External validation of the fatty liver index for identifying nonalcoholic fatty liver disease in a population-based study

Abstract

Background & aims: We aimed to validate the fatty liver index (FLI), an algorithm that is based on waist circumference, body mass index, and levels of triglyceride and γ-glutamyltransferase. We calculated its ability to identify fatty liver disease from any cause or nonalcoholic fatty liver disease (NAFLD) in a large population of white elderly persons.

Methods: We collected ultrasonography and FLI data from participants of the Rotterdam Study from February 2009 to February 2012; 2652 subjects (mean age, 76.3 ± 6.0 years) were interviewed and received a clinical examination that included abdominal ultrasound, analysis of blood samples during fasting, and anthropometric assessment. The ability of the FLI to detect (nonalcoholic) fatty liver was assessed by using area under the receiver operator characteristic (AUROC) curve analysis.

Results: FLI score was associated with NAFLD in multivariable analysis (odds ratio, 1.05; 95% confidence interval [CI], 1.04-1.05; P < .001). FLI identified patients with NAFLD with an AUROC curve of 0.813 (95% CI, 0.797-0.830) and those with fatty liver from any cause with an AUROC curve of 0.807 (95% CI, 0.792-0.823).

Conclusions: The FLI (an algorithm that is based on waist circumference, body mass index, and levels of triglyceride and γ-glutamyltransferase) accurately identifies NAFLD, confirmed via ultrasonography, in a large, white, elderly population.

Keywords: AUROC; CI; Epidemiology; FLI; HOMA-IR; LAP; Lipid Accumulation Product; NAFLD; Obesity; The Netherlands; area under the receiver operator characteristic; confidence interval; fatty liver index; homeostasis model assessment of insulin resistance; lipid accumulation product; nonalcoholic fatty liver disease.