Bayesian Nonparametric Dimensionality Reduction of Categorical Data for Predicting Severity of COVID-19 in Pregnant Women

TL;DR

This paper introduces a Bayesian nonparametric method using latent Gaussian processes to reduce dimensionality of categorical clinical data, improving COVID-19 severity prediction in pregnant women.

Contribution

It presents a novel Bayesian framework for dimensionality reduction of multivariate categorical data, enhancing predictive accuracy for COVID-19 severity in pregnant women.

Findings

Latent Gaussian process outperforms dummy encoding in prediction accuracy.

The method effectively reduces high-dimensional categorical data.

Improved severity prediction for COVID-19 in pregnant women.

Abstract

The coronavirus disease (COVID-19) has rapidly spread throughout the world and while pregnant women present the same adverse outcome rates, they are underrepresented in clinical research. We collected clinical data of 155 test-positive COVID-19 pregnant women at Stony Brook University Hospital. Many of these collected data are of multivariate categorical type, where the number of possible outcomes grows exponentially as the dimension of data increases. We modeled the data within the unsupervised Bayesian framework and mapped them into a lower-dimensional space using latent Gaussian processes. The latent features in the lower dimensional space were further used for predicting if a pregnant woman would be admitted to a hospital due to COVID-19 or would remain with mild symptoms. We compared the prediction accuracy with the dummy/one-hot encoding of categorical data and found that the latent Gaussian process had better accuracy.