Scalable Clinical Oversight of Large Language Models Via Uncertainty Triangulation

NCT07414966 · Status: NOT_YET_RECRUITING · Phase: NA · Type: INTERVENTIONAL · Enrollment: 7

Last updated 2026-02-17

No results posted yet for this study

Summary

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.

Conditions

  • Coronary Heart Disease (CHD)

Interventions

DIAGNOSTIC_TEST

SCOUT-Assisted Review Workflow

SCOUT-Assisted Review (Intervention Arm): Physicians review 56 cases processed through the SCOUT framework. For cases classified as low-uncertainty (D(x)=0), the AI prediction is auto-accepted without physician review. For high-uncertainty cases (D(x)=1), the physician reviews the case with access to the main model's chain-of-thought reasoning and the meta-verification audit results. The main model is DeepSeek-V3.1 with chain-of-thought prompting.

DIAGNOSTIC_TEST

Standard Manual Review Workflow

Physicians perform a full manual review of 54 cases using raw medical records with access to the AI model's predictions and reasoning, but without SCOUT uncertainty stratification or selective deferral.

Sponsors & Collaborators

  • China National Center for Cardiovascular Diseases

    lead OTHER_GOV

Study Design

Allocation
RANDOMIZED
Purpose
DIAGNOSTIC
Masking
NONE
Model
CROSSOVER

Eligibility

Min Age
18 Years
Sex
ALL
Healthy Volunteers
No

Timeline & Regulatory

Start
2026-02-19
Primary Completion
2026-02-28
Completion
2026-02-28

More Related Trials

Read the full study record

This page highlights key information. For complete eligibility criteria, study locations, investigator contacts, and the full protocol, visit the original record on ClinicalTrials.gov.

View NCT07414966 on ClinicalTrials.gov