Healthcare analytics (New York, N.Y.)最新文献_第6页

An analytical review of blood supply chain management literature through science mapping and strategic diagrams 通过科学制图和战略图表对血液供应链管理文献进行分析回顾

Healthcare analytics (New York, N.Y.)

Pub Date : 2025-12-01 Epub Date: 2025-11-07 DOI: 10.1016/j.health.2025.100433

Nurhadi Siswanto , Ivan Darma Wangsa , Ahmed Raecky Baihaqy , Patdono Suwignjo , Vincent F. Yu

The increasing complexity of healthcare systems and the critical role of blood supply chain (BSC) management in ensuring patient safety have motivated the need for a systematic synthesis of research in this domain. This study reviews the literature and presents a bibliometric and systematic literature review of BSC management studies. This study aimed to investigate the evolution of BSC management over twelve years (2014–2025). One hundred ninety-four published articles were retrieved from the Scopus database based on the inclusion criteria. Using bibliometric techniques, descriptive analysis was conducted to examine publication trends, citations, leading journals, influential authors, and contributing countries. Science mapping and strategic diagram analysis were employed to identify and visualize keyword networks, enabling the recognition of thematic clusters and their evolution. The results highlight five dominant research streams: donor engagement, demand forecasting, inventory and logistics optimization, resilience to disruptions, and the application of digital technologies such as artificial intelligence, machine learning, and blockchain. The analysis also reveals emerging sustainability and circular economy themes that remain underexplored, pointing to significant research gaps. This study contributes to theory by providing a structured knowledge map of BSC research and advancing understanding of its evolution. It offers practical insights for policymakers, blood banks, and healthcare managers to enhance the resilience, sustainability, and efficiency of BSC operations.

日益复杂的医疗系统和血液供应链（BSC）管理在确保患者安全方面的关键作用，促使需要在这一领域进行系统的综合研究。本研究回顾文献，对平衡记分卡管理研究进行文献计量学和系统的文献回顾。本研究旨在探讨平衡记分卡管理在过去12年（2014-2025）中的演变。根据纳入标准从Scopus数据库检索194篇已发表的文章。使用文献计量学技术，进行了描述性分析，以检查出版趋势、引用、主要期刊、有影响力的作者和贡献国家。利用科学制图和策略图分析对关键词网络进行识别和可视化，实现主题聚类及其演化的识别。结果突出了五个主要的研究流：捐助者参与、需求预测、库存和物流优化、中断恢复能力以及人工智能、机器学习和区块链等数字技术的应用。该分析还揭示了新兴的可持续性和循环经济主题仍未得到充分探索，指出了重大的研究空白。本研究通过提供平衡记分卡研究的结构化知识图谱和促进对其演变的理解，为理论做出了贡献。它为政策制定者、血库和医疗保健管理人员提供了实用的见解，以增强平衡计分卡运营的弹性、可持续性和效率。

{"title":"An analytical review of blood supply chain management literature through science mapping and strategic diagrams","authors":"Nurhadi Siswanto , Ivan Darma Wangsa , Ahmed Raecky Baihaqy , Patdono Suwignjo , Vincent F. Yu","doi":"10.1016/j.health.2025.100433","DOIUrl":"10.1016/j.health.2025.100433","url":null,"abstract":"<div><div>The increasing complexity of healthcare systems and the critical role of blood supply chain (BSC) management in ensuring patient safety have motivated the need for a systematic synthesis of research in this domain. This study reviews the literature and presents a bibliometric and systematic literature review of BSC management studies. This study aimed to investigate the evolution of BSC management over twelve years (2014–2025). One hundred ninety-four published articles were retrieved from the Scopus database based on the inclusion criteria. Using bibliometric techniques, descriptive analysis was conducted to examine publication trends, citations, leading journals, influential authors, and contributing countries. Science mapping and strategic diagram analysis were employed to identify and visualize keyword networks, enabling the recognition of thematic clusters and their evolution. The results highlight five dominant research streams: donor engagement, demand forecasting, inventory and logistics optimization, resilience to disruptions, and the application of digital technologies such as artificial intelligence, machine learning, and blockchain. The analysis also reveals emerging sustainability and circular economy themes that remain underexplored, pointing to significant research gaps. This study contributes to theory by providing a structured knowledge map of BSC research and advancing understanding of its evolution. It offers practical insights for policymakers, blood banks, and healthcare managers to enhance the resilience, sustainability, and efficiency of BSC operations.</div></div>","PeriodicalId":73222,"journal":{"name":"Healthcare analytics (New York, N.Y.)","volume":"8 ","pages":"Article 100433"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145519214","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

An integrated deep learning approach for enhancing brain tumor diagnosis 一种增强脑肿瘤诊断的集成深度学习方法

Healthcare analytics (New York, N.Y.)

Pub Date : 2025-12-01 Epub Date: 2025-09-25 DOI: 10.1016/j.health.2025.100421

Rabeya Bashri Sumona , John Pritom Biswas , Ahmed Shafkat , Md Mahbubur Rahman , Md Omor Faruk , Yaqoob Majeed

