Latent Space Temporal Model of Microbial Abundance to Predict Domination and Bacteremia

TL;DR

This paper introduces a probabilistic latent space model for analyzing temporal changes in gut microbiomes, improving prediction of clinical events like domination and bacteremia, and uncovering new antibiotic-outcome links.

Contribution

A novel probabilistic latent space model that accounts for bacterial interactions and external effects, enhancing temporal microbiome analysis and clinical prediction accuracy.

Findings

Improved prediction accuracy for intestinal domination and bacteremia.

Validated known links between antibiotics and clinical outcomes.

Discovered new associations between antibiotics and microbiome dynamics.

Abstract

Gut microbial composition has been linked to multiple health outcomes. Yet, temporal analysis of this composition had been limited to deterministic models. In this paper, we introduce a probabilistic model for the dynamics of intestinal microbiomes that takes into account interaction among bacteria as well as external effects such as antibiotics. The model successfully deals with pragmatic issues such as random measurement error and varying time intervals between measurements through latent space modeling. We demonstrate utility of the model by using latent state features to predict the clinical events of intestinal domination and bacteremia, improving accuracy over existing methods. We further leverage this framework to validate known links between antibiotics and clinical outcomes, while discovering new ones.