Improving the accuracy of fatty liver index to reflect liver fat content with predictive regression modelling

Abstract

Background The fatty liver index (FLI) is frequently used as a non-invasive clinical marker for research, prognostic and diagnostic purposes. It is also used to stratify individuals with hepatic steatosis such as non-alcoholic fatty liver disease (NAFLD), and to detect the presence of type 2 diabetes or cardiovascular disease. The FLI is calculated using a combination of anthropometric and blood biochemical variables; however, it reportedly excludes 8.5-16.7% of individuals with NAFLD. Moreover, the FLI cannot quantitatively predict liver fat, which might otherwise render an improved diagnosis and assessment of fatty liver, particularly in longitudinal studies. We propose FLI+ using predictive regression modelling, an improved index reflecting liver fat content that integrates 12 routinely-measured variables, including the original FLI. Methods and findings We evaluated FLI+ on a dataset from the UK Biobank containing 28,796 individual estimates of proton density fat fraction derived from magnetic resonance imaging across normal to severe levels and interpolated to align with the original FLI range. The results obtained for FLI+ outperform the original FLI by delivering a lower mean absolute error by approximately 47%, a lower standard deviation by approximately 20%, and an increased adjusted R2 statistic by approximately 49%, reflecting a more accurate representation of liver fat content. Conclusions Our proposed model predicting FLI+ has the potential to improve diagnosis and provide a more accurate stratification than FLI between absent, mild, moderate and severe levels of hepatic steatosis.

Fatty liver prediction: a multivariable linear regression model based on transient elastography using routine biochemical indicators and waist circumference

“…Current research on the prediction of liver fat accumulation has focused on the use of machine learning algorithms to construct new complex predictive models and on optimizing the predictive accuracy of the Fatty Liver Index (FLI) [4][5][6], with little research on the construction of simple predictive models, but the most important step in the treatment of fatty liver is the early detection and diagnosis, and the active treatment of fatty liver reversibility. Therefore, it is important to construct simple linear models to lower the threshold of public understanding and actively encourage the public to monitor body mass characteristics on a daily basis to prevent fatty liver.…”

Fatty Liver Index (FLI) Identifies Not Only Individuals with Liver Steatosis but Also at High Cardiometabolic Risk

“…Some of the guidelines-approved scores for the estimation of liver steatosis could be used for an initial diagnosis [18]. Among these scores, the fatty liver index (FLI) developed by Bedogni et al [19] is an established index to diagnose hepatic steatosis and thus MASLD [18], and one of the most widely used and validated worldwide [20][21][22][23][24]. The parameters used to calculate FLI, i.e., BMI, waist circumference (WC), triglycerides (TG), and γ-GT concentration, are also markers of increased risk of cardiometabolic disease [25][26][27][28][29][30].…”

Low-Dose Aspirin and Hepatic Fat Quantity in Patients With MASLD

“…The primary end point of the study was the mean absolute change in hepatic fat fraction, measured by single-voxel breath-hold 1H–magnetic resonance spectroscopy (1H-MRS). While magnetic resonance imaging is the criterion standard for quantitative measurement of liver fat, we suggest considering the inclusion of serum biomarkers of steatosis, such as the SteatoTest and the Fatty Liver Index (FLI), in future studies.…”