Su Pei-Yuan, Chen Yang-Yuan, Lin Chun-Yu, Su Wei-Wen, Huang Siou-Ping, Yen Hsu-Heng
Department of Internal Medicine, Division of Gastroenterology, Changhua Christian Hospital, Changhua 500, Taiwan.
College of Medicine, National Chung Hsing University, Taichung 400, Taiwan.
Diagnostics (Basel). 2023 Apr 13;13(8):1407. doi: 10.3390/diagnostics13081407.
The reported prevalence of non-alcoholic fatty liver disease in studies of lean individuals ranges from 7.6% to 19.3%. The aim of the study was to develop machine-learning models for the prediction of fatty liver disease in lean individuals. The present retrospective study included 12,191 lean subjects with a body mass index < 23 kg/m who had undergone a health checkup from January 2009 to January 2019. Participants were divided into a training (70%, 8533 subjects) and a testing group (30%, 3568 subjects). A total of 27 clinical features were analyzed, except for medical history and history of alcohol or tobacco consumption. Among the 12,191 lean individuals included in the present study, 741 (6.1%) had fatty liver. The machine learning model comprising a two-class neural network using 10 features had the highest area under the receiver operating characteristic curve (AUROC) value (0.885) among all other algorithms. When applied to the testing group, we found the two-class neural network exhibited a slightly higher AUROC value for predicting fatty liver (0.868, 0.841-0.894) compared to the fatty liver index (FLI; 0.852, 0.824-0.81). In conclusion, the two-class neural network had greater predictive value for fatty liver than the FLI in lean individuals.
在针对体型偏瘦个体的研究中，所报告的非酒精性脂肪性肝病患病率在7.6%至19.3%之间。本研究的目的是开发用于预测体型偏瘦个体患脂肪性肝病的机器学习模型。本回顾性研究纳入了12191名体重指数<23kg/m²的体型偏瘦受试者，这些受试者在2009年1月至2019年1月期间接受了健康检查。参与者被分为训练组（70%，8533名受试者）和测试组（30%，3568名受试者）。除病史以及饮酒或吸烟史外，共分析了27项临床特征。在本研究纳入的12191名体型偏瘦个体中，741人（6.1%）患有脂肪肝。在所有其他算法中，包含使用10个特征的二类神经网络的机器学习模型具有最高的受试者工作特征曲线下面积（AUROC）值（0.885）。当应用于测试组时，我们发现与脂肪肝指数（FLI；0.852，0.824 - 0.881）相比，二类神经网络在预测脂肪肝方面表现出略高的AUROC值（0.868，0.841 - 0.894）。总之，在体型偏瘦个体中，二类神经网络对脂肪肝的预测价值高于FLI。 （注：原文中FLI的范围“0.824 - 0.81”可能有误，这里按照翻译要求未做修改，推测可能是“0.824 - 0.881”之类的正确范围）
