非酒精性脂肪肝病（NAFLD）的管理包括非侵入性预测纤维化，这是患者结果的替代指标。我们旨在开发和验证一种能够预测肝相关事件（LRE）的模型，包括失代偿和/或肝细胞癌，并将其准确度与纤维化模型进行比较。来自澳大利亚和西班牙的NAFLD患者在长达28年的跟踪期内形成了推导（n=584）和验证（n=477）队列。竞争风险回归和信息标准被用于模型开发。使用时间依赖性曲线下面积（tAUC）分析比较准确度。在随访期间，推导队列和验证队列中分别发生了52（9％）和11（2.3％）例LRE。年龄、2型糖尿病、白蛋白、胆红素、血小板计数和INR是LRE的独立预测因子，并被合并成一个模型（NAFLD结果得分- NOS）。NOS模型校准良好[校准斜率0.99（推导），0.98（验证）]，整体表现极佳[综合Brier分数0.07（推导）和0.01（验证）]。大于等于1.3的截止值识别了LRE风险较高的受试者（亚组危险比24.6，p <0.001，五年累计发病率分别为38％和1.0％）。在推导队列（tAUC分别为0.92和0.90）和验证队列（tAUC分别为0.80和0.82）中，五年和十年的预测准确度均非常出色。与FIB-4或NAFLD纤维化评分相比，NOS模型更准确地预测了5年和10年的LRE（p <0.001）。 NOS模型由易于获取的指标组成，在预测NAFLD患者的结果方面具有更高的准确度，超过了现有的纤维化模型。版权所有©2023年美国肝脏病学研究协会。

Management of non-alcoholic fatty liver disease (NAFLD) involves non-invasive prediction of fibrosis, which is a surrogate for patient outcomes. We aimed to develop and validate a model predictive of liver related events (LRE) of decompensation and/or hepatocellular carcinoma and compare its accuracy with fibrosis models.NAFLD patients from Australia and Spain followed for up to 28 years formed derivation (n=584) and validation (n=477) cohorts. Competing risk regression and information criteria were used for model development. Accuracy was compared with fibrosis models using time-dependent area under the curve (tAUC) analysis. During follow-up, LRE's occurred in 52 (9%) and 11 (2.3%) patients in derivation and validation cohorts respectively. Age, type 2 diabetes, albumin, bilirubin, platelet count, and INR were independent predictors of LRE and were combined into a model (NAFLD Outcomes Score - NOS). The NOS model calibrated well [calibration slope 0.99 (derivation), 0.98 (validation)] with excellent overall performance [integrated Brier score 0.07 (derivation) and 0.01 (validation)]. A cut off ≥ 1.3 identified subjects at higher risk of LRE, (subHazard Ratio 24.6, p < 0.001, five-year cumulative incidence 38% vs. 1.0% respectively). The predictive accuracy at five and ten years was excellent in both derivation (tAUC 0.92 and 0.90 respectively) and validation cohorts (tAUC 0.80 and 0.82 respectively). The NOS was more accurate than FIB-4 or NAFLD Fibrosis Score at predicting LRE at 5 and 10 years (p < 0.001).The NOS model consists of readily available measures and has greater accuracy in predicting outcomes in NAFLD patients than existing fibrosis models.Copyright © 2023 American Association for the Study of Liver Diseases.