The diagnosis of a brain tumor poses a significant challenge due to the varied manifestations of tumors and their impact on patient health. Traditional Magnetic Resonance Imaging (MRI) based methods are time-consuming, expensive, and highly reliant on radiologists’ expertise. Automated and reliable classification techniques are crucial to enhancing diagnostic accuracy, improving patient outcomes, and ensuring timely detection. This study introduces RDXNet, a hybrid deep learning model that integrates ResNet50, DenseNet121, and Xception to improve the classification of multiclass brain tumors. We utilized three publicly available datasets which are Br35H :: Brain Tumor Detection 2020, Figshare Brain Tumor Dataset, and Radiopaedia MRI Scans, combining 7,023 MRI images in four categories: glioma, meningioma, no tumor, and pituitary tumor. After evaluating individual models, we integrated them into RDXNet using feature fusion and transfer learning. Our model achieves an accuracy of 94%, exceeding the performance of individual models and mitigating overfitting. To validate robustness, K-Fold Cross-Validation was conducted across multiple data splits. Additionally, Grad-CAM-based visualizations were employed to enhance interpretability, enabling clinicians to understand the model’s decision-making. Using hybrid deep learning techniques, RDXNet significantly improves classification performance and reliability. This study demonstrates the potential of Artificial Intelligence (AI)-driven computer-aided diagnosis (CAD) systems to support radiologists, enabling faster and more accurate brain tumor identification, ultimately improving patient outcomes. Our proposed hybrid model, RDXNet outperforms individual architectures in multiclass brain tumor classification, achieving state-of-the-art performance and contributing towards faster, more reliable automated diagnosis.

由于肿瘤的各种表现及其对患者健康的影响，脑肿瘤的诊断提出了一个重大挑战。传统的基于磁共振成像（MRI）的方法耗时、昂贵，并且高度依赖放射科医生的专业知识。自动化和可靠的分类技术对于提高诊断准确性、改善患者预后和确保及时检测至关重要。本研究引入RDXNet，这是一种集成了ResNet50、DenseNet121和Xception的混合深度学习模型，用于改进多类别脑肿瘤的分类。我们利用Br35H:: Brain Tumor Detection 2020、Figshare Brain Tumor Dataset和Radiopaedia MRI Scans三个公开可用的数据集，结合了胶质瘤、脑膜瘤、无肿瘤和垂体瘤四类7,023张MRI图像。在评估单个模型之后，我们使用特征融合和迁移学习将它们集成到RDXNet中。我们的模型达到了94%的准确率，超过了单个模型的性能并减轻了过拟合。为了验证稳健性，对多个数据分割进行K-Fold交叉验证。此外，采用基于grad - cam的可视化来增强可解释性，使临床医生能够理解模型的决策。使用混合深度学习技术，RDXNet显著提高了分类性能和可靠性。这项研究证明了人工智能（AI）驱动的计算机辅助诊断（CAD）系统在支持放射科医生、实现更快、更准确的脑肿瘤识别、最终改善患者预后方面的潜力。我们提出的混合模型RDXNet在多类别脑肿瘤分类中优于单个架构，实现了最先进的性能，并有助于更快，更可靠的自动化诊断。

{"title":"An integrated deep learning approach for enhancing brain tumor diagnosis","authors":"Rabeya Bashri Sumona , John Pritom Biswas , Ahmed Shafkat , Md Mahbubur Rahman , Md Omor Faruk , Yaqoob Majeed","doi":"10.1016/j.health.2025.100421","DOIUrl":"10.1016/j.health.2025.100421","url":null,"abstract":"<div><div>The diagnosis of a brain tumor poses a significant challenge due to the varied manifestations of tumors and their impact on patient health. Traditional Magnetic Resonance Imaging (MRI) based methods are time-consuming, expensive, and highly reliant on radiologists’ expertise. Automated and reliable classification techniques are crucial to enhancing diagnostic accuracy, improving patient outcomes, and ensuring timely detection. This study introduces RDXNet, a hybrid deep learning model that integrates ResNet50, DenseNet121, and Xception to improve the classification of multiclass brain tumors. We utilized three publicly available datasets which are Br35H :: Brain Tumor Detection 2020, Figshare Brain Tumor Dataset, and Radiopaedia MRI Scans, combining 7,023 MRI images in four categories: glioma, meningioma, no tumor, and pituitary tumor. After evaluating individual models, we integrated them into RDXNet using feature fusion and transfer learning. Our model achieves an accuracy of 94%, exceeding the performance of individual models and mitigating overfitting. To validate robustness, K-Fold Cross-Validation was conducted across multiple data splits. Additionally, Grad-CAM-based visualizations were employed to enhance interpretability, enabling clinicians to understand the model’s decision-making. Using hybrid deep learning techniques, RDXNet significantly improves classification performance and reliability. This study demonstrates the potential of Artificial Intelligence (AI)-driven computer-aided diagnosis (CAD) systems to support radiologists, enabling faster and more accurate brain tumor identification, ultimately improving patient outcomes. Our proposed hybrid model, RDXNet outperforms individual architectures in multiclass brain tumor classification, achieving state-of-the-art performance and contributing towards faster, more reliable automated diagnosis.</div></div>","PeriodicalId":73222,"journal":{"name":"Healthcare analytics (New York, N.Y.)","volume":"8 ","pages":"Article 100421"},"PeriodicalIF":0.0,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145219005","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

A machine learning model for automated contact tracing during disease outbreaks 疾病暴发期间用于自动追踪接触者的机器学习模型

Healthcare analytics (New York, N.Y.)

