Graph-Coupled HMMs for Modeling the Spread of Infection

Wen Dong, Alex Pentland, Katherine A. Heller
Proceedings of the 28th Conference on Uncertainty in Artificial Intelligence, PMLR R10:225-234, 2012.

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-vR10-dong12a, title = {Graph-Coupled HMMs for Modeling the Spread of Infection}, author = {Dong, Wen and Pentland, Alex and Heller, Katherine A.}, booktitle = {Proceedings of the 28th Conference on Uncertainty in Artificial Intelligence}, pages = {225--234}, year = {2012}, editor = {de Freitas, Nando and Murphy, Kevin}, volume = {R10}, series = {Proceedings of Machine Learning Research}, month = {14--18 Aug}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/r10/main/assets/dong12a/dong12a.pdf}, url = {https://proceedings.mlr.press/r10/dong12a.html}, 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.}, note = {Reissued by PMLR on 04 October 2026.} }
Endnote
%0 Conference Paper %T Graph-Coupled HMMs for Modeling the Spread of Infection %A Wen Dong %A Alex Pentland %A Katherine A. Heller %B Proceedings of the 28th Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2012 %E Nando de Freitas %E Kevin Murphy %F pmlr-vR10-dong12a %I PMLR %P 225--234 %U https://proceedings.mlr.press/r10/dong12a.html %V R10 %X 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. %Z Reissued by PMLR on 04 October 2026.
APA
Dong, W., Pentland, A. & Heller, K.A.. (2012). Graph-Coupled HMMs for Modeling the Spread of Infection. Proceedings of the 28th Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research R10:225-234 Available from https://proceedings.mlr.press/r10/dong12a.html. Reissued by PMLR on 04 October 2026.

Related Material