UnknownPublic Health & HealthcareNIHR-supported projectMental Health
Optimising the Identification, Prioritisation and Nature of Support Offered to High-Intensity Users of Emergency Departments: A Data-Driven Approach Informed by Andersen’s Healthcare Utilization Model (Wejdan PhD)
Recipient organisationNIHR Applied Research Collaboration Northwest London
NIHR supportRecorded as supported by this research centre
PeriodMay 2025 — Ongoing
In plain English
AI plain-English summary
A tiny fraction of patients—less than 1% of the population—accounts for a disproportionate share of NHS emergency department visits, driving up costs and staff burnout. This project tackles a gap in knowledge: current support programmes treat high-intensity users as a single group, but the underlying reasons for frequent attendance vary widely. Some patients have complex medical needs, others face social crises like homelessness or mental health struggles, and many cycle through the ED because no other service meets their needs. Without understanding these subgroups, interventions remain generic and often ineffective. Using data from North West London’s Whole Systems Integrated Care database, the researcher will apply machine learning to identify distinct clusters of high-intensity users and build predictive tools to flag individuals at risk of continued high use. Economic evaluation will assess which tailored interventions—such as dedicated social prescribing or mental health support—offer the best value. If successful, this work could help the NHS shift from one-size-fits-all case management to targeted, cost-effective support that reduces emergency department strain and improves patient outcomes. The findings will directly inform the NHS High Intensity Use programme.
View original technical description
This project aims to optimise the identification and support of High-Intensity Users (HIUs) of Emergency Departments (EDs) by applying Andersen’s Healthcare Utilization Model. HIUs, individuals with frequent ED attendances, constitute less than 1% of the population yet account for a disproportionate share of NHS emergency service use, contributing to rising healthcare costs, staff burnout, and suboptimal patient experiences. Despite existing interventions, such as the NHS High Intensity Use programme, limited understanding of HIUs as a heterogeneous group hinders the development of scalable, targeted strategies. Using a retrospective cohort design and data from the Whole Systems Integrated Care (WSIC) database, the study will map HIU characteristics into Andersen’s model of predisposing, enabling, and need-based factors. It will apply machine learning and statistical modelling to identify subgroups and build predictive tools for identifying individuals at risk of continued high use. Clustering methods will be employed to uncover patterns within HIUs, with a view to designing subgroup-specific, cost-effective interventions that address their unique needs. A key innovation of this research lies in its data-driven, theory-informed approach, combining population-level analytics with an established behavioural model. It seeks to move beyond generic case management by tailoring interventions to the underlying social and clinical drivers of frequent ED use. The study also incorporates economic evaluation to assess the value of proposed strategies. Findings will contribute to NHS goals of improving urgent care sustainability and reducing health inequalities. By generating actionable insights into the drivers of frequent ED use and the impact of tailored interventions, this project offers a roadmap for more efficient, equitable healthcare delivery. This four-year PhD is fully funded by a Saudi Arabian government scholarship and benefits from collaboration with public health experts within the NHS, including advisors from the High Intensity Use programme in North West London.
Plain English summaries and category classifications on this site are generated by AI and may not perfectly reflect the original research.
Is something wrong? Let us know