arXiv:2003.12310v1 [cs.LG] 27 Mar 2020 Proceedings of Machine Learning Research 1–17, 2020 Machine Learning for Healthcare Optimization of genomic classifiers for clinical deployment: evaluation of Bayesian optimization for identification of predictive models of acute infection and in-hospital mortality Michael B. Mayhew mmayhew@inflammatix.com Inflammatix, Inc. Burlingame, California, USA Elizabeth Tran etran@inflammatix.com Inflammatix, Inc. Burlingame, California, USA Kirindi Choi kchoi@inflammatix.com Inflammatix, Inc. Burlingame, California, USA Uros Midic umidic@inflammatix.com Inflammatix, Inc. Burlingame, California, USA Roland Luethy rluethy@inflammatix.com Inflammatix, Inc. Burlingame, California, USA Nandita Damaraju ndamaraju@inflammatix.com Inflammatix, Inc. Burlingame, California, USA Ljubomir Buturovic lbuturovic@inflammatix.com Inflammatix, Inc. Burlingame, California, USA Editor: Editor’s name Abstract Acute infection, if not rapidly and accurately detected, can lead to sepsis, organ failure and even death. Currently, detection of acute infection as well as assessment of a patient’s severity of illness are based on imperfect (and often superficial) measures of pa- tient physiology. Characterization of a patient’s immune response by quantifying expression levels of key genes from blood represents a potentially more timely and precise means of de- tecting acute infection and severe illness. Machine learning methods provide a platform for development of deployment-ready classification models robust to the smaller, more hetero- geneous datasets typical of healthcare. Identification of promising classifiers is dependent, in part, on hyperparameter optimization (HO), for which a number of approaches including grid search, random sampling and Bayesian optimization have been shown to be effective. In this analysis, we compare HO approaches for the development of diagnostic classifiers of acute infection and in-hospital mortality from gene expression of 29 diagnostic markers. Our comprehensive analysis of a multi-study patient cohort evaluates HO for three different © 2020 M.B. Mayhew, E. Tran, K. Choi, U. Midic, R. Luethy, N. Damaraju & L. Buturovic.