Ted Rogers Centre for Heart Research, Toronto, Ontario, Canada; University of Toronto, Toronto, Ontario, Canada.
Institute for Clinical Evaluative Sciences, Toronto, Ontario, Canada; Institute for Health Policy, Management and Evaluation, Toronto, Ontario, Canada; University of Toronto, Toronto, Ontario, Canada.
Can J Cardiol. 2021 Aug;37(8):1207-1214. doi: 10.1016/j.cjca.2021.02.020. Epub 2021 Mar 5.
Machine learning (ML) methods are increasingly used in addition to conventional statistical modelling (CSM) for predicting readmission and mortality in patients with myocardial infarction (MI). However, the two approaches have not been systematically compared across studies of prognosis in patients with MI.
Following PRISMA guidelines, we systematically reviewed the literature via Medline, EPub, Cochrane Central, Embase, Inspec, ACM Digital Library, and Web of Science. Eligible studies included primary research articles published from January 2000 to March 2020, comparing ML and CSM for prognostication after MI.
Of 7,348 articles, 112 underwent full-text review, with the final set composed of 24 articles representing 374,365 patients. ML methods included artificial neural networks (n = 12 studies), random forests (n = 11), decision trees (n = 8), support vector machines (n = 8), and Bayesian techniques (n = 7). CSM included logistic regression (n = 19 studies), existing CSM-derived risk scores (n = 12), and Cox regression (n = 2). Thirteen of 19 studies examining mortality reported higher C-indexes with the use of ML compared with CSM. One study examined readmissions at 2 different time points, with C-indexes that were higher for ML than CSM. Across all studies, a total of 29 comparisons were performed, but the majority (n = 26, 90%) found small (< 0.05) absolute differences in the C-index between ML and CSM. With the use of a modified CHARMS checklist, sources of bias were identifiable in the majority of studies, and only 2 were externally validated.
Although ML algorithms tended to have higher C-indexes than CSM for predicting death or readmission after MI, these studies exhibited threats to internal validity and were often unvalidated. Further comparisons are needed, with adherence to clinical quality standards for prognosis research. (Trial registration: PROSPERO CRD42019134896).
机器学习（ML）方法除了传统的统计建模（CSM）之外，越来越多地用于预测心肌梗死（MI）患者的再入院和死亡率。然而，这两种方法在 MI 患者预后的研究中并没有得到系统的比较。
根据 PRISMA 指南，我们通过 Medline、EPub、Cochrane Central、Embase、Inspec、ACM 数字图书馆和 Web of Science 系统地回顾了文献。纳入的研究包括 2000 年 1 月至 2020 年 3 月发表的比较 MI 后 ML 和 CSM 预测的原始研究文章。
在 7348 篇文章中，有 112 篇进行了全文审查，最终确定的研究由 24 篇文章组成，共涉及 374365 名患者。ML 方法包括人工神经网络（n=12 项研究）、随机森林（n=11 项）、决策树（n=8 项）、支持向量机（n=8 项）和贝叶斯技术（n=7 项）。CSM 包括逻辑回归（n=19 项研究）、现有的 CSM 衍生风险评分（n=12 项）和 Cox 回归（n=2 项）。在 19 项研究死亡的研究中，有 13 项研究报告使用 ML 比 CSM 有更高的 C 指数。有一项研究在两个不同的时间点检查了再入院情况，ML 的 C 指数高于 CSM。在所有研究中，共进行了 29 次比较，但大多数（n=26，90%）发现 ML 与 CSM 的 C 指数之间的绝对差异较小（<0.05）。使用改良的 CHARMS 清单，大多数研究中都存在偏倚的来源，只有 2 项研究进行了外部验证。
尽管 ML 算法在预测 MI 后死亡或再入院方面的 C 指数往往高于 CSM，但这些研究存在内部有效性的威胁，且往往未经验证。需要进一步比较，并遵循预后研究的临床质量标准。（试验注册：PROSPERO CRD42019134896）。
