New to MyHealth?
Manage Your Care From Anywhere.
Access your health information from any device with MyHealth. You can message your clinic, view lab results, schedule an appointment, and pay your bill.
ALREADY HAVE AN ACCESS CODE?
DON'T HAVE AN ACCESS CODE?
NEED MORE DETAILS?
MyHealth for Mobile
Abstract
Ensemble machine learning methods, like the superlearner, combine multiple models into a single one to enhance predictive accuracy. Here we explore the potential of the superlearner as a benchmarking tool for clinical risk prediction, illustrating the approach in identifying significant liver fibrosis among patients with non-alcoholic fatty liver disease (NAFLD). We used 23 demographic/clinical variables to train superlearner(s) on data from the NASH-CRN observational study (n=648) and validated models with data from the FLINT trial (n=270) and NHANES participants with NAFLD (n=1244). Comparing the superlearner's performance to existing models (FIB-4, NFS, Forns, APRI, BARD, and SAFE), it exhibited strong discriminative ability in the FLINT and NHANES validation sets, with AUCs of 0.79 (95% CI: 0.73-0.84) and 0.74 (95% CI: 0.68-0.79) respectively. Notably, the SAFE score performed similarly to the superlearner, both of which outperformed FIB-4, APRI, Forns, and BARD scores in the validation datasets. Surprisingly, the superlearner derived from 12 base models matched the performance of one with 90 base models. Overall, the superlearner, being the "best-in-class" ML predictor, excelled in detecting fibrotic NASH, and this approach can be used to benchmark the performance of conventional clinical risk prediction models.
View details for DOI 10.1097/HEP.0000000000000908
View details for PubMedID 38687634