Du Zhenzhen, Yang Yujie, Zheng Jing, Li Qi, Lin Denan, Li Ye, Fan Jianping, Cheng Wen, Chen Xie-Hui, Cai Yunpeng
Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences, Shenzhen, China.
Fiberhome Technologies College, Wuhan Research Institute of Posts and Telecommunications, Wuhan, China.
JMIR Med Inform. 2020 Jul 6;8(7):e17257. doi: 10.2196/17257.
Predictions of cardiovascular disease risks based on health records have long attracted broad research interests. Despite extensive efforts, the prediction accuracy has remained unsatisfactory. This raises the question as to whether the data insufficiency, statistical and machine-learning methods, or intrinsic noise have hindered the performance of previous approaches, and how these issues can be alleviated.
Based on a large population of patients with hypertension in Shenzhen, China, we aimed to establish a high-precision coronary heart disease (CHD) prediction model through big data and machine-learning.
Data from a large cohort of 42,676 patients with hypertension, including 20,156 patients with CHD onset, were investigated from electronic health records (EHRs) 1-3 years prior to CHD onset (for CHD-positive cases) or during a disease-free follow-up period of more than 3 years (for CHD-negative cases). The population was divided evenly into independent training and test datasets. Various machine-learning methods were adopted on the training set to achieve high-accuracy prediction models and the results were compared with traditional statistical methods and well-known risk scales. Comparison analyses were performed to investigate the effects of training sample size, factor sets, and modeling approaches on the prediction performance.
An ensemble method, XGBoost, achieved high accuracy in predicting 3-year CHD onset for the independent test dataset with an area under the receiver operating characteristic curve (AUC) value of 0.943. Comparison analysis showed that nonlinear models (K-nearest neighbor AUC 0.908, random forest AUC 0.938) outperform linear models (logistic regression AUC 0.865) on the same datasets, and machine-learning methods significantly surpassed traditional risk scales or fixed models (eg, Framingham cardiovascular disease risk models). Further analyses revealed that using time-dependent features obtained from multiple records, including both statistical variables and changing-trend variables, helped to improve the performance compared to using only static features. Subpopulation analysis showed that the impact of feature design had a more significant effect on model accuracy than the population size. Marginal effect analysis showed that both traditional and EHR factors exhibited highly nonlinear characteristics with respect to the risk scores.
We demonstrated that accurate risk prediction of CHD from EHRs is possible given a sufficiently large population of training data. Sophisticated machine-learning methods played an important role in tackling the heterogeneity and nonlinear nature of disease prediction. Moreover, accumulated EHR data over multiple time points provided additional features that were valuable for risk prediction. Our study highlights the importance of accumulating big data from EHRs for accurate disease predictions.
基于健康记录对心血管疾病风险进行预测长期以来一直吸引着广泛的研究兴趣。尽管付出了巨大努力，但预测准确性仍不尽人意。这就引发了一个问题，即数据不足、统计和机器学习方法，还是内在噪声阻碍了先前方法的性能，以及如何缓解这些问题。
基于中国深圳大量高血压患者群体，我们旨在通过大数据和机器学习建立一个高精度的冠心病（CHD）预测模型。
从冠心病发病前1 - 3年（冠心病阳性病例）或超过3年的无病随访期（冠心病阴性病例）的电子健康记录（EHRs）中调查了42676名高血压患者的大样本队列数据，其中包括20156例冠心病发病患者。将该群体平均分为独立的训练集和测试集。在训练集上采用各种机器学习方法以实现高精度预测模型，并将结果与传统统计方法和知名风险量表进行比较。进行比较分析以研究训练样本大小、因素集和建模方法对预测性能的影响。
一种集成方法XGBoost在预测独立测试数据集3年冠心病发病方面取得了高精度，受试者工作特征曲线（AUC）下面积值为0.943。比较分析表明，在相同数据集上，非线性模型（K近邻AUC为0.908，随机森林AUC为0.938）优于线性模型（逻辑回归AUC为0.865），并且机器学习方法显著超越了传统风险量表或固定模型（如弗雷明汉心血管疾病风险模型）。进一步分析表明，与仅使用静态特征相比，使用从多个记录中获得的时间相关特征，包括统计变量和变化趋势变量，有助于提高性能。亚组分析表明，特征设计对模型准确性的影响比对群体大小的影响更显著。边际效应分析表明，传统因素和EHR因素在风险评分方面均表现出高度非线性特征。
我们证明，在有足够大的训练数据群体的情况下，从EHRs中准确预测冠心病风险是可能的。复杂的机器学习方法在应对疾病预测的异质性和非线性本质方面发挥了重要作用。此外，多个时间点积累的EHR数据提供了对风险预测有价值的额外特征。我们的研究强调了从EHRs中积累大数据以进行准确疾病预测的重要性。