Pub Date : 2025-06-01 Epub Date: 2025-03-08 DOI: 10.1016/j.health.2025.100389

Zeyad Aklah , Amean Al-Safi , Marwa H. Abdali , Khalid Al-jabery

This study aims to develop and evaluate a conceptual model for assessing the Risk of Infection (ROI) within the context of automated digital contact tracing during pandemics. The proposed model incorporates five input parameters: distance, overlap time, contamination interval, incubation time, and contact facility size. These parameters capture various aspects of disease transmission dynamics. The model employs logistic functions to quantify the influence of each parameter on the overall ROI. The evaluation of the model involves two methods: a partial evaluation to observe the impact of parameter pairs on ROI, and a full evaluation, which is trained on a dataset of 24,000 simulated scenarios to identify central clusters for high, medium, and low-risk categories using K-means and the Hidden Markov Model. Additionally, the model is tested on another 16,000 simulated scenarios to assess its overall performance. Results indicate that the Hidden Markov Model categorizes 63.8% of the testing dataset as low risk, 20.7% as medium risk, and 15.5% as high risk. In contrast, K-means classifies 44.3% as low risk, 30.7% as medium risk, and 25% as high risk. The evaluation metrics favor the Hidden Markov Model, which demonstrates higher performance in terms of Log-Likelihood, with a value of 50,688, as well as in the Akaike Information Criterion (AIC) and Bayesian Information Criterion (BIC), with values of -101,365.6430 and -101,319.5609, respectively. In both evaluations, the results validate the model’s ability to automate digital contact tracing based on the input parameters. Future studies could explore classification accuracy using real contact tracing datasets. The proposed approach enhances the efficiency of public health authorities by directing their efforts toward individuals with the highest risk of infection, rather than applying the same level of intervention indiscriminately to everyone.

本研究旨在开发和评估在大流行期间自动数字接触者追踪背景下评估感染风险（ROI）的概念模型。提出的模型包含五个输入参数：距离、重叠时间、污染间隔、孵化时间和接触设施大小。这些参数反映了疾病传播动力学的各个方面。该模型采用logistic函数来量化各参数对整体ROI的影响。模型的评估包括两种方法：部分评估，观察参数对对ROI的影响；全面评估，在24,000个模拟场景的数据集上进行训练，使用K-means和隐马尔可夫模型识别高、中、低风险类别的中心聚类。此外，该模型还在另外16,000个模拟场景中进行了测试，以评估其整体性能。结果表明，隐马尔可夫模型将测试数据集的63.8%分类为低风险，20.7%为中等风险，15.5%为高风险。相比之下，K-means将44.3%分类为低风险，30.7%为中风险，25%为高风险。评价指标倾向于隐马尔可夫模型，它在对数似然方面表现出更高的性能，其值为50,688，而赤池信息准则（AIC）和贝叶斯信息准则（BIC）的值分别为-101,365.6430和-101,319.5609。在这两个评估中，结果验证了模型基于输入参数自动数字接触跟踪的能力。未来的研究可以利用真实的接触追踪数据集来探索分类的准确性。拟议的方法提高了公共卫生当局的效率，将工作重点放在感染风险最高的个人身上，而不是不分青红皂白地对所有人实施同样水平的干预。

{"title":"A machine learning model for automated contact tracing during disease outbreaks","authors":"Zeyad Aklah , Amean Al-Safi , Marwa H. Abdali , Khalid Al-jabery","doi":"10.1016/j.health.2025.100389","DOIUrl":"10.1016/j.health.2025.100389","url":null,"abstract":"<div><div>This study aims to develop and evaluate a conceptual model for assessing the Risk of Infection (ROI) within the context of automated digital contact tracing during pandemics. The proposed model incorporates five input parameters: distance, overlap time, contamination interval, incubation time, and contact facility size. These parameters capture various aspects of disease transmission dynamics. The model employs logistic functions to quantify the influence of each parameter on the overall ROI. The evaluation of the model involves two methods: a partial evaluation to observe the impact of parameter pairs on ROI, and a full evaluation, which is trained on a dataset of 24,000 simulated scenarios to identify central clusters for high, medium, and low-risk categories using K-means and the Hidden Markov Model. Additionally, the model is tested on another 16,000 simulated scenarios to assess its overall performance. Results indicate that the Hidden Markov Model categorizes 63.8% of the testing dataset as low risk, 20.7% as medium risk, and 15.5% as high risk. In contrast, K-means classifies 44.3% as low risk, 30.7% as medium risk, and 25% as high risk. The evaluation metrics favor the Hidden Markov Model, which demonstrates higher performance in terms of Log-Likelihood, with a value of 50,688, as well as in the Akaike Information Criterion (AIC) and Bayesian Information Criterion (BIC), with values of -101,365.6430 and -101,319.5609, respectively. In both evaluations, the results validate the model’s ability to automate digital contact tracing based on the input parameters. Future studies could explore classification accuracy using real contact tracing datasets. The proposed approach enhances the efficiency of public health authorities by directing their efforts toward individuals with the highest risk of infection, rather than applying the same level of intervention indiscriminately to everyone.</div></div>","PeriodicalId":73222,"journal":{"name":"Healthcare analytics (New York, N.Y.)","volume":"7 ","pages":"Article 100389"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143619509","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

An interpretable machine learning study for developing a binary classifier for predicting rehospitalization from skilled nursing facilities 一项可解释的机器学习研究，用于开发用于预测熟练护理机构再住院的二元分类器

Healthcare analytics (New York, N.Y.)

Pub Date : 2025-06-01 Epub Date: 2025-02-15 DOI: 10.1016/j.health.2025.100387

Zhouyang Lou , Zachary Hass , Nan Kong

Reducing hospital readmissions for older adults discharged to a skilled nursing facility (SNF) is important to the Unites States (U.S.) both from financial and care quality perspectives. To identify potential risk factors, researchers have used data from claims, national surveys, and administrative databases to train models that predict hospital readmissions that occur within 30 days of discharge. Machine learning techniques hold promise for this binary classification task. However, analysis pipelines are underdeveloped in data balancing, feature selection, and model interpretability. In this paper, we utilized individual resident-level data from the Long-Term Care Minimum Data Set (MDS) collected from SNFs in a midwestern U.S. state (n = 93,058). We further triangulated this data with publicly available facility quality and staffing data from the Nursing Home Compares tool of the Medicare.gov and facility neighborhood data from the National Neighborhood Data Archive. We compared several machine learning models, data balancing techniques, and feature selection methods, for the prediction task. We found that XGBoost, with Synthetic Minority Oversampling Edited Nearest Neighbor (SMOTE-ENN) to balance the data, and hierarchical clustering based on spearman correlation to select the features that produces the best prediction performance. We then used SHapley Additive exPlanations (SHAP) values to identify features that contribute most to the performance and used partial dependence plots to examine curvilinear and moderating relationships between features and the risk of 30-day rehospitalization.

