Machine learning models using non-invasive tests & B-mode ultrasound to predict liver-related outcomes in metabolic dysfunction-associated steatotic liver disease

Advanced metabolic-dysfunction-associated steatotic liver disease (MASLD) fibrosis (F3-4) predicts liver-related outcomes. Serum and elastography-based non-invasive tests (NIT) cannot yet reliably predict MASLD outcomes. The role of B-mode ultrasound (US) for outcome prediction is not yet known. We aimed to evaluate machine learning (ML) algorithms based on simple NIT and US for prediction of adverse liver-related outcomes in MASLD. Retrospective cohort study of adult MASLD patients biopsied between 2010–2021 at one of two Canadian tertiary care centers. Random forest was used to create predictive models for outcomes—hepatic decompensation, liver-related outcomes (decompensation, hepatocellular carcinoma (HCC), liver transplant, and liver-related mortality), HCC, liver-related mortality, F3-4, and fibrotic metabolic dysfunction-associated steatohepatitis (MASH). Diagnostic performance was assessed using area under the curve (AUC). 457 MASLD patients were included with 44.9% F3-4, diabetes prevalence 31.6%, 53.8% male, mean age 49.2 and BMI 32.8 kg/m 2 . 6.3% had an adverse liver-related outcome over mean 43 months follow-up. AUC for ML predictive models were—hepatic decompensation 0.90(0.79–0.98), liver-related outcomes 0.87(0.76–0.96), HCC 0.72(0.29–0.96), liver-related mortality 0.79(0.31–0.98), F3-4 0.83(0.76–0.87), and fibrotic MASH 0.74(0.65–0.85). Biochemical and clinical variables had greatest feature importance overall, compared to US parameters. FIB-4 and AST:ALT ratio were highest ranked biochemical variables, while age was the highest ranked clinical variable. ML models based on clinical, biochemical, and US-based variables accurately predict adverse MASLD outcomes in this multi-centre cohort. Overall, biochemical variables had greatest feature importance. US-based features were not substantial predictors of outcomes in this study.