68/100

Moderate evidence

GainPublished recordHealthGood Space

Verifiable summarization of electronic health records using large language models to support chart review

Truvace record
TRV-2026-2919raw data (JSON)
Version
v1Published
First published
Evidence type
Controlled or validated comparison
Sources
1 sourcePeer-reviewed
sha256
4ae6b225584c…check it

Objectives: Information overload in electronic health records hampers clinicians' ability to efficiently extract and synthesize critical information from a patient's longitudinal health record, leading to increased cognitive burden and delays in care. This study explores the potential of large language models (LLMs) to address this challenge by generating problem-based admission summaries for patients admitted with heart failure, a leading cause of hospitalization worldwide. Materials and methods: We developed a…

The gain

In a pilot study of physicians reviewing heart failure admissions, accuracy answering clinical questions was 88.0% with LLM-generated summaries versus 86.4% with standard chart review, and frequent summary use was linked to faster completion (P = .002).

What this doesn’t fix

The authors describe this as an exploratory, mixed-methods pilot study, and summary access did not significantly reduce overall completion time; benefits depended on how frequently individual physicians used the summaries.

Sources

1 on file
  1. Peer-reviewed2026-11-13

Cite this record

v1

Truvace Impact Record TRV-2026-2919, v1: “Verifiable summarization of electronic health records using large language models to support chart review.” Truvace, 2026-11-14. /record/TRV-2026-2919 (accessed on the day you copy it). sha256 4ae6b225584c1787…

Change history

1 version

Every change made to this record since it was first published, and why. Nothing has changed since it went up.

  1. Publishedv14ae6b225584c…

    Certified into the record

Check this record hasn’t been altered

Check this record hasn’t been altered
How to check it yourself, without trusting this page

Download any version from /api/record/TRV-2026-2919 and hash its canonical field yourself, for example with shasum -a 256. You should get its content_hash. Each version’s text also ends with prev:and the hash of the version before it (version 1 points to 64 zeros). If anyone had changed a single character of any version after it was saved, those hashes wouldn’t line up.