Department of Computer Engineering, Inha University, Incheon, Republic of Korea.
J Healthc Eng. 2017;2017:2780501. doi: 10.1155/2017/2780501. Epub 2017 Sep 6.
Of the machine learning techniques used in predicting coronary heart disease (CHD), neural network (NN) is popularly used to improve performance accuracy.
Even though NN-based systems provide meaningful results based on clinical experiments, medical experts are not satisfied with their predictive performances because NN is trained in a "black-box" style.
We sought to devise an NN-based prediction of CHD risk using feature correlation analysis (NN-FCA) using two stages. First, the feature selection stage, which makes features acceding to the importance in predicting CHD risk, is ranked, and second, the feature correlation analysis stage, during which one learns about the existence of correlations between feature relations and the data of each NN predictor output, is determined.
Of the 4146 individuals in the Korean dataset evaluated, 3031 had low CHD risk and 1115 had CHD high risk. The area under the receiver operating characteristic (ROC) curve of the proposed model (0.749 ± 0.010) was larger than the Framingham risk score (FRS) (0.393 ± 0.010).
The proposed NN-FCA, which utilizes feature correlation analysis, was found to be better than FRS in terms of CHD risk prediction. Furthermore, the proposed model resulted in a larger ROC curve and more accurate predictions of CHD risk in the Korean population than the FRS.
在预测冠心病 (CHD) 的机器学习技术中，神经网络 (NN) 常用于提高性能准确性。
尽管基于 NN 的系统基于临床实验提供了有意义的结果，但医学专家对其预测性能并不满意，因为 NN 是在“黑盒”模式下训练的。
我们试图使用特征相关分析 (NN-FCA) 设计基于 NN 的 CHD 风险预测，分为两个阶段。首先，特征选择阶段，根据对预测 CHD 风险的重要性对特征进行排序，其次，特征相关分析阶段，在此阶段，了解特征关系与每个 NN 预测器输出数据之间的相关性的存在。
在评估的 4146 名韩国个体中，3031 人患 CHD 的风险较低，1115 人患 CHD 的风险较高。所提出模型的接收器操作特征 (ROC) 曲线下面积（0.749±0.010）大于 Framingham 风险评分（FRS）（0.393±0.010）。
利用特征相关分析的提出的 NN-FCA 在 CHD 风险预测方面优于 FRS。此外，与 FRS 相比，所提出的模型在韩国人群中导致更大的 ROC 曲线和更准确的 CHD 风险预测。
