Machine learning approaches to enhance diagnosis and staging of patients with MASLD using routinely available clinical information

• DOI: 10.1371/journal.pone.0299487
• Publication Date: 2024-02-29T13:26:33Z
• Authors: Matthew McTeer; Douglas Applegate; Peter Mesenbrink; Vlad Ratziu; Jörn M. Schattenberg; Elisabetta Bugianesi; Andreas Geier; Manuel Romero Gomez; Jean-Francois Dufour; Mattias Ekstedt; Sven Francque; Hannele Yki-Jarvinen; Michael Allison; Luca Valenti; Luca Miele; Michael Pavlides; Jeremy Cobbold; Georgios Papatheo...; Adriaan G. Holleboom; Dina Tiniakos; Clifford Brass; Quentin M. Anstee; Paolo Missier
• Keywords: Bioinformatics (Computational Biology); Patients; Science; Q; R; 610 Medicine & health; General medicine, internal medicine and other clinical medicine; Machine Learning; Metabolic Diseases; Non-alcoholic Fatty Liver Disease; Bioinformatik (beräkningsbiologi); Humans; Medicine; Supervised Machine Learning; Human medicine; Research Article

Aims Metabolic dysfunction Associated Steatotic Liver Disease (MASLD) outcomes such as MASH (metabolic dysfunction associated steatohepatitis), fibrosis and cirrhosis are ordinarily determined by resource-intensive and invasive biopsies. We aim to show that routine clinical tests offer sufficient information to predict these endpoints.

Methods Using the LITMUS Metacohort derived from the European NAFLD Registry, the largest MASLD dataset in Europe, we create three combinations of features which vary in degree of procurement including a 19-variable feature set that are attained through a routine clinical appointment or blood test. This data was used to train predictive models using supervised machine learning (ML) algorithm XGBoost, alongside missing imputation technique MICE and class balancing algorithm SMOTE. Shapley Additive exPlanations (SHAP) were added to determine relative importance for each clinical variable.

Results Analysing nine biopsy-derived MASLD outcomes of cohort size ranging between 5385 and 6673 subjects, we were able to predict individuals at training set AUCs ranging from 0.719-0.994, including classifying individuals who are At-Risk MASH at an AUC = 0.899. Using two further feature combinations of 26-variables and 35-variables, which included composite scores known to be good indicators for MASLD endpoints and advanced specialist tests, we found predictive performance did not sufficiently improve. We are also able to present local and global explanations for each ML model, offering clinicians interpretability without the expense of worsening predictive performance.

Conclusions This study developed a series of ML models of accuracy ranging from 71.9—99.4% using only easily extractable and readily available information in predicting MASLD outcomes which are usually determined through highly invasive means.