机器学习心血管病风险预测算法的系统评价：前景与临床不确定性
本系统评价检索 Medline、Embase 和 IEEE 数据库至 2025 年 1 月，纳入 29 项将机器学习算法与 Framingham 风险评分（FRS）进行比较的研究。23 项研究报告预测能力优于 FRS，多数纳入 FRS 未包含的社会人口学预测因子。研究提示机器学习有整合多类变量的技术能力，但仍需临床洞察和筛查原则指导。
要点
- 机器学习算法纳入社会人口学变量后，多数研究报告预测能力优于 FRS。
- 部分算法加入 CT 血管造影等昂贵检查作为输入，成本效益未评估。
- 统计学显著性被普遍当作临床显著性，存在过度诊断风险。
核心结论
- 机器学习用于 CVD 风险评估展现出整合社会人口学预测因子与生物学变量并检验非线性交互的技术能力。
- 实现患者获益仍需临床洞察、对筛查原则的遵循以及所选输入指标的成本效益评估。
研究设计与样本
- 系统评价检索 Medline、Embase 和 IEEE 数据库，时间范围从建库至 2025 年 1 月 1 日。
- 纳入专门将机器学习算法心血管风险评估输出与 FRS 进行比较的研究，排除评论、信件、未发表或非同行评审文献。
- 遵循 PRISMA 指南，两名评价者独立筛选标题和摘要，并进行定性主题分析。
- 主要结局为在健康成人中算法是否相对于 FRS 改善 CVD 风险预测。
主要发现
- 共检索 707 项研究，29 项符合纳入标准，其中 23 项报告预测能力优于 FRS。
- 多数研究使用的数据集和/或病历包含 FRS 输入中未包含的 CVD 社会人口学预测因子。
- 部分研究在 FRS 筛查指标基础上加入 CT 血管造影等昂贵诊断检查。
- 高血压或心肌梗死等输入和结局在定义时并不总是遵循 FRS 的取值。
- 部分算法相比 FRS 高估了风险人群比例，但未讨论该人群是否有过度诊断风险而非 CVD 风险。
临床怎么用
- 评估机器学习 CVD 风险预测算法时，不应将统计学显著性等同于临床显著性。
- 临床应用前需评估额外输入指标如影像学检查的成本效益。
- 算法高估风险人群比例时，需考虑过度诊断而非 CVD 本身的可能。
局限性
- 纳入研究对高血压、心肌梗死等输入和结局的定义不完全遵循 FRS 取值，影响可比性。
- 统计学显著性被普遍当作临床显著性的替代指标。
- 部分算法高估风险人群比例但未讨论过度诊断问题。
以上解读依据论文摘要（全文未开放获取或许可不允许翻译转载）。
原文
Objective To examine whether the outputs of machine learning algorithms designed to predict risk of cardiovascular disease (CVD) address known deficiencies of the Framingham Risk Score (FRS) and improve risk estimates. Methods For this critical review, Medline, Embase and IEEE were searched from inception to 1 January 2025. Included were studies describing machine learning algorithms designed to specifically compare output of cardiovascular risk assessment with the FRS. Commentaries, letters, unpublished work or non-peer-reviewed papers were excluded. Following Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, two reviewers screened titles and abstracts independently, then populated a purpose-built data extraction form. A subsequent qualitative thematic analysis focused on algorithms’ strengths, added value, potential harms, unintended consequences and equity implications. The main outcome assessed was whether, among healthy adults, the algorithm improved CVD risk prediction relative to the FRS. Results Of 707 studies retrieved, 29 met inclusion criteria. 23 reported improved predictive ability relative to the FRS. Most datasets and/or medical records used included sociodemographic predictors of CVD not included among FRS inputs. Some added costly diagnostic tests like CT angiography to FRS screening indicators. When they were defined, inputs and outcomes such as hypertension or myocardial infarction did not always adhere to FRS values. Statistical significance was generally taken as a proxy for clinical significance. Some algorithms overestimated the number at risk compared with the FRS without discussing whether that larger proportion might be at risk of overdiagnosis rather than CVD, while a few decreased the proportion found to be at risk. Conclusions Use of artificial intelligence to improve accuracy of risk assessment for CVD demonstrates the technological capacity to merge known sociodemographic predictors with biologic variables and examine non-linear interactions among these. Still needed to achieve patient benefit is clinical insight, adherence to screening principles and cost–benefit assessment of inputs selected.
引用
- Open Heart：Future promise, current clinical ambiguity: a systematic review of machine learning algorithm outputs predicting risk of cardiovascular disease
供执业医师工作参考，不替代临床判断；数值与分级以指南原文为准。