A coupled hidden Markov model for disease interactions

Chris Sherlock, Tatiana Xifara*, Sandra Telfer, Mike Begon

*Corresponding author for this work

Research output: Contribution to journalArticle

9 Citations (Scopus)
4 Downloads (Pure)

Abstract

To investigate interactions between parasite species in a host, a population of field voles was studied longitudinally, with presence or absence of six different parasites measured repeatedly. Although trapping sessions were regular, a different set of voles was caught at each session, leading to incomplete profiles for all subjects. We use a discrete time hidden Markov model for each disease with transition probabilities dependent on covariates via a set of logistic regressions. For each disease the hidden states for each of the other diseases at a given time point form part of the covariate set for the Markov transition probabilities from that time point. This allows us to gauge the influence of each parasite species on the transition probabilities for each of the other parasite species. Inference is performed via a Gibbs sampler, which cycles through each of the diseases, first using an adaptive Metropolis-Hastings step to sample from the conditional posterior of the covariate parameters for that particular disease given the hidden states for all other diseases and then sampling from the hidden states for that disease given the parameters. We find evidence for interactions between several pairs of parasites and of an acquired immune response for two of the parasites.

Original languageEnglish
Pages (from-to)609-627
Number of pages19
JournalJournal of the royal statistical society series c-Applied statistics
Volume62
Issue number4
Early online date6 May 2013
DOIs
Publication statusPublished - Aug 2013

Keywords

  • adaptive Markov chain Monte Carlo sampling
  • forward-backward algorithm
  • Gibbs sampler
  • hidden Markov models
  • zoonosis
  • random-walk metropolis
  • Anaplasma-phagocytophilum
  • dynamics
  • populations
  • bartonella
  • chains
  • algorithms
  • rodents
  • cowpox
  • voles

Cite this

A coupled hidden Markov model for disease interactions. / Sherlock, Chris; Xifara, Tatiana; Telfer, Sandra; Begon, Mike.

In: Journal of the royal statistical society series c-Applied statistics, Vol. 62, No. 4, 08.2013, p. 609-627.

Research output: Contribution to journalArticle

Sherlock, Chris ; Xifara, Tatiana ; Telfer, Sandra ; Begon, Mike. / A coupled hidden Markov model for disease interactions. In: Journal of the royal statistical society series c-Applied statistics. 2013 ; Vol. 62, No. 4. pp. 609-627.
@article{d17390f5d49d4394a77ec0ca81ba6e1b,
title = "A coupled hidden Markov model for disease interactions",
abstract = "To investigate interactions between parasite species in a host, a population of field voles was studied longitudinally, with presence or absence of six different parasites measured repeatedly. Although trapping sessions were regular, a different set of voles was caught at each session, leading to incomplete profiles for all subjects. We use a discrete time hidden Markov model for each disease with transition probabilities dependent on covariates via a set of logistic regressions. For each disease the hidden states for each of the other diseases at a given time point form part of the covariate set for the Markov transition probabilities from that time point. This allows us to gauge the influence of each parasite species on the transition probabilities for each of the other parasite species. Inference is performed via a Gibbs sampler, which cycles through each of the diseases, first using an adaptive Metropolis-Hastings step to sample from the conditional posterior of the covariate parameters for that particular disease given the hidden states for all other diseases and then sampling from the hidden states for that disease given the parameters. We find evidence for interactions between several pairs of parasites and of an acquired immune response for two of the parasites.",
keywords = "adaptive Markov chain Monte Carlo sampling, forward-backward algorithm, Gibbs sampler, hidden Markov models, zoonosis, random-walk metropolis, Anaplasma-phagocytophilum, dynamics, populations, bartonella, chains, algorithms, rodents, cowpox, voles",
author = "Chris Sherlock and Tatiana Xifara and Sandra Telfer and Mike Begon",
year = "2013",
month = "8",
doi = "10.1111/rssc.12015",
language = "English",
volume = "62",
pages = "609--627",
journal = "Journal of the royal statistical society series c-Applied statistics",
issn = "0035-9254",
publisher = "Wiley-Blackwell",
number = "4",

}

TY - JOUR

T1 - A coupled hidden Markov model for disease interactions

AU - Sherlock, Chris

AU - Xifara, Tatiana

AU - Telfer, Sandra

AU - Begon, Mike

PY - 2013/8

Y1 - 2013/8

N2 - To investigate interactions between parasite species in a host, a population of field voles was studied longitudinally, with presence or absence of six different parasites measured repeatedly. Although trapping sessions were regular, a different set of voles was caught at each session, leading to incomplete profiles for all subjects. We use a discrete time hidden Markov model for each disease with transition probabilities dependent on covariates via a set of logistic regressions. For each disease the hidden states for each of the other diseases at a given time point form part of the covariate set for the Markov transition probabilities from that time point. This allows us to gauge the influence of each parasite species on the transition probabilities for each of the other parasite species. Inference is performed via a Gibbs sampler, which cycles through each of the diseases, first using an adaptive Metropolis-Hastings step to sample from the conditional posterior of the covariate parameters for that particular disease given the hidden states for all other diseases and then sampling from the hidden states for that disease given the parameters. We find evidence for interactions between several pairs of parasites and of an acquired immune response for two of the parasites.

AB - To investigate interactions between parasite species in a host, a population of field voles was studied longitudinally, with presence or absence of six different parasites measured repeatedly. Although trapping sessions were regular, a different set of voles was caught at each session, leading to incomplete profiles for all subjects. We use a discrete time hidden Markov model for each disease with transition probabilities dependent on covariates via a set of logistic regressions. For each disease the hidden states for each of the other diseases at a given time point form part of the covariate set for the Markov transition probabilities from that time point. This allows us to gauge the influence of each parasite species on the transition probabilities for each of the other parasite species. Inference is performed via a Gibbs sampler, which cycles through each of the diseases, first using an adaptive Metropolis-Hastings step to sample from the conditional posterior of the covariate parameters for that particular disease given the hidden states for all other diseases and then sampling from the hidden states for that disease given the parameters. We find evidence for interactions between several pairs of parasites and of an acquired immune response for two of the parasites.

KW - adaptive Markov chain Monte Carlo sampling

KW - forward-backward algorithm

KW - Gibbs sampler

KW - hidden Markov models

KW - zoonosis

KW - random-walk metropolis

KW - Anaplasma-phagocytophilum

KW - dynamics

KW - populations

KW - bartonella

KW - chains

KW - algorithms

KW - rodents

KW - cowpox

KW - voles

U2 - 10.1111/rssc.12015

DO - 10.1111/rssc.12015

M3 - Article

VL - 62

SP - 609

EP - 627

JO - Journal of the royal statistical society series c-Applied statistics

JF - Journal of the royal statistical society series c-Applied statistics

SN - 0035-9254

IS - 4

ER -