Opportunities and risks of artificial intelligence in patient portal messaging in primary care

Abstract

The rapid increase in patient portal messaging has heightened the workload for primary care physicians (PCPs), contributing to burnout. The use of generative artificial intelligence (AI) to draft responses to patient messages has shown promise in reducing cognitive burden, yet there is still much unknown about the safety and perceptions of using AI drafts. This cross-sectional simulation study assessed whether PCPs could identify and correct errors in AI-generated draft responses to patient portal messages. Twenty practicing PCPs reviewed 18 patient portal messages, four of which contained errors categorized as objective inaccuracies or potentially harmful omissions. Each error was insufficiently addressed by 13–15 participants, and 35–45% of erroneous drafts were submitted entirely unedited. While 80% of participants agreed AI drafts reduced cognitive workload and 75% found them safe, uncorrected errors highlight patient safety risks, underscoring the need for improved design, training, and error-detection mechanisms for AI tools.