Improving risk prediction in heart failure using machine learning
Improving risk prediction in heart failure using machine learning
复制标题
DOI：
10.1002/ejhf.1628
复制
发表时间：
2019-11-12
影响因子：
18.2
通讯作者：
Yagil, Avi
中科院分区：
文献类型：
--
作者：
Adler, Eric D.;Voors, Adriaan A.;Yagil, Avi
背景预测死亡率对心力衰竭(HF)患者很重要。然而，目前的风险预测策略只取得了一定程度的成功，这可能是因为它们来自统计分析方法，这些方法未能在包含多维相互作用的大型数据集中捕获预测信息。方法和结果我们使用了一种机器学习算法来获取患者特征和死亡率之间的相关性。通过训练增强型决策树算法，在5822名住院和门诊心衰患者的队列中，建立了一个模型，将患者数据的子集与非常高或非常低的死亡风险联系起来。通过识别八个变量(舒张压、肌酐、血尿素氮、血红蛋白、白细胞计数、血小板、白蛋白和红细胞分布宽度)，我们从这个模型中得出了准确区分低风险和高风险死亡的风险分数。这一风险评分的曲线下面积(AUC)为0.88，可以预测整个风险范围。在两个不同的心力衰竭人群中的外部验证得出的AUC分别为0.84和0.81，这优于在这些相同人群中使用两个可用的风险评分所获得的结果。结论使用机器学习和容易获得的变量，我们生成并验证了心力衰竭患者的死亡风险评分，该评分比与之进行比较的其他风险评分更准确。这些结果支持使用这种机器学习方法来评估心力衰竭患者，以及在预测风险一直具有挑战性的其他环境中。
Background Predicting mortality is important in patients with heart failure (HF). However, current strategies for predicting risk are only modestly successful, likely because they are derived from statistical analysis methods that fail to capture prognostic information in large data sets containing multi-dimensional interactions. Methods and results We used a machine learning algorithm to capture correlations between patient characteristics and mortality. A model was built by training a boosted decision tree algorithm to relate a subset of the patient data with a very high or very low mortality risk in a cohort of 5822 hospitalized and ambulatory patients with HF. From this model we derived a risk score that accurately discriminated between low and high-risk of death by identifying eight variables (diastolic blood pressure, creatinine, blood urea nitrogen, haemoglobin, white blood cell count, platelets, albumin, and red blood cell distribution width). This risk score had an area under the curve (AUC) of 0.88 and was predictive across the full spectrum of risk. External validation in two separate HF populations gave AUCs of 0.84 and 0.81, which were superior to those obtained with two available risk scores in these same populations. Conclusions Using machine learning and readily available variables, we generated and validated a mortality risk score in patients with HF that was more accurate than other risk scores to which it was compared. These results support the use of this machine learning approach for the evaluation of patients with HF and in other settings where predicting risk has been challenging.