Computer methods and programs in biomedicine update最新文献_第6页

Comment on “Picture: A web application for decision support in glioma surgery” by van Genderen et al. 对van Genderen等人的“图片：神经胶质瘤手术中决策支持的web应用程序”的评论。

Computer methods and programs in biomedicine update

Pub Date : 2025-01-01 DOI: 10.1016/j.cmpbup.2025.100223

Rosario Sarabia , Santiago Cepeda

引用次数: 0

A predictive analytics approach with Bayesian-optimized gentle boosting ensemble models for diabetes diagnosis 预测分析方法与贝叶斯优化温和促进集成模型糖尿病诊断

Computer methods and programs in biomedicine update

Pub Date : 2025-01-01 DOI: 10.1016/j.cmpbup.2025.100184

Behnaz Motamedi, Balázs Villányi

Effective disease management necessitates the accurate and timely prediction of lung cancer and diabetes. Machine learning (ML) based models have garnered attention in the realm of predictive healthcare, with ensemble methods, in particular, bolstering algorithms to improve classification performance. Nevertheless, enhancing boosting algorithms to achieve superior predictive accuracy continues to be a difficult task. This study proposes a Bayesian-Optimized GentleBoost Ensemble (BOGBEnsemble) to improve classification performance for diabetes prediction (DiP) and lung cancer prediction (LCP). Two Kaggle datasets—a diabetes dataset from multiple healthcare providers and a Survey Lung Cancer dataset from existent medical records—are utilized. Data preprocessing involves outlier removal, min–max normalization, class balancing, and Pearson correlation-based feature selection. The GentleBoost classifier is optimized using Bayesian hyperparameter tuning, focusing on learning rate and the number of weak learners, and is validated using 10-fold cross-validation. BOGBEnsemble is evaluated in comparison to leading models, such as Random Forest (RF), Adaptive Boosting (AdaBoost), Logistic Boosting (LogitBoost), Random Undersampling Boosting (RUSBoost), conventional GentleBoost, and Multi-Layer Perceptron (MLP) architectures. The DiP-BOGBEnsemble achieves a 99.26% accuracy, 98.94% precision, 99.60% recall, 99.26% F1-score, 99.46% F2-score, 98.51% MCC, 98.51 Kappa, 0.0041 FOR, and 22,606.75 DOR. The LC-BOGBEnsemble achieves a 96.51% accuracy, 97.83% precision, 94.76% recall, 96.28% F1-score, 95.36% F2-score, MCC of 93.03%, Kappa of 92.99, FOR of 0.0462, and DOR of 932.15. This study highlights the potential of BOGBEnsemble as a clinically viable tool for early disease detection and decision support, paving the way for more reliable and personalized healthcare strategies.

有效的疾病管理需要准确、及时地预测肺癌和糖尿病。基于机器学习（ML）的模型在预测性医疗保健领域引起了人们的关注，特别是集成方法，可以增强算法以提高分类性能。然而，增强增强算法以达到更高的预测精度仍然是一项艰巨的任务。本研究提出了一种贝叶斯优化的绅士boost集成（BOGBEnsemble）来提高糖尿病预测（DiP）和肺癌预测（LCP）的分类性能。使用了两个Kaggle数据集——来自多个医疗保健提供者的糖尿病数据集和来自现有医疗记录的Survey Lung Cancer数据集。数据预处理包括异常值去除、最小-最大归一化、类平衡和基于Pearson相关性的特征选择。使用贝叶斯超参数调优对GentleBoost分类器进行优化，重点关注学习率和弱学习器的数量，并使用10倍交叉验证进行验证。与随机森林（RF）、自适应增强（AdaBoost）、逻辑增强（LogitBoost）、随机不足采样增强（RUSBoost）、传统的GentleBoost和多层感知器（MLP）架构等领先模型相比，对BOGBEnsemble进行了评估。DiP-BOGBEnsemble的准确率为99.26%，精密度为98.94%，召回率为99.60%，f1评分为99.26%，f2评分为99.46%，MCC为98.51%，Kappa为98.51，FOR为0.0041，DOR为22,606.75。LC-BOGBEnsemble的准确率为96.51%，精密度为97.83%，召回率为94.76%，f1评分为96.28%，f2评分为95.36%，MCC为93.03%，Kappa为92.99，FOR为0.0462，DOR为932.15。这项研究强调了BOGBEnsemble作为早期疾病检测和决策支持的临床可行工具的潜力，为更可靠和个性化的医疗保健策略铺平了道路。

