AI watchdog aims to catch unsafe medical recommendations before they reach patients

NCT ID NCT07718893

Not yet recruiting Knowledge-focused Sponsor: Waymark Source: ClinicalTrials.gov ↗

First seen Jul 22, 2026 · Last updated Jul 23, 2026 · Updated 1 time

Summary

This trial tests CITE, a tool that checks AI-generated care plans against a library of medical evidence to flag unsafe or unsupported recommendations. Researchers will compare CITE-assisted care plans to those made with standard AI safety measures or by clinicians alone. The study involves 240 Medicaid primary care patients and focuses on how accurately CITE identifies safety hazards and how many alerts it generates for clinicians.

What this could mean

Our plain-language read of the trial. This is informational only — not medical advice or a prediction.

Active substance: CITE evidence-grounding retrieve-and-verify layer
What this could lead to: If successful, CITE could help reduce medical errors by catching unsafe or unsupported recommendations in AI-generated care plans.
What could go wrong: This is a small, early-stage trial with 240 participants, so results may not apply broadly. The tool may flag too many false alarms, overwhelming clinicians.

This is an AI summary of the original study and may miss details. Read our disclaimer.

Get updates

Get notified about this study

Sign up to get updates when this study changes or when new studies for CLINICAL DECISION SUPPORT are added.

Our safety recommendation!

By submitting, you agree to our Terms of use

As listed by the trial registrant

The condition terms exactly as the trial's registrant entered them.

CLINICAL DECISION SUPPORT PATIENT SAFETY QUALITY OF HEALTH CARE

More trials for these conditions

Other studies related to the condition(s) this trial covers.