从财务和护理质量的角度来看，减少老年人出院到专业护理机构（SNF）的再入院率对美国（U.S.）都很重要。为了确定潜在的风险因素，研究人员使用来自索赔、国家调查和行政数据库的数据来训练模型，预测出院后30天内再次住院的情况。机器学习技术为这种二元分类任务带来了希望。然而，分析管道在数据平衡、特征选择和模型可解释性方面还不发达。在本文中，我们利用了从美国中西部一个州的snf收集的长期护理最低数据集（MDS）中的个体居民水平数据（n = 93,058）。我们进一步将这些数据与Medicare.gov的养老院比较工具中公开的设施质量和人员配备数据以及国家社区数据档案中的设施社区数据进行三角分析。为了预测任务，我们比较了几种机器学习模型、数据平衡技术和特征选择方法。我们发现XGBoost使用合成少数派过采样编辑最近邻（SMOTE-ENN）来平衡数据，并基于spearman相关的分层聚类来选择产生最佳预测性能的特征。然后，我们使用SHapley加性解释（SHAP）值来识别对表现贡献最大的特征，并使用部分依赖图来检验特征与30天再住院风险之间的曲线关系和调节关系。

{"title":"An interpretable machine learning study for developing a binary classifier for predicting rehospitalization from skilled nursing facilities","authors":"Zhouyang Lou , Zachary Hass , Nan Kong","doi":"10.1016/j.health.2025.100387","DOIUrl":"10.1016/j.health.2025.100387","url":null,"abstract":"<div><div>Reducing hospital readmissions for older adults discharged to a skilled nursing facility (SNF) is important to the Unites States (U.S.) both from financial and care quality perspectives. To identify potential risk factors, researchers have used data from claims, national surveys, and administrative databases to train models that predict hospital readmissions that occur within 30 days of discharge. Machine learning techniques hold promise for this binary classification task. However, analysis pipelines are underdeveloped in data balancing, feature selection, and model interpretability. In this paper, we utilized individual resident-level data from the Long-Term Care Minimum Data Set (MDS) collected from SNFs in a midwestern U.S. state (n = 93,058). We further triangulated this data with publicly available facility quality and staffing data from the Nursing Home Compares tool of the Medicare.gov and facility neighborhood data from the National Neighborhood Data Archive. We compared several machine learning models, data balancing techniques, and feature selection methods, for the prediction task. We found that XGBoost, with Synthetic Minority Oversampling Edited Nearest Neighbor (SMOTE-ENN) to balance the data, and hierarchical clustering based on spearman correlation to select the features that produces the best prediction performance. We then used SHapley Additive exPlanations (SHAP) values to identify features that contribute most to the performance and used partial dependence plots to examine curvilinear and moderating relationships between features and the risk of 30-day rehospitalization.</div></div>","PeriodicalId":73222,"journal":{"name":"Healthcare analytics (New York, N.Y.)","volume":"7 ","pages":"Article 100387"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143480474","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

An integrated stacked convolutional neural network and the levy flight-based grasshopper optimization algorithm for predicting heart disease 一种集成的堆叠卷积神经网络和基于levy飞行的蚱蜢优化算法用于心脏病预测

Healthcare analytics (New York, N.Y.)

Pub Date : 2025-06-01 Epub Date: 2024-12-07 DOI: 10.1016/j.health.2024.100374

Syed Muhammad Salman Bukhari , Muhammad Hamza Zafar , Syed Kumayl Raza Moosavi , Majad Mansoor , Filippo Sanfilippo

Cardiovascular disease is the leading cause of death worldwide, including critical conditions such as blood vessel blockage, heart failure, and stroke. Accurate and early prediction of heart disease remains a significant challenge due to the complexity of symptoms and the variability of contributing factors. This study proposes a novel hybrid model integrating a Stacked Convolutional Neural Network (SCNN) with the Levy Flight-based Grasshopper Optimization Algorithm (LFGOA) to address this challenge. The SCNN provides robust feature extraction, while LFGOA enhances the model by optimizing hyperparameters, improving classification accuracy, and reducing overfitting. The proposed approach is evaluated using four publicly available heart disease datasets, each representing diverse clinical and demographic features. Compared to traditional classifiers, including Regression Trees, Support Vector Machine, Logistic Regression, K-Nearest Neighbors, and standard Neural Networks, the SCNN-LFGOA consistently outperforms these methods. The results highlight that the SCNN-LFGOA achieves an average accuracy of 99%, with significant improvements in specificity, sensitivity, and F1-Score, showcasing its adaptability and robustness across datasets. This study highlights the SCNN-LFGOA's potential as a transformative tool for early and accurate heart disease prediction, contributing to improved patient outcomes and more efficient healthcare resource utilization. By combining deep learning with an advanced optimization technique, this research introduces a scalable and effective solution to a critical healthcare problem.

