Sun Zhoujian, Dong Wei, Shi Hanrui, Ma Hong, Cheng Lechao, Huang Zhengxing
Zhejiang Lab, Hangzhou, China.
Zhejiang University, Hangzhou, China.
Front Cardiovasc Med. 2022 Apr 6;9:812276. doi: 10.3389/fcvm.2022.812276. eCollection 2022.
To compare the performance, clinical feasibility, and reliability of statistical and machine learning (ML) models in predicting heart failure (HF) events.
Although ML models have been proposed to revolutionize medicine, their promise in predicting HF events has not been investigated in detail.
A systematic search was performed on Medline, Web of Science, and IEEE Xplore for studies published between January 1, 2011 to July 14, 2021 that developed or validated at least one statistical or ML model that could predict all-cause mortality or all-cause readmission of HF patients. Prediction Model Risk of Bias Assessment Tool was used to assess the risk of bias, and random effect model was used to evaluate the pooled c-statistics of included models.
Two-hundred and two statistical model studies and 78 ML model studies were included from the retrieved papers. The pooled c-index of statistical models in predicting all-cause mortality, ML models in predicting all-cause mortality, statistical models in predicting all-cause readmission, ML models in predicting all-cause readmission were 0.733 (95% confidence interval 0.724-0.742), 0.777 (0.752-0.803), 0.678 (0.651-0.706), and 0.660 (0.633-0.686), respectively, indicating that ML models did not show consistent superiority compared to statistical models. The head-to-head comparison revealed similar results. Meanwhile, the immoderate use of predictors limited the feasibility of ML models. The risk of bias analysis indicated that ML models' technical pitfalls were more serious than statistical models'. Furthermore, the efficacy of ML models among different HF subgroups is still unclear.
ML models did not achieve a significant advantage in predicting events, and their clinical feasibility and reliability were worse.
比较统计模型和机器学习（ML）模型在预测心力衰竭（HF）事件方面的性能、临床可行性和可靠性。
尽管已提出ML模型可彻底改变医学，但尚未对其在预测HF事件方面的前景进行详细研究。
在Medline、科学网和IEEE Xplore上进行系统检索，查找2011年1月1日至2021年7月14日期间发表的研究，这些研究开发或验证了至少一种可预测HF患者全因死亡率或全因再入院率的统计模型或ML模型。使用预测模型偏倚风险评估工具评估偏倚风险，并使用随机效应模型评估纳入模型的合并c统计量。
从检索到的论文中纳入了202项统计模型研究和78项ML模型研究。统计模型预测全因死亡率、ML模型预测全因死亡率、统计模型预测全因再入院率、ML模型预测全因再入院率的合并c指数分别为0.733（95%置信区间0.724 - 0.742）、0.777（0.752 - 0.803）、0.678（0.651 - 0.706）和0.660（0.633 - 0.686），这表明与统计模型相比，ML模型未显示出一致的优越性。直接比较显示结果相似。同时，预测变量的过度使用限制了ML模型的可行性。偏倚风险分析表明，ML模型的技术缺陷比统计模型更严重。此外，ML模型在不同HF亚组中的疗效仍不明确。
ML模型在预测事件方面未取得显著优势，其临床可行性和可靠性较差。
