Hierarchical Gaussian Processes and Mixtures of Experts to Model COVID-19 Patient Trajectories

Sunny Cui, Elizabeth C. Yoo, Didong Li, Krzysztof Laudanski, Barbara E. Engelhardt

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Scopus citations

Abstract

Gaussian processes (GPs) are a versatile nonparametric model for nonlinear regression and have been widely used to study spatiotemporal phenomena. However, standard GPs offer limited interpretability and generalizability for datasets with naturally occurring hierarchies. With large-scale, rapidly-updating electronic health record (EHR) data, we want to study patient trajectories across diverse patient cohorts while preserving patient subgroup structure. In this work, we partition our cohort of over 2000 COVID-19 patients by sex and ethnicity. We develop and apply a hierarchical Gaussian process and a mixture of experts (MOE) hierarchical GP model to fit patient trajectories on clinical markers of disease progression. A case study for albumin, an effective predictor of COVID-19 patient outcomes, highlights the predictive performance of these models.

Original languageEnglish (US)
Title of host publicationPacific Symposium on Biocomputing 2022, PSB 2022
EditorsRuss B. Altman, A. Keith Dunker, Lawrence Hunter, Marylyn D. Ritchie, Teri E. Klein
PublisherWorld Scientific
Pages266-277
Number of pages12
ISBN (Electronic)9789811250460
DOIs
StatePublished - 2022
Event27th Pacific Symposium on Biocomputing, PSB 2022 - Kohala Coast, United States
Duration: Jan 3 2022Jan 7 2022

Conference

Conference27th Pacific Symposium on Biocomputing, PSB 2022
Country/TerritoryUnited States
CityKohala Coast
Period1/3/221/7/22

All Science Journal Classification (ASJC) codes

  • Biomedical Engineering
  • Computational Theory and Mathematics

Keywords

  • COVID-19
  • electronic health record
  • Gaussian processes
  • patient trajectories

Fingerprint

Dive into the research topics of 'Hierarchical Gaussian Processes and Mixtures of Experts to Model COVID-19 Patient Trajectories'. Together they form a unique fingerprint.

Cite this