Abstract
Resource management is an essential feature of hospital management. This is especially true for geriatric services, as older people often have complex medical and social needs. Hospital management should benefit from an explanatory model that provides predictions of duration of stay and destination on discharge. We describe how a Bayesian belief network models the behaviour of geriatric patients using predictive variables: personal details, admission reasons and dependency levels. This approach is illustrated using data on 4722 patients admitted to geriatric medicine at St. George's Hospital, London; distributions of the patient outcome given typical values of the predictive variables are provided.
Original language | English |
---|---|
Pages (from-to) | 25-30 |
Number of pages | 6 |
Journal | Health Care Management Science |
Volume | 4 |
Issue number | 1 |
DOIs | |
Publication status | Published - 01 Jan 2001 |
Externally published | Yes |
Keywords
- Bayesian belief networks
- Duration of stay
- Geriatric patients
ASJC Scopus subject areas
- Medicine (miscellaneous)
- General Health Professions