Coronary Heart Disease (CHD)SCOUTNCT07414966
Scalable Clinical Oversight of Large Language Models Via Uncertainty Triangulation
A study testing SCOUT-Assisted Review Workflow and Standard Manual Review Workflow in people with Coronary Heart Disease (CHD), run by China National Center for Cardiovascular Diseases at 1 site in China.
Trial 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… Read more about this study
- Who is it for?
- Ages 18 years and older
- Conditions the study is for
- Coronary Heart Disease (CHD)
- What is being tested?
- SCOUT-Assisted Review Workflow and Standard Manual Review Workflow
- Could I receive a placebo?
- No, everyone receives an active treatment
- How many people
- 7 participants
- Where
- 1 siteChina
- Study dates
- 15 Feb 2026to 18 Feb 2026
- Phase
- Interventional
- Are there results?
- None posted in the registry
Key requirements
Who can take part, as listed by the sponsor. Only the study team can confirm whether you are eligible, so take this list to your doctor.
- Ages 18 years and older
- All sexes
- No healthy volunteers
- Adult, Older adult
Who may be able to join
- Board-certified or in-training cardiologists at Fuwai Hospital
- Spanning three experience strata: junior residents, senior residents, attending physicians
Who cannot join
- Clinicians involved in the development or optimization of the SCOUT framework
- Clinicians involved in the gold-standard adjudication process
Trial locations and contacts
1 site in 1 country.
About this study
Official title: Prospective Evaluation of a Model-Agnostic Meta-Verification Framework (SCOUT) for Scalable Clinical Oversight of Large Language Model Outputs in Coronary Heart Disease Diagnosis: A Multi-Reader, Randomized, Crossover Trial
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.
Read the detailed description
Background: Large language models are increasingly deployed in clinical workflows, yet requiring clinician review of every AI output negates the efficiency gains that motivate their adoption. SCOUT addresses this efficiency-safety paradox through algorithmic meta-verification.
The SCOUT framework triangulates three orthogonal external signals to determine case-level uncertainty: (1) Model Heterogeneity - whether a structurally different auxiliary LLM agrees with the primary model; (2) Stochastic Inconsistency - whether repeated sampling from the same model yields divergent outputs; (3) Reasoning Critique - whether an external checker model identifies logical flaws in the chain-of-thought reasoning.
In this crossover trial, 7 clinicians of varying seniority (2 junior residents, 3 senior residents, 2 attending physicians) each review all 110 cases under both standard manual review and SCOUT-assisted review workflows. The study evaluates workflow efficiency (primary endpoint) and diagnostic accuracy (secondary endpoint).
- Conditions
- Coronary Heart Disease (CHD)
- Being tested
- SCOUT-Assisted Review Workflow, Standard Manual Review Workflow
- Keywords
- artificial intelligence
- Medical subject headings
- Coronary Disease
What participants receive
What participants receive. In a randomised study each person is assigned to one group by chance.
SCOUT-Assisted Review WorkflowDiagnostic test
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.
Standard Manual Review WorkflowDiagnostic test
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.
| Study group | Role | What they receive |
|---|---|---|
| Control (Standard Manual Review) | Active comparator | Physicians manually review all cases in the control set (n=54) with access to AI predictions and reasoning. No selective deferral. Receives: Diagnostic Test: Standard Manual Review Workflow |
| Experimental (SCOUT-Assisted Review) | Experimental | Physicians process the intervention set (n=56) through the SCOUT framework. Low-uncertainty cases are auto-accepted; high-uncertainty cases undergo physician review with full audit trail. Receives: Diagnostic Test: SCOUT-Assisted Review Workflow |
What is being measured
The primary outcome is the main question the study is designed to answer.
Mean physician review time per case (minutes)
Mean time spent by each clinician reviewing and rendering a diagnostic decision per case under each arm. Measured in minutes.
Measured: Through study completion, an average of 2 hours.
Secondary outcomes (2)
Diagnostic accuracy (%)
Proportion of correct CHD subtype classifications (STEMI, NSTEMI, unstable angina, chronic coronary syndromes) under each arm.
Measured: Through study completion, an average of 2 hours.
Computational Return on Investment (ROI)
Ratio of physician time savings (valued at standardized minute-wages from Sanming healthcare reform benchmarks) to computational cost of SCOUT inference, stratified by clinician seniority level.
Measured: Through study completion, an average of 2 hours.