{"title":"A predictive analytics approach with Bayesian-optimized gentle boosting ensemble models for diabetes diagnosis","authors":"Behnaz Motamedi, Balázs Villányi","doi":"10.1016/j.cmpbup.2025.100184","DOIUrl":"10.1016/j.cmpbup.2025.100184","url":null,"abstract":"<div><div>Effective disease management necessitates the accurate and timely prediction of lung cancer and diabetes. Machine learning (ML) based models have garnered attention in the realm of predictive healthcare, with ensemble methods, in particular, bolstering algorithms to improve classification performance. Nevertheless, enhancing boosting algorithms to achieve superior predictive accuracy continues to be a difficult task. This study proposes a Bayesian-Optimized GentleBoost Ensemble (BOGBEnsemble) to improve classification performance for diabetes prediction (DiP) and lung cancer prediction (LCP). Two Kaggle datasets—a diabetes dataset from multiple healthcare providers and a Survey Lung Cancer dataset from existent medical records—are utilized. Data preprocessing involves outlier removal, min–max normalization, class balancing, and Pearson correlation-based feature selection. The GentleBoost classifier is optimized using Bayesian hyperparameter tuning, focusing on learning rate and the number of weak learners, and is validated using 10-fold cross-validation. BOGBEnsemble is evaluated in comparison to leading models, such as Random Forest (RF), Adaptive Boosting (AdaBoost), Logistic Boosting (LogitBoost), Random Undersampling Boosting (RUSBoost), conventional GentleBoost, and Multi-Layer Perceptron (MLP) architectures. The DiP-BOGBEnsemble achieves a 99.26% accuracy, 98.94% precision, 99.60% recall, 99.26% F1-score, 99.46% F2-score, 98.51% MCC, 98.51 Kappa, 0.0041 FOR, and 22,606.75 DOR. The LC-BOGBEnsemble achieves a 96.51% accuracy, 97.83% precision, 94.76% recall, 96.28% F1-score, 95.36% F2-score, MCC of 93.03%, Kappa of 92.99, FOR of 0.0462, and DOR of 932.15. This study highlights the potential of BOGBEnsemble as a clinically viable tool for early disease detection and decision support, paving the way for more reliable and personalized healthcare strategies.</div></div>","PeriodicalId":72670,"journal":{"name":"Computer methods and programs in biomedicine update","volume":"7 ","pages":"Article 100184"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143455086","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Analysis of preprocessing for Generative Adversarial Networks: A case study on color fundoscopy to fluorescein angiography image-to-image translation 生成对抗网络的预处理分析：彩色眼底镜到荧光素血管造影图像到图像转换的案例研究

Computer methods and programs in biomedicine update

Pub Date : 2025-01-01 DOI: 10.1016/j.cmpbup.2025.100179

Veena K.M. , Veena Mayya , Rashmi Naveen Raj , Sulatha V. Bhandary , Uma Kulkarni

Generative Adversarial Networks (GANs) are capturing the attention of peer researchers in paired or unpaired image-to-image translation applications, particularly in the domain of retinal image processing. Additionally, there are several effective image preprocessing techniques available that can significantly improve the performance of GANs. This study examines the impact of five different image preprocessing techniques - Green Channel, CLAHE on Green Channel, CLAHE on RGB channels, Green Channel Gaussian Convolution, and RGB Gaussian Convolution - on five different GAN variants: CycleGAN, Pix2Pix GAN, CUT GAN, FastCut GAN, and NICE GAN. The study involved conducting 30 experiments to assess the performances of these GAN variants in the image-to-image translation of dual-mode retinal images. The evaluation utilized Frechet Inception Distance (FID) and Kernel Inception Distance (KID) metric scores to measure the performance of the GAN variants. The results demonstrated that the CycleGAN model achieved the best performance with CLAHE on RGB preprocessed images, achieving the lowest FID and KID scores of 103.49 and 0.038, respectively. This investigation underscores the significant potential of image preprocessing techniques in enhancing the performance of GANs in image translation applications.

生成对抗网络（GANs）在成对或非成对图像到图像的翻译应用中引起了同行研究人员的注意，特别是在视网膜图像处理领域。此外，有几种有效的图像预处理技术可以显著提高gan的性能。本研究考察了五种不同的图像预处理技术——绿色通道、CLAHE对绿色通道、CLAHE对RGB通道、绿色通道高斯卷积和RGB高斯卷积——对五种不同的GAN变体的影响：CycleGAN、Pix2Pix GAN、CUT GAN、FastCut GAN和NICE GAN。该研究进行了30个实验，以评估这些GAN变体在双模视网膜图像的图像到图像转换中的性能。评估利用Frechet Inception Distance （FID）和Kernel Inception Distance （KID）度量分数来衡量GAN变体的性能。结果表明，CycleGAN模型与CLAHE在RGB预处理图像上的表现最好，FID和KID得分最低，分别为103.49和0.038。这项研究强调了图像预处理技术在提高gan在图像翻译应用中的性能方面的巨大潜力。

