LSTM Home > LSTM Research > LSTM Online Archive

Mixed latent Markov models for longitudinal multiple diagnostics data with an application to Salmonella in Malawi

Henrion, Marc ORCID:, Chirambo, Angeziwa, Ndaru, Jambo, Nyirenda, Tonney and Gordon, Melita (2018) 'Mixed latent Markov models for longitudinal multiple diagnostics data with an application to Salmonella in Malawi' in JSM 2018, Vancouver, 2018.

[img] Text (JSM 2018 Proceedings paper)
867128.pdf - Published Version
Restricted to Repository staff only

Download (5MB)


Latent Markov models (LMMs) are commonly used to analyze longitudinal data from multiple diagnostic tests. LMMs consist of a structural model for the latent infection state, defining probabilities for the initial state and transmission between states, and a measurement model for the observed test results, defining the item response probabilities and thus test sensitivities and specificities. LMMs typically assume that tests are independent conditional on the latent infection state. This is likely to be violated for tests using similar technologies. We introduce random effects to relax the conditional independence assumption and we derive a generalization of the basic LMM for an application to Salmonella infection data. We analyze longitudinal data from four molecular PCR tests and a stool culture test from patients in Blantyre, Malawi. To assess the tests’ performances, we consider basic and mixed LMMs, both with time homogeneous and heterogeneous transition probabilities. We compare the different models and discuss technical considerations. A PCR assay
using primers from the TTR gene achieves the best sensitivity / specificity trade-off.

Item Type: Conference or Workshop Item (Paper)
Subjects: WA Public Health > Health Problems of Special Population Groups > WA 395 Health in developing countries
WA Public Health > Statistics. Surveys > WA 950 Theory or methods of medical statistics. Epidemiologic methods
WC Communicable Diseases > Infection. Bacterial Infections > Enteric Infections > WC 269 Salmonella infections
Faculty: Department: Clinical Sciences & International Health > Malawi-Liverpool-Wellcome Programme (MLW)
Related URLs:
Depositing User: Stacy Murtagh
Date Deposited: 06 Dec 2018 16:28
Last Modified: 23 Jan 2019 14:25


View details

Actions (login required)

Edit Item Edit Item