心血管疾病是世界范围内导致死亡的主要原因，包括血管阻塞、心力衰竭和中风等严重疾病。由于症状的复杂性和促成因素的可变性，对心脏病的准确和早期预测仍然是一项重大挑战。本研究提出了一种新的混合模型，将堆叠卷积神经网络（SCNN）与Levy基于飞行的蚱蜢优化算法（LFGOA）相结合，以解决这一挑战。SCNN提供鲁棒性特征提取，而LFGOA通过优化超参数、提高分类精度和减少过拟合来增强模型。所提出的方法使用四个公开可用的心脏病数据集进行评估，每个数据集代表不同的临床和人口统计学特征。与传统分类器（包括回归树、支持向量机、逻辑回归、k近邻和标准神经网络）相比，SCNN-LFGOA始终优于这些方法。结果表明，SCNN-LFGOA的平均准确率达到99%，特异性、敏感性和F1-Score均有显著提高，显示出其在数据集上的适应性和鲁棒性。这项研究强调了SCNN-LFGOA作为早期和准确的心脏病预测的变革性工具的潜力，有助于改善患者的预后和更有效的医疗资源利用。通过将深度学习与先进的优化技术相结合，本研究为关键的医疗保健问题引入了可扩展且有效的解决方案。

{"title":"An integrated stacked convolutional neural network and the levy flight-based grasshopper optimization algorithm for predicting heart disease","authors":"Syed Muhammad Salman Bukhari , Muhammad Hamza Zafar , Syed Kumayl Raza Moosavi , Majad Mansoor , Filippo Sanfilippo","doi":"10.1016/j.health.2024.100374","DOIUrl":"10.1016/j.health.2024.100374","url":null,"abstract":"<div><div>Cardiovascular disease is the leading cause of death worldwide, including critical conditions such as blood vessel blockage, heart failure, and stroke. Accurate and early prediction of heart disease remains a significant challenge due to the complexity of symptoms and the variability of contributing factors. This study proposes a novel hybrid model integrating a Stacked Convolutional Neural Network (SCNN) with the Levy Flight-based Grasshopper Optimization Algorithm (LFGOA) to address this challenge. The SCNN provides robust feature extraction, while LFGOA enhances the model by optimizing hyperparameters, improving classification accuracy, and reducing overfitting. The proposed approach is evaluated using four publicly available heart disease datasets, each representing diverse clinical and demographic features. Compared to traditional classifiers, including Regression Trees, Support Vector Machine, Logistic Regression, K-Nearest Neighbors, and standard Neural Networks, the SCNN-LFGOA consistently outperforms these methods. The results highlight that the SCNN-LFGOA achieves an average accuracy of 99%, with significant improvements in specificity, sensitivity, and F1-Score, showcasing its adaptability and robustness across datasets. This study highlights the SCNN-LFGOA's potential as a transformative tool for early and accurate heart disease prediction, contributing to improved patient outcomes and more efficient healthcare resource utilization. By combining deep learning with an advanced optimization technique, this research introduces a scalable and effective solution to a critical healthcare problem.</div></div>","PeriodicalId":73222,"journal":{"name":"Healthcare analytics (New York, N.Y.)","volume":"7 ","pages":"Article 100374"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143171471","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

A comparative assessment of machine learning models and algorithms for osteosarcoma cancer detection and classification 骨肉瘤癌症检测和分类的机器学习模型和算法的比较评估

Healthcare analytics (New York, N.Y.)

Pub Date : 2025-06-01 Epub Date: 2025-01-02 DOI: 10.1016/j.health.2024.100380

Amoakoh Gyasi-Agyei

Osteosarcoma is a bone-forming tumor that is more common in children and young adults than in adults. Timely detection and classification of its type is crucial to its proper treatment and possible survival. Machine learning (ML) models trained on disease datasets are more effective in detection and classification than the conventional methods with hand-crafted features highly dependent on pathologists’ expertise. A publicly available raw osteosarcoma dataset was explored and then preprocessed using different combinations of data denoising techniques (including principal component analysis, mutual information gain, analysis of variance and Kendall’s rank correlation analysis) and data augmentation to derive seven different datasets. Using the seven derived datasets and eight ML algorithms, this study designed and performed an extensive comparative analysis of seven sets of ML models (altogether over 160 models) with their hyperparameters optimized using grid search. The performance differences between the learned ML models were then validated using repeated stratified 10-fold cross-validation and 5x2 cross-validation paired t-tests to select the best model for our task. The empirical model based on the extra trees algorithm and fitted to class-balanced dataset via random oversampling and multicollinearity removed via principal component analysis proved to be the best, as it detected and classified osteosarcoma cancer in 10 ms with 97.8% area under the receiver operating characteristics curve and acceptably low false alarm and misdetection. Thus, the proposed models can be cutting-edge techniques for automated detection and classification of osteosarcoma tumors to aid timely diagnosis, prognosis, and treatment.

骨肉瘤是一种骨形成肿瘤，在儿童和年轻人中比在成人中更常见。及时发现和分类其类型对其适当治疗和可能的生存至关重要。在疾病数据集上训练的机器学习（ML）模型在检测和分类方面比具有高度依赖病理学家专业知识的手工特征的传统方法更有效。研究人员探索了一个公开可用的原始骨肉瘤数据集，然后使用不同的数据去噪技术组合（包括主成分分析、互信息增益、方差分析和肯德尔秩相关分析）和数据增强进行预处理，得出七个不同的数据集。利用七个衍生数据集和八种机器学习算法，本研究设计并对七组机器学习模型（总共超过160个模型）进行了广泛的比较分析，并使用网格搜索优化了它们的超参数。然后使用重复分层10倍交叉验证和5倍交叉验证配对t检验验证学习ML模型之间的性能差异，以选择最适合我们任务的模型。基于额外树算法并通过随机过采样和主成分分析去除多重共线性拟合到类平衡数据集的经验模型被证明是最好的，因为它在10 ms内检测和分类骨肉瘤癌症，接受者工作特征曲线下面积为97.8%，可接受的低虚警和误检。因此，所提出的模型可以成为骨肉瘤肿瘤自动检测和分类的前沿技术，有助于及时诊断、预后和治疗。

