Researchers at Stanford have built an AI-enabled agent to ease the burden of writing hospital discharge summaries. Findings reporting lower burnout scores in providers were published in JAMA Network Open.
Hospital discharge summaries are “extremely important for a patient’s ongoing care,” of course. It can take 15-30 minutes to write a single discharge summary, however, “depending on the complexity of the patient’s case.” Stanford researchers built their own in-house summary agent and deployed it at a patient care unit on August 1, 2025.
The 11 physicians working on the unit “received a secure email containing AI-generated discharge summaries for each of their patients every morning. The format of the summaries, borrowed from a best-practices discharge summary template, was designed by Stanford Medicine hospitalists. It included a one-liner about what brought the patient to the hospital, a high-level overview of their admission and a structured summary for each of the patient’s inpatient diagnoses.”
The doctors had the option to ignore the AI-generated summaries, but many ended up using the tool. Feedback on 100 AI-enabled summaries found “some omissions (25%) and inaccuracies (20%), but hallucinations were rare (2%). Physicians rated 88 unedited summaries as having no harm potential and 21 as having mild harm potential.” One was rated by a physician as likely to cause moderate harm, but independent reviewers determined the summary posed no risk.
