An artificial intelligence system developed by researchers at the University of Hertfordshire could help the NHS better predict demand, allocate resources and plan services for 1.6 million people across the East of England.
The project, led by the University as part of the University of Hertfordshire Integrated Care System (UHICS) partnership, brings together the NHS, Hertfordshire County Council and voluntary, community, faith and social enterprise organisations across Hertfordshire and West Essex.
At its core is a machine learning model designed to forecast pressure on the health system before it happens.
Rather than focusing on individual diagnoses or patient-level interventions, the system looks at the NHS operational picture as a whole – analysing five years of historical data on admissions, treatments, re-admissions, bed capacity, infrastructure pressures and workforce availability. It also factors in local demographics, including an ageing population, deprivation levels and gender- and ethnicity-specific health trends.
The aim is straightforward but ambitious: give NHS and council leaders a clearer view of future demand so they can act earlier and plan smarter.
Iosif Mporas, Professor of Signal Processing and Machine Learning at the University’s School of Physics, Engineering and Computer Science, leads the project.
“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,” he said.
Using advanced machine learning techniques, the model generates short-, medium- and long-term forecasts, showing how demand for services is likely to shift – and what that means for staffing, infrastructure and patient care.
Charlotte Mullins, Strategic Programme Manager for NHW Herts and West Essex, said the implications go beyond spreadsheets and staffing rotas.
“The strategic modelling of demand can affect everything from patient outcomes including the increased number of patients living with chronic conditions,” she said.
“Used properly, this 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 as our strategy document.”
While artificial intelligence is increasingly used within the NHS, much of that work focuses on diagnostics or supporting clinical decisions. The Hertfordshire model is different: it is designed to inform system-wide operational management – essentially helping leaders see around corners.
The tool is already being tested in hospital settings and has the potential to expand across community services and care homes.
Its development comes at a pivotal moment. The Hertfordshire and West Essex Integrated Care Board is preparing to merge with two neighbouring boards to form the Central East Integrated Care Board. That will significantly expand the population base feeding into the model, strengthening its predictive capability.
Funded by the UHICS partnership, the project launched last year and continues throughout 2026. Professor Mporas’ multidisciplinary team includes two full-time postdoctoral researchers, with further development under way as the NHS grapples with rising demand and finite resources.
If successful, the model could offer something the health service urgently needs: not just more data, but better foresight.
