A simple score based on three variables can help predict which patients with nonalcoholic fatty liver disease (NAFLD) will progress to hepatic decompensation, a study found.
The retrospective cohort study included 700 patients with NAFLD seen in one health system from 2000 to 2016. Data from 450 of the patients were used in construction of the model to predict hepatic events, and the other 250 patients were in the validation cohort. Results were published by the Journal of General Internal Medicine on March 10.
Overall, 49 patients (7%) had hepatic events during follow-up, at a mean of 6.2 years from initial NAFLD diagnosis. The risk of a hepatic event was 4.8% at five years, 10.6% at 10 years, and 11.3% at 12 years, based on Kaplan-Meier probability estimates. After investigation of a number of demographic, clinical, and biochemical factors, the researchers identified age, presence of diabetes, and platelet count as significant predictors of decompensation. Their resulting NAFLD decompensation risk score was: age×0.06335+presence of diabetes (yes=1, no=0)×0.92221−platelet count×0.01522.
The risk score model had an area under the curve of 0.89 (95% CI, 0.92 to 0.86) and performed well in both the validation (C-statistic, 0.91; 95% CI, 0.87 to 0.94) and overall (C-statistic, 0.89; 95% CI, 0.87 to 0.91) cohorts, leading the study authors to conclude that it had “excellent predictive ability to identify the development of hepatic decompensation in NAFLD patients up to 12 years from the time of diagnosis.”
They noted that the model could be easily applied in any clinical setting, including as a webpage or a smartphone app. “We thus believe that our model would help clinicians identify the small number of ‘at-risk’ patients who need close observation and/or referral to liver clinics from the vast majority of NAFLD patients who have a benign course,” the authors wrote. “Offering early intervention—such as bariatric surgery, dietary specialists, and/or enrollment in NAFLD therapeutic clinical trials—may help improve survival and decrease the need for liver transplantation.”
The authors noted that the study differed from similar previous efforts by focusing on patients with early NAFLD, whereas other risk prediction research has largely focused on patients who already have advanced fibrosis or cirrhosis. While they believe that this risk score would be applicable in a broader population than that included in the study, they also acknowledged that the study was limited by several factors, including its retrospective design and small number of events.