Identification of novel clinical factors associated with hepatic fat accumulation in extreme obesity

Abstract

Objectives: The accumulation of lipids stored as excess triglycerides in the liver (steatosis) is highly prevalent in obesity and has been associated with several clinical characteristics, but most studies have been based on relatively small sample sizes using a limited set of variables. We sought to identify clinical factors associated with liver fat accumulation in a large cohort of patients with extreme obesity.

Methods: We analyzed 2929 patients undergoing intraoperative liver biopsy during a primary bariatric surgery. Univariate and multivariate regression modeling was used to identify associations with over 200 clinical variables with the presence of any fat in the liver and with moderate to severe versus mild fat accumulation.

Results: A total of 19 data elements were associated with the presence of liver fat and 11 with severity of liver fat including ALT and AST, plasma lipid, glucose, and iron metabolism variables, several medications and laboratory measures, and sleep apnea. The accuracy of a multiple logistic regression model for presence of liver fat was 81% and for severity of liver fat accumulation was 77%.

Conclusions: A limited set of clinical factors can be used to model hepatic fat accumulation with moderate accuracy and may provide potential mechanistic insights in the setting of extreme obesity.

Figure 1

Distribution of hepatic fat by steatosis grades (n = 2929).

Figure 2

Receiver operator characteristic (ROC) curve for accuracy of final regression model for grade 0 versus grades 1, 2, and 3. The area under the curve was 0.8130.

Figure 3

Receiver operator characteristic (ROC) curve for accuracy of final regression model for grades 2 and 3 steatosis versus grade 1 steatosis. The area under the curve was 0.7724.