Researchers at the University of Hertfordshire have created an operational artificial‑intelligence forecasting model designed to improve the efficiency of healthcare resources. The model is part of a partnership with regional NHS health bodies that seeks to transform the way public sector organisations use their extensive archives of historical data for forward‑looking decision making.
Traditionally, many AI projects in the health sector concentrate on diagnostics or patient‑level interventions. The Hertfordshire team emphasises that their tool is aimed at system‑wide operational management, providing managers with data‑driven insights for staffing, patient care and resource allocation.
Project Details
The forecasting model draws on five years of historical data, incorporating metrics such as admissions, treatments, re‑admissions, bed capacity and infrastructure pressures. It also integrates workforce availability and local demographic variables, including age, gender, ethnicity and deprivation levels, to produce more accurate projections.
Professor Iosif Mporas, a specialist in signal processing and machine learning, leads the project. The research team consists of two full‑time postdoctoral researchers and is scheduled to continue development through 2026. In a statement, Professor Mporas said, “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.”
The model generates forecasts that illustrate how healthcare demand is likely to evolve over short, medium and long‑term horizons. This capability allows leadership to move beyond reactive management and plan proactively.
Reactions
Charlotte Mullins, Strategic Programme Manager for NHS Herts and West Essex, noted that strategic demand modelling can influence outcomes for patients, particularly those living with chronic conditions. She added that, “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.”
Testing of the AI model in hospital settings is currently underway, with plans to extend its application to community services and care homes. The initiative demonstrates how legacy data can drive cost efficiencies and shows that predictive models can inform “do nothing” assessments and resource allocation in complex service environments such as the NHS.
Future Plans
The Hertfordshire and West Essex Integrated Care Board serves 1.6 million residents and is preparing to merge with two neighbouring boards to form the Central East Integrated Care Board. The next phase of development will incorporate data from this expanded population to improve the predictive accuracy of the model.
By integrating varied data sources—from workforce numbers to population health trends—the project aims to create a unified view that supports decision making across the health system. The model’s continued refinement through 2026 will focus on expanding its scope and enhancing its integration with NHS operational planning tools.
Conclusion
As the partnership moves forward, the University of Hertfordshire and NHS health bodies will continue to test and refine the forecasting model in hospital settings, with a view to scaling it to community services and care homes. The upcoming merger of integrated care boards will provide a larger data set, potentially increasing the model’s predictive power. The project is expected to complete its development cycle by 2026, after which it may be adopted more widely across the NHS to support proactive resource planning and improve overall healthcare efficiency.
