How might dynamic Artificial Intelligence (AI) be used to support prescribing (DynAIRx project) to ensure efficient structured medication reviews, and what are the barriers to implementation?
Problem
Structured medication reviews (SMRs) aim to enhance shared decision-making in medication optimisation, particularly for patients with multimorbidity and polypharmacy. However, there is limited empirical evidence on SMR challenges and the potential role for artificial intelligence (AI) tools to support SMR implementation. DynAIRx project seeks to address these gaps by developing AI tools to support SMRs, focusing on individuals prone to medicine-related harm due to multimorbidity.
Approach
To explore how SMRs are currently being undertaken and how clinicians and patients feel they might be augmented by AI. Nine focus groups were conducted with doctors, pharmacists and clinical pharmacologists (n=21), and three patient focus groups with patients with multimorbidity (n=13). Five semi-structured interviews were held with 2 pharmacists, 1 trainee GP, 1 policy-maker and 1 psychiatrist. Transcripts were analysed using a thematic approach.
Findings
Two key themes limiting the effectiveness of SMRs in clinical practice were identified: ‘medication reviews in practice’ and ‘medication-related challenges’. There was wide variation in healthcare professional (HCP) perspectives and approaches to SMRs, with time being a major limiting factor due to the overwhelming density of information in electronic health records, especially for complex patients. Participants noted limitations to the efficient and effectiveness of SMRs in practice including the scarcity of digital tools for identifying and prioritising patients for SMRs; organisational and patient-related challenges in inviting patients for SMRs and ensuring they attend; the time-intensive nature of SMRs, the need for multiple appointments and shared decision-making; the impact of the healthcare context on SMR delivery; poor communication and data sharing issues between primary and secondary care, and difficulties in managing mental health medications and specific challenges associated with anticholinergic medication.. Participants stated that complex patients may need multiple appointments for a comprehensive review, and advocated for a team-based approach to managing multimorbid patients. HCPs welcomed user-friendly digital tools with intuitive interfaces, using visualisations/infographics, that could also be used to discuss clinical decisions with patients. A proposed solution to reduce time spent searching through records was a timeline linking diagnoses to medications based on indications. Quick access to resources, selective prompts, risk prediction models and risk calculators that could be incorporated in uncluttered ways were also on the wish list for AI tools. However, concerns were raised regarding medicolegal risks associated with digital tools, suggesting the need to screenshot the page viewed that led to certain clinical decisions.
Consequences
This study emphasises the complexity and time-intensive nature of SMRs, highlighting the potential for an AI prescribing support system to streamline the process. The insights gained will inform the co-development of the DynAIRx prototype to create a user-friendly digital tool to enhance SMRs for multimorbid patients.