How can we predict the number of future COVID-19 hospital admissions?

Research led by Sophie Meakin of the London School of Hygiene & Tropical Medicine in the United Kingdom suggests ensemble forecasts — a method combining multiple models to predict COVID-19 cases — may be more accurate in estimating COVID-19 hospital admissions in local areas.

The United Kingdom has reported over 8.89 million COVID-19 cases, and there are concerns that cases will exceed hospital resources. However, making accurate predictions is difficult given changes in local pandemic restrictions. Using confirmed COVID-19 cases as a predictor can help estimate future cases but still leaves a good deal of variability.

“Given the minimal data and computational requirements of the models evaluated here, this approach could be used to make early forecasts of local-level healthcare demand, and thus aid situational awareness and capacity planning, in future epidemic or pandemic settings,” concluded the research team.

The study “Comparative assessment of methods for short-term forecasts of COVID-19 admissions in England at the local level” is published on the medRxiv* preprint server.

How they did it

The study uses either individual or ensemble real-time forecasts to predict COVID-19—related hospital admissions in England. Weekly forecasts of daily admissions were taken between August 2020 and April 2021.

Three 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 — were used for forecasting. These models were measured for their accuracy in predicting the number of hospital admissions under several scenarios including, the length of the predictive horizon, when the forecast was created, the geographical location, and how forecasts improved when future cases were known.

The baseline model included no change from the last day of hospital admissions.

Mean-ensemble model was most accurate for forecasting COVID-19 hospital admissions

When the model assumes there is no change in current admissions, all models outperformed all base models in all scenarios. Of all the models, the mean-ensemble model made the most accurate predictions for the number of admissions.

Inputting COVID-19 cases into modeling promoted better predictions on the rate of future hospital admissions. However, admission predictions continued to be less accurate and sometimes even worse than trend-based modeling when other factors, such as pandemic restriction and fluctuating COVID-19 cases, were considered.

Ways to improve COVID-19 predictions for hospital admissions

The researchers propose several ways to improve the accuracy of COVID-19 forecasting. One method is to improve the underlying case forecasts by adding more detailed predictors of hospital admissions, such as labeling COVID-19 cases by age.

Adding additional models such as statistical and machine learning models may improve prediction levels as well. Another could include an ensemble model pool or a weighted ensemble that takes past performance into account.

Lastly, forecasts would be improved by mapping a smaller geographical region.

Based on the results, the researchers suggest “When forecasting local-level hospital admissions in epidemic settings, assuming no change in admissions is rarely better than including at least a trend component; including a lagged predictor, such as cases, can further improve forecasting accuracy, but is dependent on making good case forecasts, especially for longer forecast horizons. Using a mean-ensemble overcomes some of the variable performance of individual models and allows us to make more accurate and more consistently accurate forecasts across time and locations.”

*Important Notice

medRxiv publishes preliminary scientific reports that are not peer-reviewed and, therefore, should not be regarded as conclusive, guide clinical practice/health-related behavior, or treated as established information.

Written by

Jocelyn Solis-Moreira

Jocelyn Solis-Moreira graduated with a Bachelor's in Integrative Neuroscience, where she then pursued graduate research looking at the long-term effects of adolescent binge drinking on the brain's neurochemistry in adulthood.