Seven opportunities for artificial intelligence in primary care electronic visits: qualitative study of staff and patient views

Purpose: Increased workload and cost associated with electronic visits (eVisits) in primary care could be reduced by using Artificial Intelligence (AI), though it is unknown whether this would be acceptable to staff and patients. We explored patient and primary care staff views on the use of, and opportunities for, AI in eVisits.
Methods: Semi-structured interviews and focus groups with primary care staff (n=16) and patients (n=37) from primary care practices in north-west England and London (n=14) using the Patchs eVisits system (www.patchs.ai) from May 2020 to September 2021. Verbatim transcripts were analysed using thematic analysis.
Results: Misconceptions of AI were common, which led to initial reservations about its use in eVisits. Perceived potential AI benefits included reduced staff workload and quicker response times for patients. Safety concerns stemmed from the complexity of primary care and fears of a depersonalised service. Seven opportunities for AI in eVisits were identified: workflowing, signposting, prioritising, asking questions, writing assistance, self-help information provision, and face-to-face appointment booking. Despite staff concerns about patient acceptability, most patients welcomed AI if it were used as an adjunct (not replacement) for clinical judgement and could support them in getting help quicker. The retention of clinical oversight and ongoing evaluation was key to staff acceptability.
Conclusions: Patients and staff welcome the use of AI and identified seven potential uses in eVisits to decrease staff workload and improve patient safety. Successful implementation will depend on clear communication from practices, demonstrating and monitoring safety, clarifying misconceptions, and reassurance it will not replace humans.