Department of Epidemiology and Biostatistics, College of Public Health, Zhengzhou University, Zhengzhou, China.
School of Information Engineering, Zhengzhou University, Zhengzhou, China.
Front Public Health. 2021 Feb 17;9:606711. doi: 10.3389/fpubh.2021.606711. eCollection 2021.
Previous studies have constructed prediction models for type 2 diabetes mellitus (T2DM), but machine learning was rarely used and few focused on genetic prediction. This study aimed to establish an effective T2DM prediction tool and to further explore the potential of genetic risk scores (GRS) via various classifiers among rural adults. In this prospective study, the GRS for a total of 5,712 participants from the Henan Rural Cohort Study was calculated. Cox proportional hazards (CPH) regression was used to analyze the associations between GRS and T2DM. CPH, artificial neural network (ANN), random forest (RF), and gradient boosting machine (GBM) were used to establish prediction models, respectively. The area under the receiver operating characteristic curve (AUC) and net reclassification index (NRI) were used to assess the discrimination ability of the models. The decision curve was plotted to determine the clinical-utility for prediction models. Compared with the individuals in the lowest quintile of the GRS, the HR (95% CI) was 2.06 (1.40 to 3.03) for those with the highest quintile of GRS ( < 0.05). Based on conventional predictors, the AUCs of the prediction model were 0.815, 0.816, 0.843, and 0.851 via CPH, ANN, RF, and GBM, respectively. Changes with the integration of GRS for CPH, ANN, RF, and GBM were 0.001, 0.002, 0.018, and 0.033, respectively. The reclassifications were significantly improved for all classifiers when adding GRS (NRI: 41.2% for CPH; 41.0% for ANN; 46.4% for ANN; 45.1% for GBM). Decision curve analysis indicated the clinical benefits of model combined GRS. The prediction model combined with GRS may provide incremental predictions of performance beyond conventional factors for T2DM, which demonstrated the potential clinical use of genetic markers to screen vulnerable populations. The Henan Rural Cohort Study is registered in the Chinese Clinical Trial Register (Registration number: ChiCTR-OOC-15006699). http://www.chictr.org.cn/showproj.aspx?proj=11375.
先前的研究已经构建了 2 型糖尿病（T2DM）的预测模型，但很少使用机器学习，且很少关注遗传预测。本研究旨在建立一种有效的 T2DM 预测工具，并通过农村成年人中的各种分类器进一步探索遗传风险评分（GRS）的潜力。
在这项前瞻性研究中，我们计算了来自河南农村队列研究的 5712 名参与者的 GRS。Cox 比例风险（CPH）回归用于分析 GRS 与 T2DM 之间的关联。分别使用 CPH、人工神经网络（ANN）、随机森林（RF）和梯度提升机（GBM）建立预测模型。使用接受者操作特征曲线下面积（AUC）和净重新分类指数（NRI）评估模型的区分能力。绘制决策曲线以确定预测模型的临床实用性。
与 GRS 最低五分位数的个体相比，GRS 最高五分位数的个体的 HR（95%CI）为 2.06（1.40 至 3.03）（<0.05）。基于常规预测因子，CPH、ANN、RF 和 GBM 预测模型的 AUC 分别为 0.815、0.816、0.843 和 0.851。CPH、ANN、RF 和 GBM 纳入 GRS 后，AUC 分别变化 0.001、0.002、0.018 和 0.033。添加 GRS 后，所有分类器的重新分类均显著改善（NRI：CPH 为 41.2%；ANN 为 41.0%；RF 为 46.4%；GBM 为 45.1%）。决策曲线分析表明，模型结合 GRS 具有临床获益。
综上所述，与传统因素相结合的 GRS 预测模型可能为 T2DM 提供额外的预测性能，这表明遗传标志物在筛选高危人群方面具有潜在的临床应用价值。
河南农村队列研究在中国临床试验注册中心（注册号：ChiCTR-OOC-15006699）注册。http://www.chictr.org.cn/showproj.aspx?proj=11375。
