Afrifa-Yamoah Ebenezer, Peprah-Yamoah Emmanuel, Anto Enoch Odame, Opoku-Yamoah Victor, Adua Eric
Mathematical Applications & Data Analytics Group, School of Science Edith Cowan University Perth Western Australia Australia.
Teva Pharmaceuticals Salt Lake City Utah USA.
Chronic Dis Transl Med. 2025 May 7;11(3):205-212. doi: 10.1002/cdt3.70007. eCollection 2025 Sep.
Precise risk prediction of chronic diseases is essential for effective preventive care and management. Machine learning (ML) is a promising avenue to enhance chronic disease risk prediction; however, a comprehensive assessment of ML performance across various chronic diseases, populations, and health settings is needed.
This meta-analysis aims to synthesize evidence on the performance of ML techniques for predicting the risks and outcomes of chronic diseases. A literature search was conducted through PubMed, Web of Science, Scopus, Science Direct, Medline, and Embase. Studies applying ML techniques to predict chronic disease risks or outcomes and reporting performance metrics were included. Two reviewers independently screened studies, extracted data, and assessed the risk of bias. Random-effects meta-analysis, subgroup analyses, and meta-regression were performed to estimate pooled performance and explore heterogeneity.
This meta-analysis provides a comprehensive evaluation of the performance of ML techniques in predicting the risks and consequences of chronic diseases. We reported the pooled estimates of performance metrics, such as the area under the receiver operating characteristic curve (AUC-ROC), sensitivity, specificity, and F1 score, for each chronic disease. Subgroup analyses and meta-regression identified factors that influence the performance of ML models, such as the ML algorithm, sample size, and data type. This meta-analysis synthesized evidence on ML techniques for chronic disease risk prediction, guiding the development of robust and generalizable ML-based tools. By identifying best practices and addressing challenges, this work advances predictive analytics in healthcare, facilitates translation into clinical practice, and ultimately improve patient outcomes.
CRD42024566680.
对慢性病进行精确的风险预测对于有效的预防保健和管理至关重要。机器学习（ML）是增强慢性病风险预测的一条有前景的途径；然而，需要对ML在各种慢性病、人群和健康环境中的性能进行全面评估。
本荟萃分析旨在综合关于ML技术预测慢性病风险和结局性能的证据。通过PubMed、科学网、Scopus、科学Direct、Medline和Embase进行文献检索。纳入应用ML技术预测慢性病风险或结局并报告性能指标的研究。两名评审员独立筛选研究、提取数据并评估偏倚风险。进行随机效应荟萃分析、亚组分析和荟萃回归以估计合并性能并探索异质性。
本荟萃分析对ML技术在预测慢性病风险和后果方面的性能进行了全面评估。我们报告了每种慢性病的性能指标的合并估计值，如受试者工作特征曲线下面积（AUC-ROC）、敏感性、特异性和F1分数。亚组分析和荟萃回归确定了影响ML模型性能的因素，如ML算法、样本量和数据类型。本荟萃分析综合了关于ML技术用于慢性病风险预测的证据，指导了强大且可推广的基于ML的工具的开发。通过确定最佳实践并应对挑战，这项工作推动了医疗保健中的预测分析，促进了向临床实践的转化，并最终改善了患者结局。
PROSPERO协议注册：CRD42024566680。