{"title":"Analysis of preprocessing for Generative Adversarial Networks: A case study on color fundoscopy to fluorescein angiography image-to-image translation","authors":"Veena K.M. , Veena Mayya , Rashmi Naveen Raj , Sulatha V. Bhandary , Uma Kulkarni","doi":"10.1016/j.cmpbup.2025.100179","DOIUrl":"10.1016/j.cmpbup.2025.100179","url":null,"abstract":"<div><div>Generative Adversarial Networks (GANs) are capturing the attention of peer researchers in paired or unpaired image-to-image translation applications, particularly in the domain of retinal image processing. Additionally, there are several effective image preprocessing techniques available that can significantly improve the performance of GANs. This study examines the impact of five different image preprocessing techniques - Green Channel, CLAHE on Green Channel, CLAHE on RGB channels, Green Channel Gaussian Convolution, and RGB Gaussian Convolution - on five different GAN variants: CycleGAN, Pix2Pix GAN, CUT GAN, FastCut GAN, and NICE GAN. The study involved conducting 30 experiments to assess the performances of these GAN variants in the image-to-image translation of dual-mode retinal images. The evaluation utilized Frechet Inception Distance (FID) and Kernel Inception Distance (KID) metric scores to measure the performance of the GAN variants. The results demonstrated that the CycleGAN model achieved the best performance with CLAHE on RGB preprocessed images, achieving the lowest FID and KID scores of 103.49 and 0.038, respectively. This investigation underscores the significant potential of image preprocessing techniques in enhancing the performance of GANs in image translation applications.</div></div>","PeriodicalId":72670,"journal":{"name":"Computer methods and programs in biomedicine update","volume":"7 ","pages":"Article 100179"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143180370","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Retraction notice to “Healthcare strategies and initiatives about COVID19 in Pakistan: Telemedicine a way to look forward” [Computer Methods and Programs in Biomedicine Update, Volume 1, 2021, 100008] 对“巴基斯坦关于covid - 19的医疗保健战略和举措：远程医疗是一种展望”的撤回通知[生物医学计算机方法和程序更新，第1卷，2021,100008]

Computer methods and programs in biomedicine update

Pub Date : 2025-01-01 DOI: 10.1016/j.cmpbup.2025.100202

Ayesha Humayun , Syed Shahabuddin , Saira Afzal , Ahmad Azam Malik , Suleman Atique , Usman Iqbal

引用次数: 0

U-net based approach for pectoralis muscle segmentation in digital mammography 数字乳房x线摄影中基于U-net的胸肌分割方法

Computer methods and programs in biomedicine update

Pub Date : 2025-01-01 DOI: 10.1016/j.cmpbup.2025.100210

Francesca Angelone , Alfonso Maria Ponsiglione , Roberto Grassi , Francesco Amato , Mario Sansone

Accurate segmentation of the breast is a fundamental step in computer-aided diagnosis (CAD) systems for mammography. In particular, several tasks, such as the classification of breast density, evaluation of correct positioning of the breast, and automatic detection and classification of suspicious lesions, preliminarily require an accurate segmentation of the pectoralis muscle. This study aims to propose an automatic breast segmentation algorithm that combines traditional methods with Deep Learning methods limited only to the border region between the muscle and the breast. This type of approach allows for reducing the risk of having good overall accuracy in multi-class classification that does not reflect adequate accuracy with respect to small classes, such as the pectoralis muscle in a mammographic image. The U-Net network was therefore implemented on patches extracted along the straight line with which the muscle-breast edge was first estimated. The predicted patches are repositioned to perform an edge refinement and obtain the total breast mask, using histogram-based thresholding to segment the background from the breast. The results show Dice values equal to 0.848 ± 0.196 and Jaccard index equal to 0.774 ± 0.227 for the single patches, and Dice values equal to 0.971 ± 0.011 and Jaccard index equal to 0.944 ± 0.022 for the entire breast segmentation.

乳腺的准确分割是乳腺造影计算机辅助诊断（CAD）系统的基本步骤。特别是乳腺密度分类、乳腺正确定位评价、可疑病变自动检测分类等任务，初步需要对胸肌进行准确分割。本研究旨在提出一种将传统方法与深度学习方法相结合的自动乳房分割算法，该算法仅局限于肌肉和乳房之间的边界区域。这种类型的方法可以降低在多类别分类中具有良好的总体准确性的风险，这些分类不能反映小类别的足够准确性，例如乳房x线摄影图像中的胸肌。因此，U-Net网络是在沿着直线提取的补丁上实现的，这条直线是首次估计肌肉-乳房边缘的直线。利用基于直方图的阈值分割从乳房中分割背景，对预测的斑块进行重新定位以进行边缘细化并获得总乳房掩模。结果表明：单个斑块的Dice值为0.848±0.196，Jaccard指数为0.774±0.227；整个乳房分割的Dice值为0.971±0.011，Jaccard指数为0.944±0.022。

