UKHSA's Machine-Learning Pilot for Real-Time Winter Health-Care Demand Forecasting

NHS service managers need advance warning of winter respiratory-illness surges (driven by RSV in children under five) to plan capacity, but historically had to rely on data with substantial lag.

Pilot an automated forecasting pipeline, built on existing daily syndromic surveillance data, to predict the timing and intensity of seasonal peaks in NHS 111 'cough' calls and emergency-department 'acute bronchiolitis' attendances up to 28 days ahead.

During the 2022-23 winter season, UKHSA epidemiologists tested 252 model specifications combining seven supervised-learning methods (random forest, support vector machines, elastic-net regression, gradient boosting and others) with different seasonality and trend terms, publishing the full comparison in a peer-reviewed evaluation.

Random-forest models with Fourier seasonal terms performed best, achieving peak-timing and intensity forecast errors of 0.0195 (NHS 111 calls) and 0.0267 (ED attendances). In one real-time test, the model correctly forecast the 29 November 2022 bronchiolitis peak date and estimated its intensity within roughly 9% of the actual figure. An unprecedented December 2022 surge in NHS 111 cough calls, 39.3% above the previous record and driven partly by public anxiety over invasive group A streptococcal infections, degraded the cough indicator's specificity and confounded forecasts trained on historical patterns.

The authors conclude that automated forecasts fall outside their training range in genuinely novel seasons and should always be accompanied by expert interpretation rather than used as a standalone decision tool.