Timeline
From the start of the study to its completion; the mark is today. Estimated dates are the sponsor’s plan.
- First posted17 Feb 2026
- Study start15 Feb 2026
- Primary completion18 Feb 2026
- Study completion18 Feb 2026
Resources
- Official record on ClinicalTrials.govThe registry entry this page is built from, with its full change history.
- Other trials for Coronary Heart Disease (CHD)Studies of the same condition, open and under way.
- More trials run by China National Center for Cardiovascular DiseasesThe sponsor's other registered studies.
- What the trial phases meanHow a treatment moves from first tests in people to approval.
More details
For doctors and researchers: how the study is designed, who runs it, and its registry IDs.
Study design
- Study type
- Interventional
- Phase
- Phase N/A
- Primary purpose
- Diagnosis
- Allocation
- Randomised
- Intervention model
- Crossover
- Masking
- None (open label)
- Enrolment
- 7 participants (actual)
Sponsor and investigators
- Sponsor type
- Other government
- Responsible party
- Sponsor
IDs, dates and publications
- ClinicalTrials.gov ID
- NCT07414966
- Sponsor's protocol ID
- 2025-2702-1
- Acronym
- SCOUT
- Status last verified
- Feb 2026
- First submitted
- 9 Feb 2026
- Last updated
- 4 Nov 2026
- Results posted
- No
- Data monitoring committee
- Yes
- FDA-regulated drug
- No
- FDA-regulated device
- No
- Individual data sharing
- Yes: De-identified individual participant data underlying the results reported in this study will be made available.
Study at a glance
From the registry record, last updated by the sponsor on 4 Nov 2026. Recruitment status is as the sponsor reported it: confirm with the study team.
- Official title
- Prospective Evaluation of a Model-Agnostic Meta-Verification Framework (SCOUT) for Scalable Clinical Oversight of Large Language Model Outputs in Coronary Heart Disease Diagnosis: A Multi-Reader, Randomized, Crossover Trial
- ClinicalTrials.gov ID
- NCT07414966
- Acronym / sponsor ID
- SCOUT / 2025-2702-1
- Conditions
- Coronary Heart Disease (CHD)
- Keywords
- artificial intelligence
- Study type
- Interventional
- Recruitment status
- Completed
- Enrolment
- 7 participants (actual)
- Lead sponsor
- China National Center for Cardiovascular DiseasesOther government
- Study start
- 15 Feb 2026 (actual)
- Primary completion
- 18 Feb 2026 (actual)
- Study completion
- 18 Feb 2026 (actual)
- First posted
- 17 Feb 2026 (actual)
- Results
- Not posted in the source record
Clinical summary
The research question as the sponsor registered it. This describes what the study plans to test, not what it found.
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.
Detailed description
Background: Large language models are increasingly deployed in clinical workflows, yet requiring clinician review of every AI output negates the efficiency gains that motivate their adoption. SCOUT addresses this efficiency-safety paradox through algorithmic meta-verification.
The SCOUT framework triangulates three orthogonal external signals to determine case-level uncertainty: (1) Model Heterogeneity - whether a structurally different auxiliary LLM agrees with the primary model; (2) Stochastic Inconsistency - whether repeated sampling from the same model yields divergent outputs; (3) Reasoning Critique - whether an external checker model identifies logical flaws in the chain-of-thought reasoning.
In this crossover trial, 7 clinicians of varying seniority (2 junior residents, 3 senior residents, 2 attending physicians) each review all 110 cases under both standard manual review and SCOUT-assisted review workflows. The study evaluates workflow efficiency (primary endpoint) and diagnostic accuracy (secondary endpoint).
Study design
- Primary purpose
- Diagnosis
- Allocation
- Randomised
- Intervention model
- Crossover
- Masking
- None (open label)
- Number of arms
- 2
| Arm | Type | Receives |
|---|---|---|
| Control (Standard Manual Review) | Active comparator | Diagnostic Test: Standard Manual Review WorkflowPhysicians manually review all cases in the control set (n=54) with access to AI predictions and reasoning. No selective deferral. |
| Experimental (SCOUT-Assisted Review) | Experimental | Diagnostic Test: SCOUT-Assisted Review WorkflowPhysicians process the intervention set (n=56) through the SCOUT framework. Low-uncertainty cases are auto-accepted; high-uncertainty cases undergo physician review with full audit trail. |
Who may qualify
- Ages
- 18 years and older
- Sex
- All
- Healthy volunteers
- Not accepted
- Age groups
- Adult, Older adult
Key inclusion criteria (2 listed)
- Board-certified or in-training cardiologists at Fuwai Hospital
- Spanning three experience strata: junior residents, senior residents, attending physicians
Key exclusion criteria (2 listed)
- Clinicians involved in the development or optimization of the SCOUT framework
- Clinicians involved in the gold-standard adjudication process
Eligibility is decided by the study team after screening; this overview does not establish that a patient qualifies. Full inclusion and exclusion criteria.
