Daily Dose: FAST-3 Algorithm Shows Promise as Classifier for Advanced Fibrosis in MASLD

_{©New Africa/AdobeStock}

Patient Care brings primary care clinicians a lot of medical news every day—it’s easy to miss an important study. The Daily Dose provides a concise summary of one of the website's leading stories you may not have seen.

Last week, we reported on findings from a study abstract presented at the American Association for the Study of Liver Diseases’ annual scientific conference, The Liver Meeting 2023.

The study

Researchers conducted the study with the aim of developing a noninvasive classifier that would yield a quantitative estimation of available laboratory measures and transient elastography (TE) parameters as a screening and diagnostic test for advanced metabolic dysfunction-associated steatohepatitis (MASH) (NAS >4 and fibrosis stage >3 [F3]) in adults with metabolic dysfunction-associated steatotic liver disease (MASLD).

The retrospective cohort study included 258 adults with MASLD who had been evaluated with TE (FibroScan®) as well as liver biopsy.

The team developed and internally validated a predictive logistic regression-based algorithm using FibroScan-captured controlled attenuation parameter (CAP) and liver stiffness score (LSM) data for all participants.

After evaluating fractional polynomial forms of the predictors, researchers built the final model with L1 penalization (LASSO) using 10-fold cross-validation to obtain the optimum penalty factor. They examined the model for calibration (calibration plot), discrimination (area under ROC curve [AUROC]), and performance (Brier score, sensitivity, specificity, positive predictive value [PPV], and negative predictive value [NPV]), and established optimal cut points for “rule-in” and “rule-out” criteria.

Findings

Named FAST-3, the predictive algorithm incorporated 5 clinical variables (sex, body mass index, aspartate aminotransferase, bilirubin, platelet count), CAP, and LSM.

The quantitative classifier demonstrated good calibration (calibration plot), discrimination (AUROC: 0.77 [0.71 – 0.83]), and performance (Brier score 0.13 [0.11 – 0.16]), according to the study abstract. After evaluation of optimal rule-in/rule-out cut point criteria, the investigators reported excellent PPV and NPV (PPV: 45% and NPV: 95%).

Authors' comment

"The potential utility for a non-invasive classifier (FAST-3) as a replacement for invasive liver biopsies to identify patients with advanced fibrosis in MASH (NAS4/F3) is enormous."

Click here for more details.