Machine learning for subtype definition and risk prediction in heart failure, acute coronary syndromes and atrial fibrillation: systematic review of validity and clinical utility.
Machine learning for subtype definition and risk prediction in heart failure, acute coronary syndromes and atrial fibrillation: systematic review of validity and clinical utility.
复制标题
DOI：
10.1186/s12916-021-01940-7
复制
发表时间：
2021-04-06
期刊：
影响因子：
9.3
通讯作者：
Hemingway H
中科院分区：
文献类型：
--
作者：
Banerjee A;Chen S;Fatemifar G;Zeina M;Lumbers RT;Mielke J;Gill S;Kotecha D;Freitag DF;Denaxas S;Hemingway H
机器学习 (ML) 越来越多地用于亚型定义和风险预测的研究，特别是在心血管疾病方面。现有的机器学习模型尚无常规用于心血管疾病管理，其临床应用阶段也未知，部分原因是缺乏明确的标准。我们评估了 ML 对心力衰竭 (HF)、急性冠状动脉综合征 (ACS) 和心房颤动 (AF) 的亚型定义和风险预测。对于亚型定义和风险预测的 ML 研究，我们从 2000 年 1 月到 2019 年 12 月，使用 PubMed、MEDLINE 和 Web of Science 对 HF、ACS 和 AF 进行了系统回顾。通过调整已发布的诊断和预后研究标准，我们开发了一个七个领域的 ML 特定清单。在确定的 5918 项研究中，纳入了 97 项。在亚型定义 (n = 40) 和风险预测 (n = 57) 的研究中，数据源、人群规模（中位数 606 和中位数 6769）、临床环境（门诊患者、住院患者、不同科室）、协变量数量（中位数 19 和中位数 48）和机器学习方法存在差异。所有研究都是单一疾病，大多数是北美研究 (n = 61/97)，只有 14 项研究结合了定义和风险预测。亚型定义和风险预测研究分别在开发（例如，15.0%和78.9%的研究与患者获益相关；15.0%和15.8%的患者选择偏差较低）、验证（12.5%和5.3%经过外部验证）和影响（32.5%和91.2%改善了结果预测；没有有效性或成本效益评估）方面存在局限性。 HF、ACS 和 AF 的 ML 研究受到所包含协变量的数量和类型、ML 方法、人口规模、国家、临床环境的限制，并且关注单一疾病，而不是重叠或多发病。临床效用和实施依赖于开发、验证和影响方面的改进，并通过简单的清单来促进。在心血管疾病和其他疾病领域的临床实践中安全实施机器学习之前，我们提供了明确的步骤。在线版本包含可在 10.1186/s12916-021-01940-7 获取的补充材料。
Machine learning (ML) is increasingly used in research for subtype definition and risk prediction, particularly in cardiovascular diseases. No existing ML models are routinely used for cardiovascular disease management, and their phase of clinical utility is unknown, partly due to a lack of clear criteria. We evaluated ML for subtype definition and risk prediction in heart failure (HF), acute coronary syndromes (ACS) and atrial fibrillation (AF). For ML studies of subtype definition and risk prediction, we conducted a systematic review in HF, ACS and AF, using PubMed, MEDLINE and Web of Science from January 2000 until December 2019. By adapting published criteria for diagnostic and prognostic studies, we developed a seven-domain, ML-specific checklist. Of 5918 studies identified, 97 were included. Across studies for subtype definition (n = 40) and risk prediction (n = 57), there was variation in data source, population size (median 606 and median 6769), clinical setting (outpatient, inpatient, different departments), number of covariates (median 19 and median 48) and ML methods. All studies were single disease, most were North American (n = 61/97) and only 14 studies combined definition and risk prediction. Subtype definition and risk prediction studies respectively had limitations in development (e.g. 15.0% and 78.9% of studies related to patient benefit; 15.0% and 15.8% had low patient selection bias), validation (12.5% and 5.3% externally validated) and impact (32.5% and 91.2% improved outcome prediction; no effectiveness or cost-effectiveness evaluations). Studies of ML in HF, ACS and AF are limited by number and type of included covariates, ML methods, population size, country, clinical setting and focus on single diseases, not overlap or multimorbidity. Clinical utility and implementation rely on improvements in development, validation and impact, facilitated by simple checklists. We provide clear steps prior to safe implementation of machine learning in clinical practice for cardiovascular diseases and other disease areas. The online version contains supplementary material available at 10.1186/s12916-021-01940-7.
登录
查看更多内容
影响因子：
20.1
作者：
Ambale-Venkatesh B;Yang X;Wu CO;Liu K;Hundley WG;McClelland R;Gomes AS;Folsom AR;Shea S;Guallar E;Bluemke DA;Lima JAC
通讯作者：
Lima JAC
影响因子：
5.4
作者：
Al'Aref, Subhi J.;Singh, Gurpreet;Minutello, Robert M.
通讯作者：
Minutello, Robert M.
影响因子：
9
作者：
Chiew CJ;Liu N;Wong TH;Sim YE;Abdullah HR
通讯作者：
Abdullah HR
影响因子：
3.8
作者：
Awan, Saqib Ejaz;Bennamoun, Mohammed;Dwivedi, Girish
通讯作者：
Dwivedi, Girish
影响因子：
44.5
作者：
Ahlqvist, Emma;Storm, Petter;Groop, Leif
通讯作者：
Groop, Leif