Interventions
| Intervention | Type | Arms |
|---|---|---|
| SCOUT-Assisted Review WorkflowSCOUT-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 | Experimental (SCOUT-Assisted Review) |
| Standard Manual Review WorkflowPhysicians 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. | Diagnostic test | Control (Standard Manual Review) |
Primary outcome
Mean physician review time per case (minutes)
Time frame: Through study completion, an average of 2 hours.
Mean time spent by each clinician reviewing and rendering a diagnostic decision per case under each arm. Measured in minutes.
2 secondary outcomes
Diagnostic accuracy (%)
Time frame: Through study completion, an average of 2 hours.
Computational Return on Investment (ROI)
Time frame: Through study completion, an average of 2 hours.
Results and safety
The study is completed, but results are not available in the source record. That does not mean the treatment did or did not work.
Research links
- Official record on ClinicalTrials.govLast updated by the sponsor 4 Nov 2026.
- Individual participant dataSharing planned: Yes. De-identified individual participant data underlying the results reported in this study will be made available.
Related trials for Coronary Heart Disease (CHD)
Not yet recruiting
Autologous Thymus Transplant in Children With Congenital Heart Disease: A Pilot Study
Congenital Heart Disease (CHD)
Not yet recruiting
Hs-CRP-Guided Colchicine Treatment Targets in Very-High-Risk Patients With Coronary Artery Disease After PCI (TARGET-CHD)
Coronary Artery Disease, Atherosclerotic Cardiovascular Disease (ASCVD)
Active, not recruiting
Learning by Heart: The Effectiveness of an EF Training Program for Pre-schoolers With Critical CHD
Congenital Heart Disease, Executive Dysfunction
Not yet recruiting
UltraTrac for Cardiac Output Monitoring in Congenital Heart Disease
Congenital Heart Disease, Cardiac Output
RecruitingPhase 1/2
Butyric Acid Supplementation for Gut Improvement After Cardiac Surgery in Kids
Congenital Heart Disease (CHD)
Referral and contact
AzTrials does not enrol participants or take referrals. Contact the study team or a site listed below; they decide who can take part. This study is not recruiting at the moment.
The record lists no contact. Use the official record to reach the sponsor.
1 site in 1 country: see every site and its status.
Questions about this trial
What is this clinical trial studying?
A study testing SCOUT-Assisted Review Workflow and Standard Manual Review Workflow in people with Coronary Heart Disease (CHD), run by China National Center for Cardiovascular Diseases at 1 site in China.
The full registered description is in the About this study section and the official record.
Who may be eligible to take part?
The sponsor lists 2 inclusion and 2 exclusion criteria. Eligibility is decided by the study team after screening, so read the full criteria and contact a listed site.
Is this clinical trial currently recruiting?
The record says: finished, as of the sponsor's last update on 4 Nov 2026. Status can change between updates, so confirm with the study contact before making plans.
Where is the study taking place?
The record lists 1 site in China. Whether a site is taking part right now should be confirmed with that site. See every site.
What are the possible benefits and risks?
They depend on the study and the treatment, and no study can promise a benefit. The study team explains the known risks during informed consent, before anyone joins; the record itself does not list them.
Are results available for this study?
The study is completed, but results are not available in the source record. That does not mean the treatment did or did not work.
How can a doctor refer a patient or contact the research team?
The record lists no contact. The official record names the sponsor, who can be asked directly. AzTrials does not enrol participants or take referrals.
What does the primary outcome measure?
Mean physician review time per case (minutes) (time frame: Through study completion, an average of 2 hours.). It is what the study was designed to measure, not a finding.
Where can I read the original study information?
Does a listing mean the treatment is approved or proven to work?
No. A listing means the study is registered. It does not show that the treatment is safe, works, or is approved by a regulator.
How often is this information updated?
AzTrials copies changed records from ClinicalTrials.gov every night and reloads the whole registry every week. The sponsor last updated this record on 4 Nov 2026.