{"title":"A comparative assessment of machine learning models and algorithms for osteosarcoma cancer detection and classification","authors":"Amoakoh Gyasi-Agyei","doi":"10.1016/j.health.2024.100380","DOIUrl":"10.1016/j.health.2024.100380","url":null,"abstract":"<div><div>Osteosarcoma is a bone-forming tumor that is more common in children and young adults than in adults. Timely detection and classification of its type is crucial to its proper treatment and possible survival. Machine learning (ML) models trained on disease datasets are more effective in detection and classification than the conventional methods with hand-crafted features highly dependent on pathologists’ expertise. A publicly available raw osteosarcoma dataset was explored and then preprocessed using different combinations of data denoising techniques (including principal component analysis, mutual information gain, analysis of variance and Kendall’s rank correlation analysis) and data augmentation to <em>derive</em> seven different datasets. Using the seven derived datasets and eight ML algorithms, this study designed and performed an extensive comparative analysis of seven sets of ML models (altogether over 160 models) with their hyperparameters optimized using grid search. The performance differences between the learned ML models were then validated using repeated stratified 10-fold cross-validation and 5x2 cross-validation paired <em>t</em>-tests to select the best model for our task. The empirical model based on the extra trees algorithm and fitted to class-balanced dataset via random oversampling and multicollinearity removed via principal component analysis proved to be the best, as it detected and classified osteosarcoma cancer in 10 ms with 97.8% area under the receiver operating characteristics curve and acceptably low false alarm and misdetection. Thus, the proposed models can be cutting-edge techniques for automated detection and classification of osteosarcoma tumors to aid timely diagnosis, prognosis, and treatment.</div></div>","PeriodicalId":73222,"journal":{"name":"Healthcare analytics (New York, N.Y.)","volume":"7 ","pages":"Article 100380"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143169863","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

An efficient blood supply chain network model with multiple echelons for managing outdated products 一种高效的多梯队血液供应链网络模型，用于过期产品的管理

Healthcare analytics (New York, N.Y.)

Pub Date : 2025-06-01 Epub Date: 2024-12-18 DOI: 10.1016/j.health.2024.100377

Agus Mansur , Ivan Darma Wangsa , Novrianty Rizky , Iwan Vanany

This study examines the lack of coordination between blood production and inventories in the blood supply chain networks. Prior studies neglect to optimize operational costs through blood production, inventory, and waste. We propose a mixed-integer linear programming approach addressing multiple echelons, types of blood, and blood bag shelf lifetime. The model is developed by determining the facility locations, assigning regional blood banks, and allocating the right products. Indonesia's blood supply chain is used as a case study to evaluate the applicability of the proposed model using optimization software. A sensitivity analysis is performed on production rate and patient demand to assess how these factors affect the overall cost of expired products. The results show that the proposed method's total cost and expired products are 4.69%–5.60% and 4.71%–5.75%, respectively.

本研究探讨了血液供应链网络中血液生产和库存之间缺乏协调。先前的研究忽略了通过血液生产、库存和浪费来优化运营成本。我们提出了一种混合整数线性规划方法来处理多梯队、血液类型和血袋保质期。该模型是通过确定设施位置、分配区域血库和分配正确的产品来开发的。以印度尼西亚的血液供应链为例，利用优化软件评估所提出模型的适用性。对生产率和患者需求进行敏感性分析，以评估这些因素如何影响过期产品的总成本。结果表明，该方法的总成本为4.69% ~ 5.60%，过期产品为4.71% ~ 5.75%。

引用次数: 0

An enhanced machine learning approach with stacking ensemble learner for accurate liver cancer diagnosis using feature selection and gene expression data 基于特征选择和基因表达数据的肝癌准确诊断的增强机器学习方法

Healthcare analytics (New York, N.Y.)

Pub Date : 2025-06-01 Epub Date: 2024-12-12 DOI: 10.1016/j.health.2024.100373

Amena Mahmoud , Eiko Takaoka

Liver cancer is a significant global health concern, necessitating accurate and timely diagnosis for effective treatment. Machine learning approaches have emerged as promising tools for improving liver cancer classification using gene expression data in recent years. This study presents an advanced machine learning approach for liver cancer diagnosis using gene expression data, combining feature selection techniques with a stacking ensemble learning model. Our method addresses the challenges of high dimensionality and complex patterns in genomic data to improve diagnostic accuracy and interpretability. We employed a feature selection process to identify the most relevant gene expressions associated with liver cancer. This approach reduced the dimensionality of the data while preserving crucial biological information. The selected features were then used to train a stacking ensemble model, which combined multiple base learners, including Multi-Layer Perceptron (MLP), Random Forest (RF) model, K-nearest neighbor (KNN) model, and Support vector machine (SVM), with a meta-learner Extreme Gradient Boosting (Xgboost) model to make final predictions. The stacking ensemble achieved an accuracy of (97%), outperforming individual machine learning algorithms and traditional diagnostic methods. Furthermore, the model demonstrated high sensitivity (96.8%) and specificity (98.1%), crucial for early detection and minimizing false positives.