{"title":"U-net based approach for pectoralis muscle segmentation in digital mammography","authors":"Francesca Angelone , Alfonso Maria Ponsiglione , Roberto Grassi , Francesco Amato , Mario Sansone","doi":"10.1016/j.cmpbup.2025.100210","DOIUrl":"10.1016/j.cmpbup.2025.100210","url":null,"abstract":"<div><div>Accurate segmentation of the breast is a fundamental step in computer-aided diagnosis (CAD) systems for mammography. In particular, several tasks, such as the classification of breast density, evaluation of correct positioning of the breast, and automatic detection and classification of suspicious lesions, preliminarily require an accurate segmentation of the pectoralis muscle. This study aims to propose an automatic breast segmentation algorithm that combines traditional methods with Deep Learning methods limited only to the border region between the muscle and the breast. This type of approach allows for reducing the risk of having good overall accuracy in multi-class classification that does not reflect adequate accuracy with respect to small classes, such as the pectoralis muscle in a mammographic image. The U-Net network was therefore implemented on patches extracted along the straight line with which the muscle-breast edge was first estimated. The predicted patches are repositioned to perform an edge refinement and obtain the total breast mask, using histogram-based thresholding to segment the background from the breast. The results show Dice values equal to 0.848 ± 0.196 and Jaccard index equal to 0.774 ± 0.227 for the single patches, and Dice values equal to 0.971 ± 0.011 and Jaccard index equal to 0.944 ± 0.022 for the entire breast segmentation.</div></div>","PeriodicalId":72670,"journal":{"name":"Computer methods and programs in biomedicine update","volume":"8 ","pages":"Article 100210"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144770953","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Electronic community health information system practice and associated factors among health extension workers in South Wollo Zone, North East Ethiopia: Mixed study 埃塞俄比亚东北部南沃罗区卫生推广工作者的电子社区卫生信息系统实践及其相关因素：混合研究

Computer methods and programs in biomedicine update

Pub Date : 2025-01-01 DOI: 10.1016/j.cmpbup.2025.100215

Mohammed Ali Dawud , Mulugeta Hayelom Kalayou , Yitbarek Wasihun , Toyeb Yasine , Tewoflos Ayalew , Mulugeta Desalegn Kasaye

Background

Despite several hindering factors, such as limited internet access, unstable power supply, insufficient smart phone, lack of trainings regarding e-CHIS, affecting its implementation, electronic community health information system is a digitized type of community health information system content on a mobile platform that creates a logically interconnected programmatic content module for usage by health extension workers to register and provide high quality health services across the Nation. This study assessed electronic community health information system practice and its associated factors among health extension workers of south Wollo zone, Amhara, Ethiopia, 2024.

Methods

A facility-based cross-sectional study was conducted from 22 January 2024 to 01 April 2024. Study participants were selected by using simple random sampling for the quantitative study, and purposive sampling was employed for qualitative study. Data were collected using an interviewer-administered questionnaire. Data were entered into Epi Data version 4.6.1 and exported to SPSS version 26 for analysis. Descriptive statistics were summarized using figures and tables. Both bi-variable and multivariable logistic regression analyses were carried out. The level of significance was determined based on the AOR with 95 % CI and P-value at <0.05. Thematic analysis was used to analyze the data for qualitative part.

Results

In this study, 46 % of health extension workers showed Good practice of eCHIS. Respondents’ Knowledge, presence of electricity at the health facility, Availability of tablets for eCHIS, and work experience of participants were statistically significant associations with the practice of eCHIS.

Conclusion and Recommendation

In this study, the practice of eCHIS was 46 %. Variables such as availability of tablets, work experience, knowledge, and facility electricity supply were factors associated with electronic-health-information-system. Improving the knowledge of the participants would improve the e-CHIS practice.

尽管有一些阻碍因素，如有限的互联网接入，不稳定的电力供应，缺乏智能手机，缺乏有关电子卫生信息系统的培训，影响了它的实施，电子社区卫生信息系统是一种基于移动平台的数字化社区卫生信息系统内容，它创建了一个逻辑上相互关联的程序化内容模块，供卫生推广工作者在全国范围内注册和提供高质量的卫生服务。本研究评估了2024年埃塞俄比亚阿姆哈拉南Wollo区卫生推广工作者的电子社区卫生信息系统实践及其相关因素。方法于2024年1月22日至2024年4月1日进行以设施为基础的横断面研究。定量研究采用简单随机抽样，定性研究采用目的抽样。数据收集采用访谈者管理的问卷。数据输入Epi Data 4.6.1版本，导出到SPSS 26版本进行分析。描述性统计用图表进行汇总。进行了双变量和多变量logistic回归分析。以AOR确定显著性水平，95% CI， p值为0.05。定性部分数据采用主题分析法进行分析。结果有46%的卫生推广人员表现出良好的eCHIS行为。应答者的知识、卫生设施的电力供应、eCHIS药片的可获得性以及参与者的工作经验与eCHIS的实践具有统计上的显著相关性。结论与建议本研究中eCHIS的实施率为46%。诸如平板电脑的可用性、工作经验、知识和设施电力供应等变量是与电子卫生信息系统相关的因素。提高参与者的知识水平将会改善电子卫生信息系统的实践。

