Graph-Coupled HMMs for Modeling the Spread of Infection

TL;DR

This paper introduces Graph-Coupled Hidden Markov Models (GCHMMs) that utilize social network data to model and predict the spread of infectious diseases at an individual level, enabling personalized health insights.

Contribution

The paper extends Coupled Hidden Markov Models to incorporate social network structures for modeling disease spread at individual resolution.

Findings

Successfully modeled infection spread using mobile phone data from 84 individuals.

Enabled personalized infection predictions based on social network dependencies.

Extended CHMMs to dynamic social graphs for epidemiological modeling.

Abstract

We develop Graph-Coupled Hidden Markov Models (GCHMMs) for modeling the spread of infectious disease locally within a social network. Unlike most previous research in epidemiology, which typically models the spread of infection at the level of entire populations, we successfully leverage mobile phone data collected from 84 people over an extended period of time to model the spread of infection on an individual level. Our model, the GCHMM, is an extension of widely-used Coupled Hidden Markov Models (CHMMs), which allow dependencies between state transitions across multiple Hidden Markov Models (HMMs), to situations in which those dependencies are captured through the structure of a graph, or to social networks that may change over time. The benefit of making infection predictions on an individual level is enormous, as it allows people to receive more personalized and relevant health advice.