肝癌是一个重大的全球健康问题，需要准确和及时的诊断才能有效治疗。近年来，机器学习方法已成为利用基因表达数据改进肝癌分类的有前途的工具。本研究提出了一种利用基因表达数据进行肝癌诊断的先进机器学习方法，将特征选择技术与堆叠集成学习模型相结合。我们的方法解决了基因组数据中高维和复杂模式的挑战，以提高诊断的准确性和可解释性。我们采用特征选择过程来确定与肝癌相关的最相关的基因表达。这种方法降低了数据的维数，同时保留了关键的生物信息。然后使用选择的特征来训练堆叠集成模型，该模型结合了多个基础学习器，包括多层感知器（MLP），随机森林（RF）模型，k -近邻（KNN）模型和支持向量机（SVM），以及元学习器极端梯度增强（Xgboost）模型来进行最终预测。堆叠集成实现了（97%）的准确率，优于单个机器学习算法和传统诊断方法。此外，该模型具有很高的灵敏度（96.8%）和特异性（98.1%），这对于早期检测和减少假阳性至关重要。

{"title":"An enhanced machine learning approach with stacking ensemble learner for accurate liver cancer diagnosis using feature selection and gene expression data","authors":"Amena Mahmoud , Eiko Takaoka","doi":"10.1016/j.health.2024.100373","DOIUrl":"10.1016/j.health.2024.100373","url":null,"abstract":"<div><div>Liver cancer is a significant global health concern, necessitating accurate and timely diagnosis for effective treatment. Machine learning approaches have emerged as promising tools for improving liver cancer classification using gene expression data in recent years. This study presents an advanced machine learning approach for liver cancer diagnosis using gene expression data, combining feature selection techniques with a stacking ensemble learning model. Our method addresses the challenges of high dimensionality and complex patterns in genomic data to improve diagnostic accuracy and interpretability. We employed a feature selection process to identify the most relevant gene expressions associated with liver cancer. This approach reduced the dimensionality of the data while preserving crucial biological information. The selected features were then used to train a stacking ensemble model, which combined multiple base learners, including Multi-Layer Perceptron (MLP), Random Forest (RF) model, K-nearest neighbor (KNN) model, and Support vector machine (SVM), with a meta-learner Extreme Gradient Boosting (Xgboost) model to make final predictions. The stacking ensemble achieved an accuracy of (97%), outperforming individual machine learning algorithms and traditional diagnostic methods. Furthermore, the model demonstrated high sensitivity (96.8%) and specificity (98.1%), crucial for early detection and minimizing false positives.</div></div>","PeriodicalId":73222,"journal":{"name":"Healthcare analytics (New York, N.Y.)","volume":"7 ","pages":"Article 100373"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143171470","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

Deterministic compartmental model for optimal control strategies of Giardiasis infection with saturating incidence and environmental dynamics 具有饱和发病率和环境动态的贾第虫病感染最优控制策略的确定性室室模型

Healthcare analytics (New York, N.Y.)

Pub Date : 2025-06-01 Epub Date: 2025-01-07 DOI: 10.1016/j.health.2025.100383

Stephen Edward , Nyimvua Shaban

This study develops a deterministic compartmental model that tracks Giardiasis’s direct and indirect transmission dynamics. The study begins by constructing a model incorporating four constant controls: health education, screening, hospitalization, and sanitation. The analytical results of the model are investigated and presented. The positivity of the solutions and the existence of invariant regions were established. The model exhibits a unique disease-free equilibrium and multiple endemic equilibria. The effective reproduction number was derived using the Next-Generation Matrix (NGM) approach, and its implications for the stability of the equilibria were explored. Local stability of the disease-free equilibrium was confirmed using the Routh–Hurwitz criteria, while global stability results were also presented. Sensitivity analysis was conducted based on the effective reproduction number, identifying the most influential parameters. We introduce an optimal control problem to curb the spread of Giardiasis. We rigorously establish the existence of optimal control solutions and analytically characterize these solutions using Pontryagin’s Maximum Principle. We conduct numerical simulations to evaluate the effectiveness of various control strategies. The results are promising, showing that the simultaneous implementation of all four control measures, education, screening, treatment, and sanitation, can lead to a significant reduction in disease cases, thereby offering a reassuring solution to the spread of Giardiasis.

本研究开发了一个确定性的室室模型，跟踪贾第虫病的直接和间接传播动力学。该研究首先构建了一个包含四个恒定控制因素的模型：健康教育、筛查、住院和卫生。对模型的分析结果进行了研究和介绍。证明了解的正性和不变量区域的存在性。该模型具有独特的无病平衡和多个地方性平衡。利用新一代矩阵（NGM）方法推导了有效繁殖数，并探讨了其对平衡稳定性的影响。利用Routh-Hurwitz准则证实了无病平衡的局部稳定性，同时也给出了全局稳定性结果。根据有效繁殖数进行敏感性分析，找出影响最大的参数。我们引入一个最优控制问题来抑制贾第虫病的传播。我们严格地建立了最优控制解的存在性，并利用庞特里亚金极大值原理对这些解进行了解析表征。我们通过数值模拟来评估各种控制策略的有效性。结果令人鼓舞，表明同时实施所有四项控制措施，即教育、筛查、治疗和卫生，可导致疾病病例显著减少，从而为贾第虫病的传播提供了一种令人放心的解决方案。