{"title":"Electronic community health information system practice and associated factors among health extension workers in South Wollo Zone, North East Ethiopia: Mixed study","authors":"Mohammed Ali Dawud , Mulugeta Hayelom Kalayou , Yitbarek Wasihun , Toyeb Yasine , Tewoflos Ayalew , Mulugeta Desalegn Kasaye","doi":"10.1016/j.cmpbup.2025.100215","DOIUrl":"10.1016/j.cmpbup.2025.100215","url":null,"abstract":"<div><h3>Background</h3><div>Despite several hindering factors, such as limited internet access, unstable power supply, insufficient smart phone, lack of trainings regarding e-CHIS, affecting its implementation, electronic community health information system is a digitized type of community health information system content on a mobile platform that creates a logically interconnected programmatic content module for usage by health extension workers to register and provide high quality health services across the Nation. This study assessed electronic community health information system practice and its associated factors among health extension workers of south Wollo zone, Amhara, Ethiopia, 2024.</div></div><div><h3>Methods</h3><div>A facility-based cross-sectional study was conducted from 22 January 2024 to 01 April 2024. Study participants were selected by using simple random sampling for the quantitative study, and purposive sampling was employed for qualitative study. Data were collected using an interviewer-administered questionnaire. Data were entered into Epi Data version 4.6.1 and exported to SPSS version 26 for analysis. Descriptive statistics were summarized using figures and tables. Both bi-variable and multivariable logistic regression analyses were carried out. The level of significance was determined based on the AOR with 95 % CI and P-value at <0.05. Thematic analysis was used to analyze the data for qualitative part.</div></div><div><h3>Results</h3><div>In this study, 46 % of health extension workers showed Good practice of eCHIS. Respondents’ Knowledge, presence of electricity at the health facility, Availability of tablets for eCHIS, and work experience of participants were statistically significant associations with the practice of eCHIS.</div></div><div><h3>Conclusion and Recommendation</h3><div>In this study, the practice of eCHIS was 46 %. Variables such as availability of tablets, work experience, knowledge, and facility electricity supply were factors associated with electronic-health-information-system. Improving the knowledge of the participants would improve the e-CHIS practice.</div></div>","PeriodicalId":72670,"journal":{"name":"Computer methods and programs in biomedicine update","volume":"8 ","pages":"Article 100215"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144750274","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Predicting Alzheimer's Disease onset: A machine learning framework for early diagnosis using biomarker data 预测阿尔茨海默病发病：使用生物标志物数据进行早期诊断的机器学习框架

Computer methods and programs in biomedicine update

Pub Date : 2025-01-01 DOI: 10.1016/j.cmpbup.2025.100209

Shehu Mohammed, Neha Malhotra

Alzheimer’s Disease (AD) is a significant global health issue, and the current diagnostic techniques cannot diagnose the disease at its early stages, hence the difficulty of early therapeutic management. In response to the formulated research problem, this study articulates a new multimodal machine-learning framework for early AD diagnosis. The main goal is to combine multiple biomarkers: neuroimaging, CSF, genetic, and longitudinal cognitive data and develop a robust model for accurate early AD diagnosis. The importance of this work is in the opportunity to shift diagnostic paradigms by employing deep learning algorithms, including CNNs, LSTM networks, and GNNs to analyze spatial, temporal, and relational patterns across multi-modal data. The methodology involves federated learning and domain adaptation with GANs to integrate data from multiple centers with the patient’s privacy intact. It shows that the proposed multimodal model is superior to single-modality models with an AUC-ROC of 0.94 and reveals that hippocampal volume and plasma p-tau are the most informative biomarkers in the early diagnosis of AD. The study’s implications indicate that combining multimodal data improves diagnostic accuracy and clinical relevance by providing a roadmap to developing personalized medicine and better patient care. Future work will be aimed at increasing the variability of the dataset and the clinical trials to test the model to improve its applicability and performance in actual practice.

阿尔茨海默病（Alzheimer 's Disease， AD）是一个重大的全球性健康问题，目前的诊断技术无法在疾病的早期阶段进行诊断，因此难以进行早期治疗管理。为了回应既定的研究问题，本研究阐明了一种新的多模态机器学习框架，用于早期AD诊断。主要目标是结合多种生物标志物：神经影像学、脑脊液、遗传和纵向认知数据，并建立一个准确的早期AD诊断的稳健模型。这项工作的重要性在于，通过使用深度学习算法（包括cnn、LSTM网络和gnn）来分析多模态数据的空间、时间和关系模式，有机会改变诊断范式。该方法包括联合学习和gan的领域适应，以整合来自多个中心的数据，同时不影响患者的隐私。结果表明，多模态模型优于单模态模型，AUC-ROC为0.94，表明海马体积和血浆p-tau是AD早期诊断中最有信息的生物标志物。该研究的意义表明，通过为开发个性化医疗和更好的患者护理提供路线图，结合多模式数据可以提高诊断准确性和临床相关性。未来的工作将旨在增加数据集的可变性和临床试验来测试模型，以提高其在实际实践中的适用性和性能。

