Effect of Large Language Model in Assisting Discharge Summary Notes Writing for Hospitalized Patients

Effect of Large Language Model in Assisting Discharge Summary Notes Writing for Hospitalized Patients: A Pilot Pragmatic Randomized Controlled Trial

This pilot study aims to assess the feasibility of carrying out a full-scale pragmatic, cluster-randomized controlled trial which will investigate whether discharge summary writing assisted by a large language model (LLM), called CURE (Checker for Unvalidated Response Errors), improves care delivery without adversely impacting patient outcomes.

PATIENTS

Inclusion Criteria:

• Adult patients admitted to one of three participating cardiology services at Mayo Clinic in Rochester, MN

Exclusion Criteria:

• Minor patients (<18)
• Patients admitted to a hospital service where CURE is not implemented

CLINICIANS

Inclusion Criteria:

• Clinicians who provide care to randomized patients included in this pilot

Exclusion Criteria:

• Clinicians who do not provide care to randomized patients included in this pilot