Medical Information Only. Always consult your healthcare provider before enrolling in any clinical trial.
NCT06098950 · ClinicalTrials.gov registry record · NA
Human Algorithm Interactions for Acute Respiratory Failure Diagnosis
A NA study, sponsored by University of Michigan.
- Completed
- Registry status
- NA
- Development phase
- 457
- Enrollment target
NCT06098950 is a NA study that has completed, run by University of Michigan. The registered enrollment target is 457 participants.
The verdict
NCT06098950, a NA study, has completed, sponsored by University of Michigan.
- COMPLETED
- Registry status
- NA
- Development phase
- 457 participants
- Enrollment target
Study Summary
Artificial intelligence (AI) shows promising in identifying abnormalities in clinical images. However, systematically biased AI models, where a model makes inaccurate predictions for entire subpopulations, can lead to errors and potential harms. When shown incorrect predictions from an AI model, clinician diagnostic accuracy can be harmed. This study aims to study the effectiveness of providing clinicians with image-based AI model explanations when provided AI model predictions to help clinicians better understand the logic of an AI model's prediction. It will evaluate whether providing clinicians with AI model explanations can improve diagnostic accuracy and help clinicians catch when models are making incorrect decisions. As a test case, the study will focus on the diagnosis of acute respiratory failure because determining the underlying causes of acute respiratory failure is critically important for guiding treatment decisions but can be clinically challenging. To determine if providing AI explanations can improve clinician diagnostic accuracy and alleviate the potential impact of showing clinicians a systematically biased AI model, a randomized clinical vignette survey study will be conducted. During the survey, study participants will be shown clinical vignettes of patients hospitalized with acute respiratory failure, including the patient's presenting symptoms, physical exam, laboratory results, and chest X-ray. Study participants will then be asked to assess the likelihood that heart failure, pneumonia and/or Chronic Obstructive Pulmonary Disease (COPD) is the underlying diagnosis. During specific vignettes in the survey, participants will also be shown standard or systematically biased AI models that provide an estimate the likelihood that heart failure, pneumonia and/or COPD is the underlying diagnosis. Clinicians will be randomized see AI predictions alone or AI predictions with explanations when shown AI models. This survey design will allow for testing
Interventions
- OTHER Artificial Intelligence model predictions without explanation
- OTHER Artificial intelligence model predictions with explanation
- OTHER AI model biased against heart failure
- OTHER AI model biased against pneumonia
- OTHER AI model biased against COPD
Trial Details
| Field | Value |
|---|---|
| Enrollment Target | 457 participants |
| Start Date | 2022-04-01 |
| Est. Completion | 2023-01-31 |
| Phase | NA |
Interested in This Trial?
Full Details on ClinicalTrials.gov ↗What the Registry Record Tells You About NCT06098950
The ClinicalTrials.gov registry entry for NCT06098950 describes a study currently listed as completed, categorized as NA. The registered enrollment target is 457 participants, a figure that helps gauge the scale of data the investigators plan to collect. The listed sponsor is University of Michigan, which has 1,327 total studies on file at ClinicalTrials.gov.
The record links to 0 conditions, and to 5 interventions - of which Artificial Intelligence model predictions without explanation is the first listed.
NCT06098950 reports 0 study locations.
Frequently Asked Questions
What is clinical trial NCT06098950 about?
NCT06098950 is a clinical study titled "Human Algorithm Interactions for Acute Respiratory Failure Diagnosis". Artificial intelligence (AI) shows promising in identifying abnormalities in clinical images. However, systematically biased AI models, where a model makes inaccurate predictions for entire subpopulations, can lead to errors and potential harms. When shown incorrect predictions from an AI model, cli...
What is the current status of trial NCT06098950?
This trial is currently completed. It is a NA study. The enrollment target is 457 participants. The study started on 2022-04-01. Estimated completion is 2023-01-31.
What interventions are being tested in trial NCT06098950?
The interventions under investigation include: Artificial Intelligence model predictions without explanation (OTHER), Artificial intelligence model predictions with explanation (OTHER), AI model biased against heart failure (OTHER), AI model biased against pneumonia (OTHER), AI model biased against COPD (OTHER).
Who is sponsoring clinical trial NCT06098950?
This trial is sponsored by University of Michigan, which has 1,327 total clinical trials registered on ClinicalTrials.gov.
Learn More About Clinical Trials
Explore more on PlainTrial
Read our methodology - how this data is sourced, computed, and verified.
Related
Every figure on PlainTrial is rendered directly from the ClinicalTrials.gov registry, no number is typed in by an editor. This page mirrors this trial's own ClinicalTrials.gov registry record, live from the dataset. See our editorial standards & corrections policy, the methodology behind these numbers, or report a data error.