Machine learning algorithm improves detection of NASH (NAS-based) and at-risk NASH, a development and validation study

Lee, Jenny; Westphal, Max; Vali, Yasaman; Boursier, Jerome; Ostroff, Rachel; Alexander, Leigh; Chen, Yu; Fournier, Celine; Geier, Andreas; Francque, Sven; Wonders, Kristy; Tiniakos, Dina; Bedossa, Pierre; Allison, Mike; Papatheodoridis, Georgios; Cortez-Pinto, Helena; Pais, Raluca; Dufour, Jean-Francois; Leeming, Diana Julie; Harrison, Stephen; Cobbold, Jeremy; Holleboom, Adriaan G.; Yki-Järvinen, Hannele; Crespo, Javier; Ekstedt, Mattias; Aithal, Guruprasad P.; Bugianesi, Elisabetta; Romero-Gomez, Manuel; Karsdal, Morten; Yunis, Carla; Schattenberg, Jörn M.; Schuppan, Detlef; Ratziu, Vlad; Brass, Clifford; Duffin, Kevin; Zwinderman, Koos; Pavlides, Michael; Anstee, Quentin M.; Bossuyt, Patrick M.; LITMUS investigators, LITMUS investigators

Abstract

Background & Aims: Detecting non-alcoholic steatohepatitis (NASH) remains challenging, while at-risk NASH (steatohepatitis and F>2) tends to progress and is of interest for drug development and clinical application. We developed prediction models by supervised machine learning (ML) techniques, with clinical data and biomarkers to stage and grade non-alcoholic fatty liver disease (NAFLD) patients.

Approach & Results: Learning data were collected in the LITMUS Metacohort (966 biopsy-proven NAFLD adults), staged and graded according to NASH-CRN. Conditions of interest were clinical trial definition of NASH (NAS≥4;53%), at-risk NASH (NASH with F≥2;35%), significant (F>2;47%) and advanced fibrosis (F>3;28%). Thirty-five predictors were included. Missing data were handled by multiple imputation. Data were randomly split into training/validation (75/25) sets. Gradient boosting machine (GBM) was applied to develop two models for each condition: clinical versus extended (clinical and biomarkers). Two variants of the NASH and at-risk NASH models were constructed: direct and composite models.

Citation

Lee, J., Westphal, M., Vali, Y., Boursier, J., Ostroff, R., Alexander, L., …LITMUS investigators, L. I. (in press). Machine learning algorithm improves detection of NASH (NAS-based) and at-risk NASH, a development and validation study. Hepatology,

• Journal Article Type: Article
• Acceptance Date: Dec 23, 2022
• Deposit Date: Feb 23, 2023
• Journal: Hepatology
• Print ISSN: 0270-9139
• Electronic ISSN: 1527-3350
• Publisher: Wiley
• Peer Reviewed: Peer Reviewed
• Public URL: https://nottingham-repository.worktribe.com/output/17660766
• Additional Information: Authors on behalf of the LITMUS Investigators.