{"title":"Predicting Alzheimer's Disease onset: A machine learning framework for early diagnosis using biomarker data","authors":"Shehu Mohammed, Neha Malhotra","doi":"10.1016/j.cmpbup.2025.100209","DOIUrl":"10.1016/j.cmpbup.2025.100209","url":null,"abstract":"<div><div>Alzheimer’s Disease (AD) is a significant global health issue, and the current diagnostic techniques cannot diagnose the disease at its early stages, hence the difficulty of early therapeutic management. In response to the formulated research problem, this study articulates a new multimodal machine-learning framework for early AD diagnosis. The main goal is to combine multiple biomarkers: neuroimaging, CSF, genetic, and longitudinal cognitive data and develop a robust model for accurate early AD diagnosis. The importance of this work is in the opportunity to shift diagnostic paradigms by employing deep learning algorithms, including CNNs, LSTM networks, and GNNs to analyze spatial, temporal, and relational patterns across multi-modal data. The methodology involves federated learning and domain adaptation with GANs to integrate data from multiple centers with the patient’s privacy intact. It shows that the proposed multimodal model is superior to single-modality models with an AUC-ROC of 0.94 and reveals that hippocampal volume and plasma p-tau are the most informative biomarkers in the early diagnosis of AD. The study’s implications indicate that combining multimodal data improves diagnostic accuracy and clinical relevance by providing a roadmap to developing personalized medicine and better patient care. Future work will be aimed at increasing the variability of the dataset and the clinical trials to test the model to improve its applicability and performance in actual practice.</div></div>","PeriodicalId":72670,"journal":{"name":"Computer methods and programs in biomedicine update","volume":"8 ","pages":"Article 100209"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144750303","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Integrative in Silico modeling for mTOR inhibition: From ridge classifiers to descriptor-free deep neural networks mTOR抑制的集成计算机建模：从脊分类器到无描述符的深度神经网络

Computer methods and programs in biomedicine update

Pub Date : 2025-01-01 DOI: 10.1016/j.cmpbup.2025.100208

Seyed Alireza Khanghahi , Hadi Kamkar , Seyedehsamaneh Shojaeilangari , Abdollah Allahverdi , Parviz Abdolmaleki

Inhibiting the mammalian Target of Rapamycin (mTOR) represents a promising strategy in cancer therapy due to its crucial role in cell growth, survival, and metabolism. Using a variety of quantitative structure-activity relationship (QSAR) models, we present a comprehensive comparison of deep learning (DL) and classical machine learning (ML) techniques for modeling mTOR inhibitor activity. Unlike prior studies that focused on specific algorithms or limited descriptors, we benchmark a wide range of models, from traditional models like Random Forest, logistic regression, and SVM to modern algorithms like CNNs, GRUs, and LSTMs, on both descriptor-based features obtained by Dragon and descriptor-free inputs, including raw SMILES string, and Morgan fingerprints. This comprehensive analysis provides a robust foundation for using the best QSAR models specific to mTOR inhibition. Our findings revealed that while the Random Forest classifier achieved the highest accuracy among all models (0.9290 accuracy, 0.8940 F1-score, 0.9737 AUC), DL methods also demonstrated strong predictive capabilities, with nearly all models attaining an accuracy above 0.90. Among the DL models, CNN-QSAR using Morgan fingerprints achieved the highest accuracy (0.9271), F1-score (0.8950), and AUC (0.9696), demonstrating its effectiveness in capturing structural characteristics. The GRU-QSAR and LSTM-QSAR models, which utilized tokenized SMILES, achieved accuracies of 0.9002 and 0.9021, F1-scores of 0.8595 and 0.8603, and AUCs of 0.9270 and 0.9529, respectively, leveraging their ability to process sequential data.

抑制哺乳动物雷帕霉素靶点（mTOR）是一种很有前景的癌症治疗策略，因为它在细胞生长、存活和代谢中起着至关重要的作用。利用各种定量结构-活性关系（QSAR）模型，我们全面比较了深度学习（DL）和经典机器学习（ML）技术对mTOR抑制剂活性的建模。与之前专注于特定算法或有限描述符的研究不同，我们对广泛的模型进行了基准测试，从随机森林、逻辑回归和SVM等传统模型到cnn、gru和LSTMs等现代算法，包括Dragon获得的基于描述符的特征和无描述符的输入，包括原始SMILES字符串和Morgan指纹。这一综合分析为使用mTOR抑制的最佳QSAR模型提供了坚实的基础。我们的研究结果表明，虽然随机森林分类器在所有模型中准确率最高（0.9290准确率，0.8940 f1分数，0.9737 AUC），但DL方法也表现出很强的预测能力，几乎所有模型的准确率都在0.90以上。在深度学习模型中，采用Morgan指纹的CNN-QSAR准确率最高（0.9271），f1得分最高（0.8950），AUC最高（0.9696），显示了其捕获结构特征的有效性。使用标记化SMILES的GRU-QSAR和LSTM-QSAR模型，利用其处理序列数据的能力，准确率分别为0.9002和0.9021，f1得分分别为0.8595和0.8603，auc分别为0.9270和0.9529。

