Truace
Subscribe

A Real-World Evaluation of Large Language Model-Generated Hospital Courses in Pediatrics

Background Large language model (LLM)-generated hospital courses are increasingly integrated into electronic health records (EHRs), yet their accuracy and safety in pediatric populations remain poorly characterized. Objective To evaluate the accuracy, text quality, and perceived potential harm of EHR-integrated and LLM-generated hospital courses in pediatric inpatient care during early clinical implementation. Methods We conducted a descriptive evaluation from June 10 to August 8, 2025, at an academic freestandi…

By the Truvace desk1 min read1 sourcePeer-reviewedTRV-2026-0977· cite & verify
A Real-World Evaluation of Large Language Model-Generated Hospital Courses in Pediatrics
Alain Berset Cox's Bazar Sadar Hospital Swiss Cooperation 2018-02-06 (PID-0045781) by Press Information Department. Public domain

In brief

Background Large language model (LLM)-generated hospital courses are increasingly integrated into electronic health records (EHRs), yet their accuracy and safety in pediatric populations remain poorly characterized. Objective To evaluate the accuracy, text quality, and perceived potential harm of EHR-integrated and LLM-generated hospital courses in pediatric inpatient care during early clinical implementation.

Methods We conducted a descriptive evaluation from June 10 to August 8, 2025, at an academic freestanding children's hospital using an Epic EHR with an integrated LLM tool (GPT-4o and GPT-4.1). Clinicians across multiple roles, including attending physicians, residents, and advanced practice providers, reviewed LLM-generated hospital courses for their own patients.

Main points

  1. Objective To evaluate the accuracy, text quality, and perceived potential harm of EHR-integrated and LLM-generated hospital courses in pediatric inpatient care during early clinical implementation.
  2. Methods We conducted a descriptive evaluation from June 10 to August 8, 2025, at an academic freestanding children's hospital using an Epic EHR with an integrated LLM tool (GPT-4o and GPT-4.1).
  3. Clinicians across multiple roles, including attending physicians, residents, and advanced practice providers, reviewed LLM-generated hospital courses for their own patients.

The problem

Objective To evaluate the accuracy, text quality, and perceived potential harm of EHR-integrated and LLM-generated hospital courses in pediatric inpatient care during early clinical implementation.

Sources

  1. Peer-reviewedHospital Pediatrics2026-09-03

The debate