{"title":"Deterministic compartmental model for optimal control strategies of Giardiasis infection with saturating incidence and environmental dynamics","authors":"Stephen Edward , Nyimvua Shaban","doi":"10.1016/j.health.2025.100383","DOIUrl":"10.1016/j.health.2025.100383","url":null,"abstract":"<div><div>This study develops a deterministic compartmental model that tracks Giardiasis’s direct and indirect transmission dynamics. The study begins by constructing a model incorporating four constant controls: health education, screening, hospitalization, and sanitation. The analytical results of the model are investigated and presented. The positivity of the solutions and the existence of invariant regions were established. The model exhibits a unique disease-free equilibrium and multiple endemic equilibria. The effective reproduction number was derived using the Next-Generation Matrix (NGM) approach, and its implications for the stability of the equilibria were explored. Local stability of the disease-free equilibrium was confirmed using the Routh–Hurwitz criteria, while global stability results were also presented. Sensitivity analysis was conducted based on the effective reproduction number, identifying the most influential parameters. We introduce an optimal control problem to curb the spread of Giardiasis. We rigorously establish the existence of optimal control solutions and analytically characterize these solutions using Pontryagin’s Maximum Principle. We conduct numerical simulations to evaluate the effectiveness of various control strategies. The results are promising, showing that the simultaneous implementation of all four control measures, education, screening, treatment, and sanitation, can lead to a significant reduction in disease cases, thereby offering a reassuring solution to the spread of Giardiasis.</div></div>","PeriodicalId":73222,"journal":{"name":"Healthcare analytics (New York, N.Y.)","volume":"7 ","pages":"Article 100383"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143171082","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

An analytical transmission model for evaluating pneumonia vaccination and control strategies 评估肺炎疫苗接种和控制策略的分析传播模型

Healthcare analytics (New York, N.Y.)

Pub Date : 2025-06-01 Epub Date: 2025-04-27 DOI: 10.1016/j.health.2025.100394

Dipo Aldila , Abdullah Hasan Hassan , Mohamad Hifzhudin Noor Aziz , Putri Zahra Kamalia

Pneumonia is an infectious disease caused by various agents, such as viruses, bacteria, or fungi. This study proposes an analytical pneumonia model to assess the impact of vaccine interventions. The proposed mathematical model reveals that pneumonia will be eradicated from the population if the basic reproduction number is less than one. Furthermore, our bifurcation analysis indicates the absence of a backward bifurcation, meaning that the basic reproduction number is the sole threshold for determining the endemicity of a disease. In other words, pneumonia will be extinct if the basic reproduction number is less than one and will exist if it is larger than one. We estimate our model parameter values using incidence data from five districts in Jakarta, Indonesia. The dataset consists of weekly incidence data from 2023 until mid-2024. Our analysis shows North Jakarta has the highest case incidence per 100,000 individuals compared to the other districts. A global sensitivity analysis, using the partial rank correlation coefficient and Latin hypercube sampling, was conducted to identify the most impactful parameters on the basic reproduction number for each district in Jakarta. An optimal control problem was formulated to determine the most effective strategies for controlling pneumonia in the field. We found that adult vaccination has a greater impact on reducing the spread of pneumonia than a newborn vaccination strategy. However, combining both newborn and adult vaccinations is essential to ensure long-lasting immunity in children.

肺炎是一种传染病，由多种病原体引起，如病毒、细菌或真菌。本研究提出了一个分析性肺炎模型来评估疫苗干预的影响。提出的数学模型表明，如果基本繁殖数小于1，肺炎将从种群中被根除。此外，我们的分岔分析表明不存在向后分岔，这意味着基本繁殖数是确定疾病地方性的唯一阈值。也就是说，如果基本繁殖数小于1，肺炎就会灭绝，如果基本繁殖数大于1，肺炎就会存在。我们使用印度尼西亚雅加达五个地区的发病率数据估计模型参数值。该数据集包括从2023年到2024年中期的每周发病率数据。我们的分析显示，与其他地区相比，雅加达北部每10万人的发病率最高。利用偏秩相关系数和拉丁超立方抽样进行了全球敏感性分析，以确定对雅加达各区基本再生产数影响最大的参数。制定了一个最优控制问题，以确定在现场控制肺炎的最有效策略。我们发现，与新生儿疫苗接种策略相比，成人疫苗接种对减少肺炎传播的影响更大。然而，结合新生儿和成人疫苗接种对于确保儿童长期免疫至关重要。

{"title":"An analytical transmission model for evaluating pneumonia vaccination and control strategies","authors":"Dipo Aldila , Abdullah Hasan Hassan , Mohamad Hifzhudin Noor Aziz , Putri Zahra Kamalia","doi":"10.1016/j.health.2025.100394","DOIUrl":"10.1016/j.health.2025.100394","url":null,"abstract":"<div><div>Pneumonia is an infectious disease caused by various agents, such as viruses, bacteria, or fungi. This study proposes an analytical pneumonia model to assess the impact of vaccine interventions. The proposed mathematical model reveals that pneumonia will be eradicated from the population if the basic reproduction number is less than one. Furthermore, our bifurcation analysis indicates the absence of a backward bifurcation, meaning that the basic reproduction number is the sole threshold for determining the endemicity of a disease. In other words, pneumonia will be extinct if the basic reproduction number is less than one and will exist if it is larger than one. We estimate our model parameter values using incidence data from five districts in Jakarta, Indonesia. The dataset consists of weekly incidence data from 2023 until mid-2024. Our analysis shows North Jakarta has the highest case incidence per 100,000 individuals compared to the other districts. A global sensitivity analysis, using the partial rank correlation coefficient and Latin hypercube sampling, was conducted to identify the most impactful parameters on the basic reproduction number for each district in Jakarta. An optimal control problem was formulated to determine the most effective strategies for controlling pneumonia in the field. We found that adult vaccination has a greater impact on reducing the spread of pneumonia than a newborn vaccination strategy. However, combining both newborn and adult vaccinations is essential to ensure long-lasting immunity in children.</div></div>","PeriodicalId":73222,"journal":{"name":"Healthcare analytics (New York, N.Y.)","volume":"7 ","pages":"Article 100394"},"PeriodicalIF":0.0,"publicationDate":"2025-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143879067","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