{"title":"Integrative in Silico modeling for mTOR inhibition: From ridge classifiers to descriptor-free deep neural networks","authors":"Seyed Alireza Khanghahi , Hadi Kamkar , Seyedehsamaneh Shojaeilangari , Abdollah Allahverdi , Parviz Abdolmaleki","doi":"10.1016/j.cmpbup.2025.100208","DOIUrl":"10.1016/j.cmpbup.2025.100208","url":null,"abstract":"<div><div>Inhibiting the mammalian Target of Rapamycin (mTOR) represents a promising strategy in cancer therapy due to its crucial role in cell growth, survival, and metabolism. Using a variety of quantitative structure-activity relationship (QSAR) models, we present a comprehensive comparison of deep learning (DL) and classical machine learning (ML) techniques for modeling mTOR inhibitor activity. Unlike prior studies that focused on specific algorithms or limited descriptors, we benchmark a wide range of models, from traditional models like Random Forest, logistic regression, and SVM to modern algorithms like CNNs, GRUs, and LSTMs, on both descriptor-based features obtained by Dragon and descriptor-free inputs, including raw SMILES string, and Morgan fingerprints. This comprehensive analysis provides a robust foundation for using the best QSAR models specific to mTOR inhibition. Our findings revealed that while the Random Forest classifier achieved the highest accuracy among all models (0.9290 accuracy, 0.8940 F1-score, 0.9737 AUC), DL methods also demonstrated strong predictive capabilities, with nearly all models attaining an accuracy above 0.90. Among the DL models, CNN-QSAR using Morgan fingerprints achieved the highest accuracy (0.9271), F1-score (0.8950), and AUC (0.9696), demonstrating its effectiveness in capturing structural characteristics. The GRU-QSAR and LSTM-QSAR models, which utilized tokenized SMILES, achieved accuracies of 0.9002 and 0.9021, F1-scores of 0.8595 and 0.8603, and AUCs of 0.9270 and 0.9529, respectively, leveraging their ability to process sequential data.</div></div>","PeriodicalId":72670,"journal":{"name":"Computer methods and programs in biomedicine update","volume":"8 ","pages":"Article 100208"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144653529","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Enhancing diabetes prediction performance using feature selection based on grey wolf optimizer with autophagy mechanism 基于自噬机制的灰狼优化器特征选择提高糖尿病预测性能

Computer methods and programs in biomedicine update

Pub Date : 2025-01-01 DOI: 10.1016/j.cmpbup.2025.100207

Sirmayanti , Pulung Hendro Prastyo , Mahyati

Diabetes mellitus, often called a silent killer, is a chronic condition characterized by insufficient insulin production and elevated blood sugar levels, leading to complications in vital organs such as the nerves, eyes, and kidneys. Machine learning is a powerful tool for predicting diabetes; however, noisy features can negatively impact its accuracy, making an effective feature selection essential. This study proposes an improved feature selection approach for diabetes prediction, leveraging the Grey Wolf Optimizer with an integrated Autophagy Mechanism (GWO-AM) on the Pima Indian Diabetes Dataset. The autophagy mechanism, inspired by cellular self-degradation and recycling, is incorporated into GWO to enhance exploration and exploitation. The method was also tested on glioma and lung cancer datasets to assess scalability. Comprehensive experiments demonstrate that GWO-AM significantly improves prediction accuracy while reducing the number of selected features. For the diabetes dataset, GWO-AM achieved an accuracy of 90.91 %, outperforming existing methods. It also excelled in the glioma and lung cancer datasets, highlighting its potential for application to other medical datasets.

糖尿病通常被称为“无声杀手”，是一种以胰岛素分泌不足和血糖水平升高为特征的慢性疾病，会导致神经、眼睛和肾脏等重要器官的并发症。机器学习是预测糖尿病的有力工具；然而，噪声特征会对其精度产生负面影响，因此有效的特征选择至关重要。本研究提出了一种改进的糖尿病预测特征选择方法，利用灰狼优化器与集成自噬机制（GWO-AM）在皮马印第安人糖尿病数据集上。自噬机制受细胞自降解和循环利用的启发，被纳入GWO，以加强探索和开发。该方法还在神经胶质瘤和肺癌数据集上进行了测试，以评估可扩展性。综合实验表明，GWO-AM在减少特征选择数量的同时显著提高了预测精度。对于糖尿病数据集，GWO-AM的准确率达到90.91%，优于现有方法。它在神经胶质瘤和肺癌数据集方面也表现出色，突出了其应用于其他医疗数据集的潜力。

{"title":"Enhancing diabetes prediction performance using feature selection based on grey wolf optimizer with autophagy mechanism","authors":"Sirmayanti , Pulung Hendro Prastyo , Mahyati","doi":"10.1016/j.cmpbup.2025.100207","DOIUrl":"10.1016/j.cmpbup.2025.100207","url":null,"abstract":"<div><div>Diabetes mellitus, often called a silent killer, is a chronic condition characterized by insufficient insulin production and elevated blood sugar levels, leading to complications in vital organs such as the nerves, eyes, and kidneys. Machine learning is a powerful tool for predicting diabetes; however, noisy features can negatively impact its accuracy, making an effective feature selection essential. This study proposes an improved feature selection approach for diabetes prediction, leveraging the Grey Wolf Optimizer with an integrated Autophagy Mechanism (GWO-AM) on the Pima Indian Diabetes Dataset. The autophagy mechanism, inspired by cellular self-degradation and recycling, is incorporated into GWO to enhance exploration and exploitation. The method was also tested on glioma and lung cancer datasets to assess scalability. Comprehensive experiments demonstrate that GWO-AM significantly improves prediction accuracy while reducing the number of selected features. For the diabetes dataset, GWO-AM achieved an accuracy of 90.91 %, outperforming existing methods. It also excelled in the glioma and lung cancer datasets, highlighting its potential for application to other medical datasets.</div></div>","PeriodicalId":72670,"journal":{"name":"Computer methods and programs in biomedicine update","volume":"8 ","pages":"Article 100207"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144680167","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Optimized soft-voting CNN ensemble using particle swarm optimization for endometrial cancer histopathology classification 基于粒子群优化的软投票CNN集合用于子宫内膜癌组织病理学分类

