DataSheet_1_An easy-to-use AIHF-nomogram to predict advanced liver fibrosis in patients with autoimmune hepatitis.docx

BackgroundThe evaluation of liver fibrosis is essential in the management of patients with autoimmune hepatitis (AIH). We aimed to establish and validate an easy-to-use nomogram to identify AIH patients with advanced liver fibrosis.
MethodsAIH patients who underwent liver biopsies were included and randomly divided into a training set and a validation set. The least absolute shrinkage and selection operator (LASSO) regression was used to select independent predictors of advanced liver fibrosis from the training set, which were utilized to establish a nomogram. The performance of the nomogram was evaluated using the receiver characteristic curve (ROC), calibration curve, and decision curve analysis (DCA).
ResultsThe median age of 235 patients with AIH was 54 years old, with 83.0% of them being female. Six independent factors associated with advanced fibrosis, including sex, age, red cell distribution width, platelets, alkaline phosphatase, and prothrombin time, were combined to construct a predictive AIH fibrosis (AIHF)-nomogram. The AIHF-nomogram showed good agreement with real observations in the training and validation sets, according to the calibration curve. The AIHF-nomogram performed significantly better than the fibrosis-4 and aminotransferase-to-platelet ratio scores in the training and validation sets, with an area under the ROCs for predicting advanced fibrosis of 0.804 in the training set and 0.781 in the validation set. DCA indicated that the AIHFI-nomogram was clinically useful. The nomogram will be available at http://ndth-zzy.shinyapps.io/AIHF-nomogram/as a web-based calculator.
ConclusionsThe novel, easy-to-use web-based AIHF-nomogram model provides an insightful and applicable tool to identify AIH patients with advanced liver fibrosis.

背景 自身免疫性肝炎（autoimmune hepatitis, AIH）患者的肝纤维化评估在其临床管理中至关重要。本研究旨在构建并验证一款易于使用的列线图（nomogram），用于识别合并进展期肝纤维化的AIH患者。
方法 纳入接受肝活检（liver biopsy）的AIH患者，将其随机分为训练集与验证集。采用最小绝对收缩和选择算子（least absolute shrinkage and selection operator, LASSO）回归从训练集中筛选进展期肝纤维化的独立预测因子，并基于此构建列线图。通过受试者工作特征曲线（receiver operating characteristic curve, ROC）、校准曲线（calibration curve）以及决策曲线分析（decision curve analysis, DCA）评估该列线图的预测性能。
结果 本研究共纳入235例AIH患者，中位年龄为54岁，其中女性占比83.0%。筛选得到性别、年龄、红细胞分布宽度、血小板计数、碱性磷酸酶以及凝血酶原时间共6项与进展期肝纤维化相关的独立危险因素，以此构建AIH纤维化列线图（AIHF-nomogram）。校准曲线结果显示，AIHF-nomogram在训练集与验证集中均与实际观测结果具有良好的一致性。在训练集与验证集中，AIHF-nomogram的预测性能均显著优于肝纤维化4指数（fibrosis-4）与转氨酶血小板比值评分（aminotransferase-to-platelet ratio score），其预测进展期肝纤维化的ROC曲线下面积分别为0.804（训练集）与0.781（验证集）。决策曲线分析结果表明，该AIHF-nomogram具有临床实用性。该列线图可通过网页计算器http://ndth-zzy.shinyapps.io/AIHF-nomogram/在线获取。
结论 这款新颖且易于使用的网页版AIHF-nomogram模型，可为识别合并进展期肝纤维化的AIH患者提供一款兼具临床洞察力与应用价值的工具。