TL;DR

Researchers at the University of Hertfordshire are working with regional NHS bodies to develop an AI forecasting model that uses five years of historical data to predict healthcare demand. The tool is designed to help NHS leaders make proactive decisions about staffing, patient care, and resource allocation.

From Historical Data to Forward Planning

Public sector organisations often sit on large archives of historical data that never feed into forward-looking decisions. The partnership between the University of Hertfordshire and NHS Herts and West Essex aims to change that by applying machine learning to operational planning.

Unlike most healthcare AI projects, which focus on diagnostics or individual patient interventions, this model targets system-wide operational management. It integrates metrics including admissions, treatments, re-admissions, bed capacity, and infrastructure pressures. The system also factors in workforce availability and local demographics such as age, gender, ethnicity, and deprivation levels.

“By working together with the NHS, we are creating tools that can forecast what will happen if no action is taken and quantify the impact of a changing regional demographic on NHS resources,” said Professor Iosif Mporas, who leads the project.

Practical Applications

The model produces short-, medium-, and long-term forecasts showing how healthcare demand is likely to shift. This gives NHS leadership the ability to plan ahead rather than react to pressures as they emerge.

Charlotte Mullins, strategic programme manager for NHS Herts and West Essex, said the tool “could enable NHS leaders to take more proactive decisions and enable delivery of the 10-year plan articulated within the Central East Integrated Care Board.”

The model is currently being tested in hospital settings. The next phase will extend it to community services and care homes, aligning with structural changes in the region. The Hertfordshire and West Essex Integrated Care Board, which serves 1.6 million residents, is preparing to merge with two neighbouring boards, creating a larger dataset for improved predictions.

Looking Forward

The project demonstrates a practical approach to using AI in the NHS — not replacing clinical judgement but improving the operational decisions that determine whether resources are in the right place at the right time. As the model scales to cover a wider population, it could offer a template for other integrated care boards looking to make better use of existing data.