用混合模型提升糖尿病风险分层，跨数据集表现更稳定。
Generalizable Diabetes Risk Stratification via Hybrid Machine Learning Models
- 结合梯度提升与随机森林的混合模型，提升预测性能。
- 在主数据集和外部验证集上，AUC均超0.99，优于其他模型。
- 适合临床部署，支持根据实际需求调整分类阈值。
糖尿病影响全球超5370万人，预计2045年将达7830万。早期风险分层可借助机器学习实现。本文对比两种混合分类器：XGBoost+随机森林（XGB-RF）和支持向量机+逻辑回归（SVM-LR），并评估其在外部队列中的泛化能力。采用防数据泄露的标准化流程（编码、插补、归一化；仅训练折使用SMOTE；SVM进行概率校准）在主数据集上训练并冻结模型。评估侧重于无阈值判别能力（AUROC/AUPRC）与校准性（Brier分数、斜率/截距）。外部验证使用PIMA队列（N=768），所有指标基于冻结流程计算，阈值设定为tau=0.5。主数据集上，XGB-RF的AUROC约0.995，AUPRC约0.998，优于SVM-LR（AUROC约0.978；AUPRC约0.947）。在PIMA队列中（基线患病率约0.349），XGB-RF仍保持高表现（AUROC约0.990；AUPRC约0.959）；而SVM-LR下降明显（AUROC约0.963；AUPRC约0.875）。在tau=0.5下，PIMA上的准确率分别为：XGB-RF（0.960）、SVM-LR（0.900）；精确率分别为：0.941和0.855；召回率分别为：0.944和0.858；F1分别为：0.942和0.857。结论：在内外部队列中，XGB-RF持续优于SVM-LR，且外部衰减更小，校准性良好。结果支持基于梯度提升的混合模型作为糖尿病风险分层稳健、可迁移的方法，并建议开展多中心前瞻性验证，部署时依据临床权衡选择阈值。
原文摘要 · Abstract (English)
Background/Purpose: Diabetes affects over 537 million people worldwide and is projected to reach 783 million by 2045. Early risk stratification can benefit from machine learning. We compare two hybrid classifiers and assess their generalizability on an external cohort. Methods: Two hybrids were built: (i) XGBoost + Random Forest (XGB-RF) and (ii) Support Vector Machine + Logistic Regression (SVM-LR). A leakage-safe, standardized pipeline (encoding, imputation, min-max scaling; SMOTE on training folds only; probability calibration for SVM) was fit on the primary dataset and frozen. Evaluation prioritized threshold-independent discrimination (AUROC/AUPRC) and calibration (Brier, slope/intercept). External validation used the PIMA cohort (N=768) with the frozen pipeline; any thresholded metrics on PIMA were computed at the default rule tau = 0.5. Results: On the primary dataset (PR baseline = 0.50), XGB-RF achieved AUROC ~0.995 and AUPRC ~0.998, outperforming SVM-LR (AUROC ~0.978; AUPRC ~0.947). On PIMA (PR baseline ~0.349), XGB-RF retained strong performance (AUROC ~0.990; AUPRC ~0.959); SVM-LR was lower (AUROC ~0.963; AUPRC ~0.875). Thresholded metrics on PIMA at tau = 0.5 were XGB-RF (Accuracy 0.960; Precision 0.941; Recall 0.944; F1 0.942) and SVM-LR (Accuracy 0.900; Precision 0.855; Recall 0.858; F1 0.857). Conclusions: Across internal and external cohorts, XGB-RF consistently dominated SVM-LR and exhibited smaller external attenuation on ROC/PR with acceptable calibration. These results support gradient-boosting-based hybridization as a robust, transferable approach for diabetes risk stratification and motivate prospective, multi-site validation with deployment-time threshold selection based on clinical trade-offs.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。