JMIR Publications

ABSTRACT

Background:

Approaches to addressing unwarranted variation in healthcare service delivery have traditionally relied on the prospective identification of activities and outcomes, based on a hypothesis, with subsequent reporting against defined measures. Practice-level prescribing data in England are made publicly available by the NHS Business Services Authority for all general practices. There is an opportunity to adopt a more data-driven approach to capture variability and identify outliers by applying hypothesis free data driven algorithms to national datasets.

Objective:

To develop and apply a hypothesis free algorithm to identify unusual prescribing behaviour in primary care data at multiple administrative levels in the NHS in England, and to visualise these results using organisation-specific interactive dashboards.

Methods:

Here we report a new data-driven approach to quantify how ‘unusual’ prescribing rates of a particular chemical within an organisation are as compared to peer organisations, over a period of six months (June-December 2021). This is followed by ranking to identify which chemicals are the most notable outliers in each organisation. These outlying chemicals are calculated for all practices, primary care networks, clinical commissioning groups and sustainability and transformation partnerships in England. Results are presented via organisation-specific interactive dashboards, the iterative development of which has been informed by user feedback.

Results:

User feedback and internal review of case studies demonstrate that our methodology identifies chemicals that are in line with local policies and internal reporting.

Conclusions:

Data-driven approaches overcome existing biases with regards to the planning and execution of audits, interventions and policy-making within NHS organisations, potentially revealing new targets for improved healthcare service delivery. We provide our dashboards as a candidate list for the consideration of expert users to prioritise for further interpretation and qualitative research in terms of potential targets for improved performance.