Using a continuous time hidden Markov process, with covariates, to model bed occupancy of people aged over 65 years

Previously, the application of a continuous time hidden Markov model with discrete states was used to model geriatric inpatient behaviour. This was itself built on research using a discrete deterministic model to represent the flow of geriatric patients around departments of geriatric medicine. This paper uses the continuous time hidden Markov models and includes the effect of covariates, age and sex, in the model. Fitting the models we can visually see that the two compartment models provides estimates that are much closer to those observed in the data. The addition of covariates provides us with evidence of a difference in length of stay between men and women. However, even significant alterations to the mean age of patients in the model does not effect the length of stay.