The quality and safety of using generative AI to produce patient-centred discharge instructions
Kristian Stanceski, Shiyin Zhong, Xumou Zhang, Sam Khadra, Marguerite Tracy, Linda Koria, Sarita Lo, Vasi Naganathan, Jinman Kim, Adam G. Dunn, Julie Ayre
Abstract
Patient-centred instructions on discharge can improve adherence and outcomes. Using GPT-3.5 to generate patient-centred discharge instructions, we evaluated responses for safety, accuracy and language simplification. When tested on 100 discharge summaries from MIMIC-IV, potentially harmful safety issues attributable to the AI tool were found in 18%, including 6% with hallucinations and 3% with new medications. AI tools can generate patient-centred discharge instructions, but careful implementation is needed to avoid harms.
Topics & Concepts
Patient safetyComputer scienceQuality (philosophy)MedicineHealth careEpistemologyEconomic growthEconomicsPhilosophyMachine Learning in HealthcareElectronic Health Records SystemsArtificial Intelligence in Healthcare and Education