Abstract

Clinical prognostic models derived from largescale healthcare data can inform critical diagnostic and therapeutic decisions. To enable off-theshelf usage of machine learning (ML) in prognostic research, we developed AUTO P ROGNOSIS: a system for automating the design of predictive modeling pipelines tailored for clinical prog nosis. AUTO P ROGNOSIS optimizes ensembles of pipeline configurations efficiently using a novel batched Bayesian optimization (BO) algorithm that learns a low-dimensional decomposition of the pipelines’ high-dimensional hyperparameter space in concurrence with the BO procedure. This is achieved by modeling the pipelines’ performances as a black-box function with a Gaussian process prior, and modeling the “similarities” between the pipelines’ baseline algorithms via a sparse additive kernel with a Dirichlet prio Meta-learning is used to warmstart BO with external data from “similar” patient cohorts by cali brating the priors using an algorithm that mimics the empirical Bayes method. The system automatically explains its predictions by presenting the clinicians with logical association rules that link patients’ features to predicted risk strata. demonstrate the utility of AUTO P ROGNOSIS using 9 major patient cohorts representing various aspects of cardiovascular patient care.