Department of Epidemiology and Biostatistics, College of Public Health, Zhengzhou University, 100 Kexue Avenue, Zhengzhou, 450001, Henan, People's Republic of China.
School of Information Engineering, Zhengzhou University, Zhengzhou, Henan, People's Republic of China.
Lipids Health Dis. 2021 Feb 12;20(1):11. doi: 10.1186/s12944-021-01439-3.
Few studies have developed risk models for dyslipidaemia, especially for rural populations. Furthermore, the performance of genetic factors in predicting dyslipidaemia has not been explored. The purpose of this study is to develop and evaluate prediction models with and without genetic factors for dyslipidaemia in rural populations.
A total of 3596 individuals from the Henan Rural Cohort Study were included in this study. According to the ratio of 7:3, all individuals were divided into a training set and a testing set. The conventional models and conventional+GRS (genetic risk score) models were developed with Cox regression, artificial neural network (ANN), random forest (RF), and gradient boosting machine (GBM) classifiers in the training set. The area under the receiver operating characteristic curve (AUC), net reclassification index (NRI), and integrated discrimination index (IDI) were used to assess the discrimination ability of the models, and the calibration curve was used to show calibration ability in the testing set.
Compared to the lowest quartile of GRS, the hazard ratio (HR) (95% confidence interval (CI)) of individuals in the highest quartile of GRS was 1.23(1.07, 1.41) in the total population. Age, family history of diabetes, physical activity, body mass index (BMI), triglycerides (TGs), high-density lipoprotein cholesterol (HDL-C), and low-density lipoprotein cholesterol (LDL-C) were used to develop the conventional models, and the AUCs of the Cox, ANN, RF, and GBM classifiers were 0.702(0.673, 0.729), 0.736(0.708, 0.762), 0.787 (0.762, 0.811), and 0.816(0.792, 0.839), respectively. After adding GRS, the AUCs increased by 0.005, 0.018, 0.023, and 0.015 with the Cox, ANN, RF, and GBM classifiers, respectively. The corresponding NRI and IDI were 25.6, 7.8, 14.1, and 18.1% and 2.3, 1.0, 2.5, and 1.8%, respectively.
Genetic factors could improve the predictive ability of the dyslipidaemia risk model, suggesting that genetic information could be provided as a potential predictor to screen for clinical dyslipidaemia.
The Henan Rural Cohort Study has been registered at the Chinese Clinical Trial Register. (Trial registration: ChiCTR-OOC-15006699 . Registered 6 July 2015 - Retrospectively registered).
很少有研究针对血脂异常开发风险模型，特别是针对农村人群。此外，遗传因素在预测血脂异常方面的作用尚未得到探索。本研究旨在开发并评估针对农村人群血脂异常的具有和不具有遗传因素的预测模型。
本研究共纳入来自河南农村队列研究的 3596 名个体。根据 7:3 的比例，所有个体被分为训练集和测试集。在训练集中，使用 Cox 回归、人工神经网络（ANN）、随机森林（RF）和梯度提升机（GBM）分类器开发常规模型和常规+GRS（遗传风险评分）模型。使用接收者操作特征曲线下的面积（AUC）、净重新分类指数（NRI）和综合判别指数（IDI）评估模型的判别能力，并用校准曲线在测试集中显示校准能力。
与 GRS 最低四分位相比，GRS 最高四分位个体的风险比（HR）（95%置信区间（CI））为 1.23（1.07，1.41）。年龄、糖尿病家族史、体力活动、体重指数（BMI）、甘油三酯（TGs）、高密度脂蛋白胆固醇（HDL-C）和低密度脂蛋白胆固醇（LDL-C）用于开发常规模型，Cox、ANN、RF 和 GBM 分类器的 AUC 分别为 0.702（0.673，0.729）、0.736（0.708，0.762）、0.787（0.762，0.811）和 0.816（0.792，0.839）。加入 GRS 后，Cox、ANN、RF 和 GBM 分类器的 AUC 分别增加了 0.005、0.018、0.023 和 0.015。相应的 NRI 和 IDI 分别为 25.6%、7.8%、14.1%和 18.1%和 2.3%、1.0%、2.5%和 1.8%。
遗传因素可以提高血脂异常风险模型的预测能力，提示遗传信息可以作为一种潜在的预测指标，用于筛选临床血脂异常。
河南农村队列研究已在中国临床试验注册中心注册。（试验注册：ChiCTR-OOC-15006699. 注册于 2015 年 7 月 6 日-回溯性注册）。
