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.

翻译：非酒精性脂肪性肝病（NAFLD）影响全球约25%的成年人口，带来显著的肝脏和心血管风险。然而，人群层面的筛查工具仍显不足。我们提出一种机器学习框架Method，用于NAFLD风险预测，该方法将梯度提升决策树与保形预测相结合，从而在个体风险估计上提供校准后的无分布覆盖保证。该框架通过自助重采样，整合基于互信息的稳定性选择过程，识别出一个紧凑且临床可解释的特征子集，并构建预测集，其边际覆盖率可证明地超过用户指定的置信水平。我们使用来自中国广州的多中心队列（主要队列n=2,187；外部验证n=412），利用涵盖人口统计学、代谢生物标志物和生活方式因素的78个候选特征对Method进行了评估。Method在内部验证中AUROC达到0.912，在外部验证中达到0.891，性能优于深度神经网络、TabNet、支持向量机和逻辑回归。在90%的名义置信水平下，保形预测集实现了91.3%的经验覆盖率。基于这些分数得出的三级风险分层将人群分为不同组别，其中高风险亚组的12个月进展率是低风险组的4.7倍。所选特征——特别是腰围、ALT、GGT、甘油三酯、空腹血糖和BMI——与已知代谢风险因素一致，提供了生物学合理性。