AutoPrognosis: Automated Clinical Prognostic Modeling via Bayesian Optimization with Structured Kernel Learning

[edit]

Ahmed Alaa, Mihaela Schaar ;
Proceedings of the 35th International Conference on Machine Learning, PMLR 80:139-148, 2018.

Abstract

Clinical prognostic models derived from largescalehealthcare data can inform critical diagnosticand therapeutic decisions. To enable off-theshelfusage of machine learning (ML) in prognosticresearch, we developed AUTOPROGNOSIS:a system for automating the design of predictivemodeling pipelines tailored for clinical prognosis.AUTOPROGNOSIS optimizes ensembles ofpipeline configurations efficiently using a novelbatched Bayesian optimization (BO) algorithmthat learns a low-dimensional decomposition ofthe pipelines’ high-dimensional hyperparameterspace in concurrence with the BO procedure.This is achieved by modeling the pipelines’ performancesas a black-box function with a Gaussianprocess prior, and modeling the “similarities”between the pipelines’ baseline algorithmsvia a sparse additive kernel with a Dirichlet prior.Meta-learning is used to warmstart BO with externaldata from “similar” patient cohorts by calibratingthe priors using an algorithm that mimicsthe empirical Bayes method. The system automaticallyexplains its predictions by presentingthe clinicians with logical association rules thatlink patients’ features to predicted risk strata. Wedemonstrate the utility of AUTOPROGNOSIS using10 major patient cohorts representing various aspectsof cardiovascular patient care.

Related Material