Novel coronavirus disease 2019 (COVID-19) is rapidly spreading throughout the world and while pregnant women present the same adverse outcome rates, they are underrepresented in clinical research. In this paper, we model categorical variables of 89 test-positive COVID-19 pregnant women within the unsupervised Bayesian framework. We model the data using latent Gaussian processes for density estimation of multivariate categorical data. The results show that the model can find latent patterns in the data, which in turn could provide additional insights into the study of pregnant women that are COVID-19 positive.