Computer methods and programs in biomedicine update

Pub Date : 2025-01-01 DOI: 10.1016/j.cmpbup.2025.100217

Firas Ibrahim AlZobi , Khalid Mansour , Ahmad Nasayreh , Ghassan Samara , Neda’a Alsalman , Ayah Bashkami , Aseel Smerat , Khalid M.O. Nahar

The heterogeneity of endometrial cancer tissue presents a significant obstacle to accurate automated classification using histopathological images. While ensemble methods are a promising alternative to single Convolutional Neural Networks (CNNs), we introduce PSO-SV (Particle Swarm Optimization–Soft Voting), a novel framework that adaptively fuses the outputs of MobileNetV2, VGG19, DenseNet121, Swin Transformer, and Vision Transformer (ViT). Our key innovation is the use of Particle Swarm Optimization to dynamically determine the optimal contribution of each model in a soft-voting ensemble. We validated PSO-SV on two datasets, the first one consists from 11,977 tiles from 95 whole-slide images (WSIs) obtained from The Cancer Genome Atlas Uterine Corpus Endometrial Carcinoma (TCGA-UCEC) project, the other dataset consists of 3,302 images from 498 patients, which are categorized into four classes. The proposed framework achieved outstanding results, including 99.67% accuracy, a 99.67% F1-score, and an Area Under the Curve (AUC) of 99.9% on the first dataset and 99% for all metrics for the second dataset. It consistently outperformed all three individual CNNs and a traditional hard-voting ensemble, highlighting its ability to synergistically combine complementary model strengths. The PSO-SV framework offers a powerful and clinically promising approach for robust endometrial cancer classification.

子宫内膜癌组织的异质性对使用组织病理学图像进行准确的自动分类提出了重大障碍。虽然集成方法是单一卷积神经网络（cnn）的一种有前途的替代方法，但我们引入了PSO-SV（粒子群优化-软投票），这是一种自适应融合MobileNetV2， VGG19, DenseNet121， Swin Transformer和Vision Transformer （ViT）输出的新框架。我们的关键创新是使用粒子群优化来动态确定每个模型在软投票集合中的最佳贡献。我们在两个数据集上验证了PSO-SV，第一个数据集包括来自癌症基因组图谱子宫肌体子宫内膜癌（TCGA-UCEC）项目的95张全片图像（WSIs）中的11,977张，另一个数据集包括来自498名患者的3,302张图像，分为四类。提出的框架取得了出色的结果，包括99.67%的准确率，99.67%的f1分数，第一个数据集的曲线下面积（AUC）为99.9%，第二个数据集的所有指标为99%。它始终优于所有三个单独的cnn和传统的硬投票集合，突出了其协同结合互补模型优势的能力。PSO-SV框架为子宫内膜癌分类提供了一种强大的、有临床前景的方法。

{"title":"Optimized soft-voting CNN ensemble using particle swarm optimization for endometrial cancer histopathology classification","authors":"Firas Ibrahim AlZobi , Khalid Mansour , Ahmad Nasayreh , Ghassan Samara , Neda’a Alsalman , Ayah Bashkami , Aseel Smerat , Khalid M.O. Nahar","doi":"10.1016/j.cmpbup.2025.100217","DOIUrl":"10.1016/j.cmpbup.2025.100217","url":null,"abstract":"<div><div>The heterogeneity of endometrial cancer tissue presents a significant obstacle to accurate automated classification using histopathological images. While ensemble methods are a promising alternative to single Convolutional Neural Networks (CNNs), we introduce PSO-SV (Particle Swarm Optimization–Soft Voting), a novel framework that adaptively fuses the outputs of MobileNetV2, VGG19, DenseNet121, Swin Transformer, and Vision Transformer (ViT). Our key innovation is the use of Particle Swarm Optimization to dynamically determine the optimal contribution of each model in a soft-voting ensemble. We validated PSO-SV on two datasets, the first one consists from 11,977 tiles from 95 whole-slide images (WSIs) obtained from The Cancer Genome Atlas Uterine Corpus Endometrial Carcinoma (TCGA-UCEC) project, the other dataset consists of 3,302 images from 498 patients, which are categorized into four classes. The proposed framework achieved outstanding results, including 99.67% accuracy, a 99.67% F1-score, and an Area Under the Curve (AUC) of 99.9% on the first dataset and 99% for all metrics for the second dataset. It consistently outperformed all three individual CNNs and a traditional hard-voting ensemble, highlighting its ability to synergistically combine complementary model strengths. The PSO-SV framework offers a powerful and clinically promising approach for robust endometrial cancer classification.</div></div>","PeriodicalId":72670,"journal":{"name":"Computer methods and programs in biomedicine update","volume":"8 ","pages":"Article 100217"},"PeriodicalIF":0.0,"publicationDate":"2025-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144912933","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0