Predicting Non-Alcoholic Fatty Liver Disease for Adults Using Practical Clinical Measures: Evidence from the Multi-ethnic Study of Atherosclerosis.

Abstract

Many adults have risk factors for non-alcoholic fatty liver disease (NAFLD). Screening all adults with risk factors for NAFLD using imaging is not feasible. To develop a practical scoring tool for predicting NAFLD using participant demographics, medical history, anthropometrics, and lab values. Cross-sectional. Data came from 6194 white, African American, Hispanic, and Chinese American participants from the Multi-Ethnic Study of Atherosclerosis cohort, ages 45-85 years. NAFLD was identified by liver computed tomography (≤ 40 Hounsfield units indicating > 30% hepatic steatosis) and data on 14 predictors was assessed for predicting NAFLD. Random forest variable importance was used to identify the minimum subset of variables required to achieve the highest predictive power. This subset was used to derive (n = 4132) and validate (n = 2063) a logistic regression-based score (NAFLD-MESA Index). A second NAFLD-Clinical Index excluding laboratory predictors was also developed. NAFLD prevalence was 6.2%. The model included eight predictors: age, sex, race/ethnicity, type 2 diabetes, smoking history, body mass index, gamma-glutamyltransferase (GGT), and triglycerides (TG). The NAFLD-Clinical Index model excluded GGT and TG. In the NAFLD-MESA model, the derivation set achieved an AUC_NAFLD-MESA = 0.83 (95% CI, 0.81 to 0.86), and the validation set an AUC_NAFLD-MESA = 0.80 (0.77 to 0.84). The NAFLD-Clinical Index model was AUC_Clinical = 0.78 [0.75 to 0.81] in the derivation set and AUC_Clinical = 0.76 [0.72 to 0.80] in the validation set (p_{Bonferroni-adjusted} < 0.01). The two models are simple but highly predictive tools that can aid clinicians to identify individuals at high NAFLD risk who could benefit from imaging.