Skip to content
TechBio Today

The front page of AI-driven biology.

peer reviewed · Nature Medicine

Prospective evaluation of a large language model clinical decision support system in the emergency department

Liron Leibovitch and colleagues report that a four-week emergency-department evaluation found mostly appropriate sampled outputs but falling clinician adoption and no reduction in length of stay.

Author affiliations

  • Rambam Health Care Campus
  • Technion – Israel Institute of Technology

In plain English

Researchers prospectively evaluated SHAKED, a clinical decision-support system built on multiple large language models, across two parallel units of a tertiary emergency department. In a sample of 100 outputs, experts judged 99 clinically appropriate and detected no adverse events. Adoption nevertheless fell from 68% to 30%, and median emergency-department length of stay was 4.9 hours in both groups.

How the study worked

A plain-language walk through the work behind the result.

  1. Ran a four-week DECIDE-AI stage 1 evaluation involving 1,138 patients in two parallel emergency-department units.

  2. Measured clinician use, sampled output appropriateness, safety events, length of stay, and consultation timing.

What they found

  • Expert review judged 99 of 100 sampled outputs clinically appropriate, with no detected adverse events.
  • Adoption declined from 68% to 30%, and length of stay was unchanged at 4.9 hours.

Why it matters

The study adds prospective workflow evidence to a field dominated by retrospective accuracy tests and shows that technically acceptable output does not guarantee sustained clinical use.

The catch

  • This was a stage 1 prospective evaluation, not a randomized efficacy trial.
  • The detailed appropriateness review covered a sample of 100 outputs.
  • A reported 9.4-minute consultation-cycle reduction was a nonsignificant trend, and the authors say the evidence does not justify deployment.

Evidence ledger

Sources behind this brief

  1. 01
    Primary source

    Nature Medicine article

    peer reviewed · Accessed August 22, 2026

  2. 02
    Supporting context

    SHAKED analysis code

    primary source · Accessed August 22, 2026