Scalable Clinical Oversight of Large Language Models Via Uncertainty Triangulation

Starting soon · Not applicable

Conditions studied: Coronary Heart Disease (CHD)

In brief

This prospective, multi-reader, randomized crossover trial evaluates SCOUT (Scalable Clinical Oversight via Uncertainty Triangulation), a model-agnostic meta-verification framework that selectively defers unreliable large language model (LLM) predictions to clinicians by triangulating three orthogonal uncertainty signals: model heterogeneity, stochastic inconsistency, and reasoning critique. The trial assesses whether SCOUT-assisted review can reduce physician review time compared with standard manual review of AI-generated diagnoses while maintaining non-inferior diagnostic accuracy in coronary heart disease (CHD) subtyping.

Key facts

Study ID

NCT07414966

Run by

China National Center for Cardiovascular Diseases

People needed

7

Starts

2026-02-19

Expected to finish

2026-02-28

Last updated by the study team

2026-02-17

Who can join

Age: 18 and older. Sex: any. Healthy volunteers: not accepted.

You may qualify if…

• Board-certified or in-training cardiologists at Fuwai Hospital
• Spanning three experience strata: junior residents, senior residents, attending physicians

You may not qualify if…

• Clinicians involved in the development or optimization of the SCOUT framework
• Clinicians involved in the gold-standard adjudication process

Full record on ClinicalTrials.gov

Trial information comes from ClinicalTrials.gov and is refreshed daily. TrialsForMe does not provide medical care and does not run the studies it lists.