Abstract
Objectives The main objective of the study was to develop more accurate and precise short-term forecasting models for admissions and bed occupancy for an NHS Trust located in Bristol, England. Subforecasts for the medical and surgical specialties, and for different lengths of stay were realised
Design Autoregressive integrated moving average models were specified on a training dataset of daily count data, then tested on a 6-week forecast horizon. Explanatory variables were included in the models: day of the week, holiday days, lagged temperature and precipitation.
Setting A secondary care hospital in an NHS Trust in South West England.
Participants Hospital admissions between September 2016 and March 2020, comprising 1291 days.
Primary and secondary outcome measures The accuracy of the forecasts was assessed through standard measures, as well as compared with the actual data using accuracy thresholds of 10% and 20% of the mean number of admissions or occupied beds.
Results The overall Autoregressive Integrated Moving Average (ARIMA) admissions forecast was compared with the Trust’s forecast, and found to be more accurate, namely, being closer to the actual value 95.6% of the time. Furthermore, it was more precise than the Trust’s. The subforecasts, as well as those for bed occupancy, tended to be less accurate compared with the overall forecasts. All of the explanatory variables improved the forecasts.
Conclusions ARIMA models can forecast non-elective admissions in an NHS Trust accurately on a 6-week horizon, which is an improvement on the current predictive modelling in the Trust. These models can be readily applied to other contexts, improving patient flow.
Design Autoregressive integrated moving average models were specified on a training dataset of daily count data, then tested on a 6-week forecast horizon. Explanatory variables were included in the models: day of the week, holiday days, lagged temperature and precipitation.
Setting A secondary care hospital in an NHS Trust in South West England.
Participants Hospital admissions between September 2016 and March 2020, comprising 1291 days.
Primary and secondary outcome measures The accuracy of the forecasts was assessed through standard measures, as well as compared with the actual data using accuracy thresholds of 10% and 20% of the mean number of admissions or occupied beds.
Results The overall Autoregressive Integrated Moving Average (ARIMA) admissions forecast was compared with the Trust’s forecast, and found to be more accurate, namely, being closer to the actual value 95.6% of the time. Furthermore, it was more precise than the Trust’s. The subforecasts, as well as those for bed occupancy, tended to be less accurate compared with the overall forecasts. All of the explanatory variables improved the forecasts.
Conclusions ARIMA models can forecast non-elective admissions in an NHS Trust accurately on a 6-week horizon, which is an improvement on the current predictive modelling in the Trust. These models can be readily applied to other contexts, improving patient flow.
| Original language | English |
|---|---|
| Article number | e056523 |
| Pages (from-to) | e056523 |
| Number of pages | 9 |
| Journal | BMJ Open |
| Volume | 12 |
| Issue number | 4 |
| DOIs | |
| Publication status | Published - 20 Apr 2022 |
Bibliographical note
Funding Information:Contributors EE drafted the manuscript. EE and TJ analysed the data. MTR and TK supervised the project. TJ managed the data. MP conceptualised the methodology and conducted preliminary analysis of the data. MTR is the guarantor of this paper. The public contributed through the patient and public involvement process in the development of the study. Funding This study was funded by the HDRUK Better Care Partnership (#6.12). This research was supported by the National Institute for Health Research Applied Research Collaboration West.
Publisher Copyright:
©
Research Groups and Themes
- NIHR ARC West
- HEHP@Bristol