei-Hung Hung , Hung-Wen Chiu","doi":"10.1016/j.cmpb.2025.108654","DOIUrl":"10.1016/j.cmpb.2025.108654","url":null,"abstract":"<div><h3>Background and Objective</h3><div>Few studies have evaluated peripheral artery disease (PAD) in patients with lower extremity wounds by a convolutional neural network (CNN)-based deep learning algorithm. We aimed to establish a framework for PAD detection, peripheral arterial occlusive disease (PAOD) detection, and PAD classification in patients with lower extremity wounds by the AlexNet, GoogleNet, and ResNet101V2 algorithms.</div></div><div><h3>Methods</h3><div>Our proposed framework was based on a CNN-based AlexNet, GoogleNet, or ResNet 101V2 model devoted to performing optimized detection and classification of PAD in patients with lower extremity wounds. We also evaluated the performance of the plastic and reconstructive surgeons (PRS) and general practitioner (GP).</div></div><div><h3>Results</h3><div>Compared to the performance of AlexNet or GoogleNet, a slight increase in ResNet101V2-based performance of PAD detection, PAOD detection, and PAD classification with original images was observed. A similar observation was found for PAD detection, PAOD detection, and PAD classification with background-removal or cropped images. GP group had a lower performance for PAD and PAOD detection than did the three models with original images, while a similar performance for PAD detection was observed in PRS group and the 3 models.</div></div><div><h3>Conclusions</h3><div>We proposed a promising framework using CNN-based deep learning based on objective ankle-brachial index (ABI) values and image preprocessing to characterize PAD detection, PAOD detection, and PAD classification for lower extremity wounds, which provides an easily implemented and objective and reliable computational tool for physicians to automatically identify and classify PAD.</div></div>","PeriodicalId":10624,"journal":{"name":"Computer methods and programs in biomedicine","volume":"263 ","pages":"Article 108654"},"PeriodicalIF":4.9,"publicationDate":"2025-02-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143445395","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