Department of Cardiology, The First Hospital of China Medical University, No. 155, Nanjing Bei Street, Shenyang, 110001, China.
Guangdong Provincial People's Hospital (Guangdong Academy of Medical Sciences), Southern Medical University, 106 Zhongshan 2nd Road, Guangzhou, 510080, China.
BMC Med Inform Decis Mak. 2023 Jul 24;23(1):134. doi: 10.1186/s12911-023-02242-z.
Accurately predicting the risk of atherosclerotic cardiovascular disease (ASCVD) is crucial for implementing individualized prevention strategies and improving patient outcomes. Our objective is to develop machine learning (ML)-based models for predicting ASCVD risk in a prospective Chinese population and compare their performance with conventional regression models.
A hybrid dataset consisting of 551 features was used, including 98 demographic, behavioral, and psychological features, 444 Electrocardiograph (ECG) features, and 9 Echocardiography (Echo) features. Seven machine learning (ML)-based models were trained, validated, and tested after selecting the 30 most informative features. We compared the discrimination, calibration, net benefit, and net reclassification improvement (NRI) of the ML models with those of conventional ASCVD risk calculators, such as the Pooled Cohort Equations (PCE) and Prediction for ASCVD Risk in China (China-PAR).
The study included 9,609 participants (mean age 53.4 ± 10.4 years, 53.7% female), and during a median follow-up of 4.7 years, 431 (4.5%) participants developed ASCVD. In the testing set, the final ML-based ANN model outperformed PCE, China-PAR, recalibrated PCE, and recalibrated China-PAR in predicting ASCVD. This was demonstrated by the model's higher area under the curve (AUC) of 0.800, compared to 0.777, 0.780, 0.779, and 0.779 for the other models, respectively. Additionally, the model had a lower Hosmer-Lemeshow χ2 of 9.1, compared to 37.3, 67.6, 126.6, and 18.6 for the other models. The net benefit at a threshold of 5% was also higher for the ML-based ANN model at 0.017, compared to 0.016, 0.013, 0.017, and 0.016 for the other models, respectively. Furthermore, the NRI was 0.089 for the ML-based ANN model, while it was 0.355, 0.098, and 0.088 for PCE, China-PAR, and recalibrated PCE, respectively.
Compared to conventional regression ASCVD risk calculators, such as PCE and China-PAR, the ANN prediction model may help optimize identification of individuals at heightened cardiovascular risk by flexibly incorporating a wider range of potential predictors. The findings may help guide clinical decision-making and ultimately contribute to ASCVD prevention and management.
准确预测动脉粥样硬化性心血管疾病（ASCVD）的风险对于实施个体化预防策略和改善患者预后至关重要。我们的目标是为前瞻性中国人群开发基于机器学习（ML）的 ASCVD 风险预测模型，并比较其与传统回归模型的性能。
使用了一个混合数据集，其中包含 98 个人口统计学、行为和心理特征、444 个心电图（ECG）特征和 9 个超声心动图（Echo）特征。在选择了 30 个最有信息量的特征后，我们训练、验证和测试了七个基于机器学习（ML）的模型。我们将 ML 模型的区分度、校准度、净效益和净重新分类改善（NRI）与传统的 ASCVD 风险计算器（如 Pooled Cohort Equations [PCE] 和 Prediction for ASCVD Risk in China [China-PAR]）进行了比较。
该研究共纳入了 9609 名参与者（平均年龄 53.4±10.4 岁，53.7%为女性），在中位随访 4.7 年后，有 431 名（4.5%）参与者发生了 ASCVD。在测试集中，最终的基于机器学习的 ANN 模型在预测 ASCVD 方面优于 PCE、China-PAR、重新校准的 PCE 和重新校准的 China-PAR。这表现在模型的曲线下面积（AUC）更高，分别为 0.800、0.777、0.780、0.779 和 0.779。此外，模型的 Hosmer-Lemeshow χ2 值也更低，为 9.1，而其他模型的 Hosmer-Lemeshow χ2 值分别为 37.3、67.6、126.6 和 18.6。在阈值为 5%时，基于机器学习的 ANN 模型的净效益也更高，分别为 0.017、0.016、0.013、0.017 和 0.016。此外，基于机器学习的 ANN 模型的 NRI 为 0.089，而 PCE、China-PAR 和重新校准的 PCE 的 NRI 分别为 0.355、0.098 和 0.088。
与传统的回归 ASCVD 风险计算器（如 PCE 和 China-PAR）相比，ANN 预测模型通过灵活地纳入更广泛的潜在预测因素，可能有助于优化对心血管风险升高的个体的识别。研究结果可能有助于指导临床决策，并最终有助于 ASCVD 的预防和管理。
