用梯度提升与不确定性校准预测脂肪肝风险，结果更可靠且可解释。
Conformal Risk Prediction for Non-Alcoholic Fatty Liver Disease Using Gradient Boosting with Distribution-Free Coverages
- 结合梯度提升与置信预测，生成无需分布假设的风险区间。
- 内部和外部验证的准确率分别达0.912和0.891，覆盖率达91.3%（目标90%）。
- 筛选出腰围、转氨酶等关键指标，适合临床风险分层应用。
非酒精性脂肪肝病（NAFLD）影响全球约25%成年人，带来显著肝病和心血管风险，但现有群体筛查工具不足。本文提出一种机器学习框架Method，将梯度提升决策树与置信预测结合，为个体风险估计提供校准的、无需分布假设的覆盖保证。该方法通过基于互信息的稳定性选择，在Bootstrap重采样中识别出紧凑且临床可解释的特征子集，构建的预测集边际覆盖率可保证超过用户指定的置信水平。在来自中国广州的多中心队列中评估（主队列n=2,187；外部验证n=412），使用78个人口统计学、代谢生物标志物和生活方式特征。Method在内部验证中获得0.912的AUROC，外部验证中为0.891，优于深度神经网络、TabNet、支持向量机和逻辑回归。置信预测集在90%名义水平下实现91.3%的实际覆盖率。基于风险评分的三阶梯分层将人群分为不同组别，高风险组12个月进展率是低风险组的4.7倍。所选特征（如腰围、ALT、GGT、甘油三酯、空腹血糖、BMI）与既定代谢风险因素一致，具备生物学合理性。
原文摘要 · Abstract (English)
Non-alcoholic fatty liver disease (NAFLD) affects roughly 25% of global adults, posing substantial hepatic and cardiovascular risks. Yet, population-level screening tools remain inadequate. We present Method, a machine-learning framework for NAFLD risk prediction coupling gradient-boosted decision trees with conformal prediction to yield calibrated, distribution-free coverage guarantees on individual risk estimates. It integrates a mutual-information-based stability selection procedure to identify a compact, clinically interpretable feature subset via bootstrap resampling, constructing prediction sets whose marginal coverage provably exceeds a user-specified confidence level. We evaluated Method on a multicenter cohort from Guangzhou, China (primary n=2,187; external validation n=412) using 78 candidate features across demographics, metabolic biomarkers, and lifestyle factors. Method achieves an AUROC of 0.912 internally and 0.891 externally, outperforming deep neural networks, TabNet, support vector machines, and logistic regression. Conformal prediction sets achieve 91.3% empirical coverage at the 90% nominal level. A three-tier risk stratification derived from these scores separates the population into distinct groups, with the high-risk subgroup showing a 12-month progression rate 4.7 times that of the low-risk tier. The selected features -- notably waist circumference, ALT, GGT, triglycerides, fasting glucose, and BMI -- align with established metabolic risk factors, providing biological plausibility.
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。