Mpanya Dineo, Celik Turgay, Klug Eric, Ntsinjana Hopewell
Division of Cardiology, Department of Internal Medicine, School of Clinical Medicine, Faculty of Health Sciences, University of the Witwatersrand, Johannesburg, South Africa.
Wits Institute of Data Science, University of the Witwatersrand, Johannesburg, South Africa.
Int J Cardiol Heart Vasc. 2021 Apr 12;34:100773. doi: 10.1016/j.ijcha.2021.100773. eCollection 2021 Jun.
The partnership between humans and machines can enhance clinical decisions accuracy, leading to improved patient outcomes. Despite this, the application of machine learning techniques in the healthcare sector, particularly in guiding heart failure patient management, remains unpopular. This systematic review aims to identify factors restricting the integration of machine learning derived risk scores into clinical practice when treating adults with acute and chronic heart failure.
Four academic research databases and Google Scholar were searched to identify original research studies where heart failure patient data was used to build models predicting all-cause mortality, cardiac death, all-cause and heart failure-related hospitalization.
Thirty studies met the inclusion criteria. The selected studies' sample size ranged between 71 and 716 790 patients, and the median age was 72.1 (interquartile range: 61.1-76.8) years. The minimum and maximum area under the receiver operating characteristic curve (AUC) for models predicting mortality were 0.48 and 0.92, respectively. Models predicting hospitalization had an AUC of 0.47 to 0.84. Nineteen studies (63%) used logistic regression, 53% random forests, and 37% of studies used decision trees to build predictive models. None of the models were built or externally validated using data originating from Africa or the Middle-East.
The variation in the aetiologies of heart failure, limited access to structured health data, distrust in machine learning techniques among clinicians and the modest accuracy of existing predictive models are some of the factors precluding the widespread use of machine learning derived risk calculators.
人机合作能够提高临床决策的准确性，从而改善患者的治疗效果。尽管如此，机器学习技术在医疗保健领域的应用，尤其是在指导心力衰竭患者管理方面，仍然不受欢迎。本系统评价旨在确定在治疗急慢性心力衰竭成人患者时，限制将机器学习得出的风险评分整合到临床实践中的因素。
检索了四个学术研究数据库和谷歌学术，以确定使用心力衰竭患者数据建立预测全因死亡率、心源性死亡、全因及心力衰竭相关住院率模型的原始研究。
30项研究符合纳入标准。所选研究的样本量在71至716790名患者之间，中位年龄为72.1岁（四分位间距：61.1 - 76.8岁）。预测死亡率模型的受试者工作特征曲线（AUC）下面积最小值和最大值分别为0.48和0.92。预测住院率的模型AUC为0.47至0.84。19项研究（63%）使用逻辑回归，53%使用随机森林，37%的研究使用决策树构建预测模型。没有一个模型是使用来自非洲或中东的数据构建或外部验证的。
心力衰竭病因的差异、结构化健康数据获取有限、临床医生对机器学习技术的不信任以及现有预测模型的适度准确性是阻碍机器学习得出的风险计算器广泛应用的一些因素。
