Department of Computer and Information Sciences, Computational Biomedicine Lab, University of Delaware, Newark, Delaware.
Hypertrophic Cardiomyopathy Center of Excellence, Johns Hopkins University, Baltimore, Maryland; Division of Cardiology, Taipei Veterans General Hospital, Taipei, Taiwan; Institute of Public Health, National Yang-Ming University, Taipei, Taiwan.
Am J Cardiol. 2019 May 15;123(10):1681-1689. doi: 10.1016/j.amjcard.2019.02.022. Epub 2019 Feb 27.
Clinical risk stratification for sudden cardiac death (SCD) in hypertrophic cardiomyopathy (HC) employs rules derived from American College of Cardiology Foundation/American Heart Association (ACCF/AHA) guidelines or the HCM Risk-SCD model (C-index ∼0.69), which utilize a few clinical variables. We assessed whether data-driven machine learning methods that consider a wider range of variables can effectively identify HC patients with ventricular arrhythmias (VAr) that lead to SCD. We scanned the electronic health records of 711 HC patients for sustained ventricular tachycardia or ventricular fibrillation. Patients with ventricular tachycardia or ventricular fibrillation (n = 61) were tagged as VAr cases and the remaining (n = 650) as non-VAr. The 2-sample ttest and information gain criterion were used to identify the most informative clinical variables that distinguish VAr from non-VAr; patient records were reduced to include only these variables. Data imbalance stemming from low number of VAr cases was addressed by applying a combination of over- and undersampling strategies. We trained and tested multiple classifiers under this sampling approach, showing effective classification. We evaluated 93 clinical variables, of which 22 proved predictive of VAr. The ensemble of logistic regression and naïve Bayes classifiers, trained based on these 22 variables and corrected for data imbalance, was most effective in separating VAr from non-VAr cases (sensitivity = 0.73, specificity = 0.76, C-index = 0.83). Our method (HCM-VAr-Risk Model) identified 12 new predictors of VAr, in addition to 10 established SCD predictors. In conclusion, this is the first application of machine learning for identifying HC patients with VAr, using clinical attributes. Our model demonstrates good performance (C-index) compared with currently employed SCD prediction algorithms, while addressing imbalance inherent in clinical data.
临床风险分层对于肥厚型心肌病（HC）患者的心脏性猝死（SCD），采用的是美国心脏病学会基金会/美国心脏协会（ACCF/AHA）指南或 HCM 风险-SCD 模型（C 指数∼0.69）中的规则，这些规则使用了少数临床变量。我们评估了数据驱动的机器学习方法，这些方法考虑了更广泛的变量，是否可以有效地识别导致 SCD 的 HC 患者的室性心律失常（VAr）。我们扫描了 711 例 HC 患者的电子健康记录，以寻找持续性室性心动过速或心室颤动。有室性心动过速或心室颤动（n=61）的患者被标记为 VAr 病例，其余（n=650）为非 VAr 病例。采用两样本 t 检验和信息增益标准来识别最能区分 VAr 和非 VAr 的有意义的临床变量；患者记录仅包含这些变量。由于 VAr 病例数量较少导致的数据不平衡问题，通过应用过采样和欠采样策略组合来解决。在这种采样方法下，我们训练和测试了多个分类器，结果显示分类效果有效。我们评估了 93 个临床变量，其中 22 个变量对 VAr 有预测作用。基于这 22 个变量，通过逻辑回归和朴素贝叶斯分类器集成，并对数据不平衡进行校正，该方法在区分 VAr 和非 VAr 病例方面最为有效（灵敏度=0.73，特异性=0.76，C 指数=0.83）。我们的方法（HCM-VAr-Risk 模型）除了识别出 10 个已确立的 SCD 预测因子外，还确定了 12 个新的 VAr 预测因子。总之，这是首次应用机器学习方法，基于临床属性来识别发生 VAr 的 HC 患者。与目前使用的 SCD 预测算法相比，我们的模型表现出良好的性能（C 指数），同时解决了临床数据固有的不平衡问题。
