Birdi Sharon, Rabet Roxana, Durant Steve, Patel Atushi, Vosoughi Tina, Shergill Mahek, Costanian Christy, Ziegler Carolyn P, Ali Shehzad, Buckeridge David, Ghassemi Marzyeh, Gibson Jennifer, John-Baptiste Ava, Macklin Jillian, McCradden Melissa, McKenzie Kwame, Mishra Sharmistha, Naraei Parisa, Owusu-Bempah Akwasi, Rosella Laura, Shaw James, Upshur Ross, Pinto Andrew D
Upstream Lab, MAP Centre for Urban Health Solutions, Li Ka Shing Knowledge Institute, Unity Health Toronto, 30 Bond Street, Toronto, ON, M5B 1W8, Canada.
Michael G. DeGroote School of Medicine, McMaster University, Hamilton, ON, Canada.
BMC Public Health. 2024 Dec 28;24(1):3599. doi: 10.1186/s12889-024-21081-9.
Machine learning (ML) is increasingly used in population and public health to support epidemiological studies, surveillance, and evaluation. Our objective was to conduct a scoping review to identify studies that use ML in population health, with a focus on its use in non-communicable diseases (NCDs). We also examine potential algorithmic biases in model design, training, and implementation, as well as efforts to mitigate these biases.
We searched the peer-reviewed, indexed literature using Medline, Embase, Cochrane Central Register of Controlled Trials and Cochrane Database of Systematic Reviews, CINAHL, Scopus, ACM Digital Library, Inspec, Web of Science's Science Citation Index, Social Sciences Citation Index, and the Emerging Sources Citation Index, up to March 2022.
The search identified 27 310 studies and 65 were included. Study aims were separated into algorithm comparison (n = 13, 20%) or disease modelling for population-health-related outputs (n = 52, 80%). We extracted data on NCD type, data sources, technical approach, possible algorithmic bias, and jurisdiction. Type 2 diabetes was the most studied NCD. The most common use of ML was for risk modeling. Mitigating bias was not extensively addressed, with most methods focused on mitigating sex-related bias.
This review examines current applications of ML in NCDs, highlighting potential biases and strategies for mitigation. Future research should focus on communicable diseases and the transferability of ML models in low and middle-income settings. Our findings can guide the development of guidelines for the equitable use of ML to improve population health outcomes.
机器学习（ML）在人口与公共卫生领域的应用日益广泛，以支持流行病学研究、监测和评估。我们的目标是进行一项范围综述，以识别在人口健康中使用机器学习的研究，重点关注其在非传染性疾病（NCDs）中的应用。我们还研究了模型设计、训练和实施中潜在的算法偏差，以及减轻这些偏差的措施。
我们使用Medline、Embase、Cochrane对照试验中心注册库和Cochrane系统评价数据库、CINAHL、Scopus、ACM数字图书馆、Inspec、Web of Science的科学引文索引、社会科学引文索引和新兴来源引文索引，检索截至2022年3月的同行评审索引文献。
检索共识别出27310项研究，纳入65项。研究目的分为算法比较（n = 13，20%）或针对与人口健康相关产出的疾病建模（n = 52，80%）。我们提取了关于非传染性疾病类型、数据来源、技术方法、可能的算法偏差和管辖范围的数据。2型糖尿病是研究最多的非传染性疾病。机器学习最常见的用途是风险建模。减轻偏差并未得到广泛探讨，大多数方法集中于减轻与性别相关的偏差。
本综述考察了机器学习在非传染性疾病中的当前应用，突出了潜在偏差和减轻偏差的策略。未来研究应聚焦于传染病以及机器学习模型在低收入和中等收入环境中的可转移性。我们的研究结果可为公平使用机器学习以改善人群健康结果的指南制定提供指导。
