Hierarchical Gaussian Processes and Mixtures of Experts to Model COVID-19 Patient Trajectories
Cui, S.; Yoo, E.; Li, D.; Laudanski, K.; Engelhardt, B.
Show 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. These hierarchical spatiotemporal models of EHR data bring us a step closer toward our goal of building flexible approaches to capture patient data that can be used in real-time systems*.
Matching journals
The top 6 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- High-dimensional Biomarker Identification for Scalable and Interpretable Disease Prediction via Machine Learning Models 95%
- A statistical approach for tracking clonal dynamics in cancer using longitudinal next-generation sequencing data 94%
- Gene regulatory network inference from single-cell data using optimal transport 94%
Similar papers in this journal
- Probabilistic Cause-of-disease Assignment using Case-control Diagnostic Tests: A Latent Variable Regression Approach 95%
- Penalized reduced rank regression for multi-outcome survival data supports a common metabolic risk score for age-related diseases 94%
- A Stability-Enhanced Lasso Approach for Covariate Selection in Non-Linear Mixed Effect Model 94%
Similar papers in this journal
- Tree-informed Bayesian multi-source domain adaptation: cross-population probabilistic cause-of-death assignment using verbal autopsy 93%
- Adaptive Transfer Learning for Time-to-Event Modeling with Applications in Disease Risk Assessment 93%
- Survival Analysis on Rare Events Using Group-Regularized Multi-Response Cox Regression 93%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.