Inference of a Multi-Domain Machine Learning Model to Predict Mortality in Hospital Stays for Patients with Cancer upon Febrile Neutropenia Onset Xinsong Du ** Department of Health Outcomes and Biomedical Informatics, College of Medicine, University of Florida, 2004 Mowry Road, Gainesville, FL, 32610 Jae Min ** Department of Epidemiology, College of Medicine, University of Florida, 2004 Mowry Road, Gainesville, FL, 32610 Dominick J. Lemas Department of Health Outcomes and Biomedical Informatics, College of Medicine, University of Florida, 2004 Mowry Road, Gainesville, FL, 32610 Mattia Prosperi Department of Epidemiology, College of Medicine, University of Florida, 2004 Mowry Road, Gainesville, FL, 32610 Abstract Background:. Febrile neutropenia (FN) has been associated with high mortality, especially among adults with cancer. Understanding the patient- and provider- level heterogeneity in FN hospital admissions has potential to inform personal- ized interventions focused on increasing survival of individuals with FN. Objective:. In this study we leverage machine learning techniques to disentan- gling the complex interactions among multi-domain risk factors in a population with FN. Our goal is to evaluate the capability of machine learning model for FN mortality prediction using high-dimensional admission data, evaluate the * Corresponding author ** Both authors contributed equally to this research. Email address: xinsongdu@ufl.edu (Xinsong Du) Preprint submitted to Arxiv June 30, 2022 arXiv:1902.07839v1 [q-bio.QM] 21 Feb 2019