Development, Validation, and Evaluation of a Simple Machine Learning Model to Predict Cirrhosis Mortality

This cohort study compares different machine learning methods in predicting overall mortality in cirrhosis and uses machine learning to select easily scored clinical variables for a novel prognostic model in patients with cirrhosis. Key PointsQuestionCan a blended approach that uses clinical variables selected from machine learning to develop traditional prognostic models improve the accuracy of prediction while addressing challenges related to interpretability? FindingsIn a prognostic study including a cohort of 107 939 patients with cirrhosis, simple machine learning techniques performed as well as the more advanced ensemble gradient boosting techniques. Using the clinical variables identified from simple machine learning in a cirrhosis mortality model produced a new score more predictive than the traditional Model for End Stage Liver Disease with sodium. MeaningThese findings suggest that this blended approach can improve data-driven risk prognostication through the development of new scores that are both more transparent and actionable than machine learning and more predictive than traditional risk scores. ImportanceMachine-learning algorithms offer better predictive accuracy than traditional prognostic models but are too complex and opaque for clinical use. ObjectiveTo compare different machine learning methods in predicting overall mortality in cirrhosis and to use machine learning to select easily scored clinical variables for a novel cirrhosis prognostic model. Design, Setting, and ParticipantsThis prognostic study used a retrospective cohort of adult patients with cirrhosis or its complications seen in 130 hospitals and affiliated ambulatory clinics in the integrated, national Veterans Affairs health care system from October 1, 2011, to September 30, 2015. Patients were followed up through December 31, 2018. Data were analyzed from October 1, 2017, to May 31, 2020. ExposuresPotential predictors included demographic characteristics; liver disease etiology, severity, and complications; use of health care resources; comorbid conditions; and comprehensive laboratory and medication data. Patients were randomly selected for model development (66.7%) and validation (33.3%). Three different statistical and machine learning methods were evaluated: gradient descent boosting, logistic regression with least absolute shrinkage and selection operator (LASSO) regularization, and logistic regression with LASSO constrained to select no more than 10 predictors (par