DynAIRx version 1
Research type
Research Study
Full title
DynAIRx: AIs for dynamic prescribing optimisation and care integration in multimorbidity
IRAS ID
312063
Contact name
Iain Buchan
Contact email
Sponsor organisation
University of Liverpool
Duration of Study in the UK
2 years, 6 months, 28 days
Research summary
Research question: Can artificial intelligence (AI) help bring together information about patient journeys scattered across different databases, and feed this back to prescribers alongside predictions of a patient’s risks and care guidelines to support medicines optimisation for people living with multiple long-term conditions?
Structured Medication Reviews (SMRs) were introduced in Primary Care to support delivery of the NHS Long Term Plan for medicines optimisation. However, it is often challenging to gather the information needed for these reviews due to poor integration of health records across providers and there is little guidance on how to identify those patients most in need of SMR. DynAIRx will focus on three key groups with poor outcomes due to multiple interacting conditions and medicines:
• Older people with frailty.
• People with co-existing mental and physical health problems.
• Other people with complex multimorbidity (≥4 long-term conditions), potentially problematic polypharmacy (≥10 regular medications), and/or potentially harmful drug-drug interactions.We will:
1. Interview all relevant stakeholders (doctors, pharmacists, patients) to identify what they need from a data system to run SMRs.
2. Gather data from large national data sources (~11million patients). This involves analyses of anonymised patient-level data from local participating practices. These data and the dashboard infrastructure will be held in Trustworthy Research Environments.
3. Train AIs to identify patterns of conditions, medicines, tests that lead to adverse outcomes to identify the people most in need of medicines review
4. Provide longitudinal summaries of risky patient journeys to be aware of
5. Introduce these trajectories into an existing prescribing audit and feedback system for GPs, creating a learning system in the form of prescribing dashboards.
6. Embed engagement with patients throughout the interviews and work together (Citizen's juries) to ensure the AIs are fair and ethical in who they prioritise for SMR.REC name
North East - Newcastle & North Tyneside 2 Research Ethics Committee
REC reference
22/NE/0088
Date of REC Opinion
22 Jun 2022
REC opinion
Further Information Favourable Opinion