Journal
BMC MEDICINE
Volume 20, Issue 1, Pages -Publisher
BMC
DOI: 10.1186/s12916-022-02271-x
Keywords
COVID-19; Infectious disease; Outbreak; Healthcare demand; Real-time; Forecasting; Ensemble
Categories
Funding
- Wellcome Trust [210758/Z/18/Z, 206250/Z/17/Z, 206471/Z/17/Z, 208812/Z/17/Z, 221303/Z/20/Z, UNS110424]
- Health Protection Research Unit [NIHR200908]
- Bill & Melinda Gates Foundation [INV-001754, INV-003174, INV-016832]
- Bill & Melinda Gates Foundation (NTD Modelling Consortium) [OPP1184344, OPP1139859, OPP1183986, OPP1191821]
- BMGF [INV-016832, OPP1157270]
- CADDE [MR/S0195/1]
- FAPESP [18/14389-0]
- DTRA [HDTRA1-18-1-0051]
- European Union [RIA2020EF-2983-CSIGN, 101003688]
- Department of Health and Social Care using UK Aid
- Department of Health and SocialCare [PR-OD-1017-20001]
- National Institute for Health Research (NIHR) using UK aid from the UK Government
- ERC Starting Grant [757699]
- ERC [SG 757688]
- FCDO/Wellcome Trust [221303/Z/20/Z]
- HDR UK [MR/S003975/1]
- Global Challenges Research Fund (GCRF) project 'RECAP'
- ESRC [ES/P010873/1]
- HPRU [NIHR200908]
- Innovation Fund [01VSF18015]
- MRC [MR/N013638/1, MR/V027956/1, MC_PC_19065]
- Nakajima Foundation
- NIHR [16/136/46, 16/137/109, 1R01AI141534-01A1]
- Health Protection Research Unit for Modelling Methodology [NIHR200908, HPRU-201210096, NIHR200929, PR-OD-1017-20002]
- Royal Society [RP\EA\180004]
- Singapore Ministry of Health
- UK MRC [MC_PC_19065, LID DTP MR/N013638/1, MR/P014658/1]
- UK Public Health Rapid Support Team by United Kingdom Department of Health and Social Care
- UKRI [MR/V028456/1]
- MRC [MR/V027956/1, MR/V028456/1] Funding Source: UKRI
- Wellcome Trust [221303/Z/20/Z] Funding Source: Wellcome Trust
- Economic and Social Research Council [ES/P010873/1] Funding Source: researchfish
- Medical Research Council [MR/V027956/1, MC_PC_19065] Funding Source: researchfish
- Wellcome Trust [206471/Z/17/Z] Funding Source: researchfish
- Fundacao de Amparo a Pesquisa do Estado de Sao Paulo (FAPESP) [18/14389-0] Funding Source: FAPESP
- European Research Council (ERC) [757699] Funding Source: European Research Council (ERC)
- Bill and Melinda Gates Foundation [OPP1139859] Funding Source: Bill and Melinda Gates Foundation
Ask authors/readers for more resources
Forecasting healthcare demand is crucial during epidemics, and in this study, three disease-agnostic forecasting models were used to predict COVID-19 hospital admissions in England. The mean-ensemble model was the most accurate and consistently accurate among all the models. Using future observed cases improved the accuracy of admissions forecasts. Ensemble forecasts can provide consistently accurate predictions across time and locations.
Background Forecasting healthcare demand is essential in epidemic settings, both to inform situational awareness and facilitate resource planning. Ideally, forecasts should be robust across time and locations. During the COVID-19 pandemic in England, it is an ongoing concern that demand for hospital care for COVID-19 patients in England will exceed available resources. Methods We made weekly forecasts of daily COVID-19 hospital admissions for National Health Service (NHS) Trusts in England between August 2020 and April 2021 using three disease-agnostic forecasting models: a mean ensemble of autoregressive time series models, a linear regression model with 7-day-lagged local cases as a predictor, and a scaled convolution of local cases and a delay distribution. We compared their point and probabilistic accuracy to a mean-ensemble of them all and to a simple baseline model of no change from the last day of admissions. We measured predictive performance using the weighted interval score (WIS) and considered how this changed in different scenarios (the length of the predictive horizon, the date on which the forecast was made, and by location), as well as how much admissions forecasts improved when future cases were known. Results All models outperformed the baseline in the majority of scenarios. Forecasting accuracy varied by forecast date and location, depending on the trajectory of the outbreak, and all individual models had instances where they were the top- or bottom-ranked model. Forecasts produced by the mean-ensemble were both the most accurate and most consistently accurate forecasts amongst all the models considered. Forecasting accuracy was improved when using future observed, rather than forecast, cases, especially at longer forecast horizons. Conclusions Assuming no change in current admissions is rarely better than including at least a trend. Using confirmed COVID-19 cases as a predictor can improve admissions forecasts in some scenarios, but this is variable and depends on the ability to make consistently good case forecasts. However, ensemble forecasts can make forecasts that make consistently more accurate forecasts across time and locations. Given minimal requirements on data and computation, our admissions forecasting ensemble could be used to anticipate healthcare needs in future epidemic or pandemic settings.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available