Integrating AI Predictions With Clinician Expertise
Public ClinicalTrials.gov record NCT07457840. Field values are reproduced from the official study page; the official ClinicalTrials.gov record remains the source of truth for eligibility, enrollment, and contact information.
Data is sourced from official ClinicalTrials.gov public API records. Always review the official ClinicalTrials.gov record for the latest information.
Official title
Transforming Clinical Decision Support Systems: Using Continuous Bayesian Updates to Integrate AI Predictions With Clinician Expertise
Brief summary
Reproduced verbatim from the official ClinicalTrials.gov record. Not medical advice.
Optimizing the interaction between the human and the machine is a major topic when deploying artificial intelligence (AI) at the bedside. The goal of this randomized clinical vignette study is to learn if presenting AI model outputs via continuous Bayesian updates and/or uncertainty quantification can improve diagnostic accuracy and clinician trust in healthcare professionals (physicians, residents, fellows, physician assistants (PAs), and nurse practitioners (NPs)) from US academic institutions evaluating patients with chest pain or dyspnea. The main questions it aims to answer are: * Does presenting AI predictions as Bayesian-updated post-test probabilities improve diagnostic accuracy compared to standard predicted probabilities? * Does the addition of uncertainty quantification (95% confidence intervals) to AI predictions improve diagnostic accuracy? * Do these interventions (Bayesian updating and/or uncertainty quantification) help clinicians recover from the negative effects of intentionally misleading AI predictions? Comparison: Researchers will compare standard AI predicted probabilities (presented without uncertainty) to Bayesian-updated post-test probabilities and/or outputs containing 95% confidence intervals to see if the interventions improve diagnostic accuracy, clinician confidence, and resilience against misleading AI. Participants will: * Review 8 clinical vignettes (simulated patient cases) focusing on chest pain or dyspnea. * Provide an initial "pre-test" diagnostic probability for 5 possible diagnoses based on the clinical history alone. * View AI model outputs that vary by experimental condition (standard probability vs. Bayesian update, with or without uncertainty intervals, and accurate vs. misleading). * Provide an updated "post-test" diagnostic probability for the diagnoses after viewing the AI output. * Select and rank diagnostic tests and therapeutic steps for each vignette. Complete a post-survey regarding their trust in the AI, comfort with the data presentation, and demographics.
Study identification
- NCT ID
- NCT07457840
- Recruitment status
- Enrolling by invitation
- Study type
- Interventional
- Phase
- Not applicable
- Enrollment
- 100 participants
Conditions and interventions
Conditions
Interventions
- Bayesian-Updated Post-Test Probability Behavioral
- Standard AI Predicted Probability Behavioral
- Uncertainty Quantification (95% Confidence Interval) Behavioral
Behavioral
Eligibility (public fields only)
- Age range
- 18 Years and older
- Sex
- All
- Healthy volunteers
- Accepts healthy volunteers
This page does not interpret eligibility. Detailed inclusion and exclusion criteria are on the official ClinicalTrials.gov record.
Study timeline
- Start date
- Feb 14, 2026
- Primary completion
- Nov 30, 2026
- Completion
- Nov 30, 2026
- Last update posted
- Jul 13, 2026
2026
United States locations
- U.S. sites
- 1
- U.S. states
- 1
- U.S. cities
- 1
| Facility | City | State | ZIP | Site status |
|---|---|---|---|---|
| ZSFG | San Francisco | California | 94110 | — |
Site contact phone numbers, emails, and investigator names are intentionally not displayed here. Open the official ClinicalTrials.gov record for site contact information.
About this trial record page
- What this page shows
- Public field values for ClinicalTrials.gov record NCT07457840, including study identification, conditions, interventions, eligibility (age, sex, healthy volunteer), timeline, and U.S. site list.
- What this page does not do
- No medical advice, eligibility judgments, treatment recommendations, study quality scoring, or AI-generated medical summaries. No site contact phone numbers, emails, or investigator names.
- Where the data comes from
- Sourced from the official ClinicalTrials.gov public API. The official record is the source of truth.
- Last refresh
- Last update posted Jul 13, 2026 · Synced Sep 2, 2026
Related: full search, browse by condition, browse by drug or therapy, browse by sponsor, browse by U.S. city.
Open the official record
The complete protocol, eligibility criteria, and contact information for NCT07457840 live on ClinicalTrials.gov.