TRV-2026-1666Certified recordPeer-reviewed

(AI)lephant in the Room: Utility of Generative AI to Develop Discussion Guides for Cardiac Surgery Morbidity and Mortality Conferences

Objective: Morbidity & Mortality Conferences (M&Ms) are forums to assess adverse outcomes and to analyze their root causes. We sought to utilize a large language model (LLM) to generate discussion materials for cardiac surgery M&Ms, based upon data available in the electronic medical record (EMR). Design: EMR data, including information from notes, bloodwork, vital sign monitoring, and the medication administration record, were input into a private instance of GPT-5. A prompt was iterated to accomplish three tas…

Health · Good Space — documented gain · certified 2026-10-17 · v1 · article view · machine-readable

Current reading — gain

A private GPT-5 instance produced case outlines, deviation tables and discussion questions for cardiac surgery M&Ms from EMR data, matching trainee outline length and earning high perceived clinical applicability.

What this doesn’t fix

The evaluation covered only fourteen cases and a survey of nine trainees at a single department, and preferences for operative and perioperative content were evenly split, so the findings are preliminary.

Evidence

Reader signal

How should this claim be treated?

Cite this record

Truvace Impact Record TRV-2026-1666, v1: “(AI)lephant in the Room: Utility of Generative AI to Develop Discussion Guides for Cardiac Surgery Morbidity and Mortality Conferences.” Truvace, 2026-10-17. /record/TRV-2026-1666 (accessed at citation time). sha256 463887b8245a48ff…

Calibration history

Every change to this record since certification, in the open. None yet — the reading has held since it entered the record.

  1. Certifiedv1463887b8245a…

    Certified into the record

Verify this record
How to verify without trusting this page

Fetch the canonical text of any version from /api/record/TRV-2026-1666 and hash it yourself — for example shasum -a 256 on the saved canonical field. The result must equal content_hash, and each version’s text ends with prev:followed by the prior version’s hash (version 1 chains to 64 zeros). If a single character of any version had been altered since certification, the chain would not reproduce.