How different AI displays change clinicians' confidence when predicting preterm birth
Does AI Make Clinicians More Appropriately Confident? A Randomized Study in Preterm Birth Prediction
This project tests whether showing AI as a yes/no prediction or as a percentage risk changes how obstetricians and trainees judge and manage the chance of spontaneous preterm birth.
Quick facts
| Phase | Not applicable |
|---|---|
| Study type | Interventional |
| Enrollment | 125 (estimated) |
| Sex | All |
| Sponsor | Rigshospitalet, Denmark Academic / other |
| Locations | 7 sites (Copenhagen and 6 other locations) |
| Trial ID | NCT07402668 on ClinicalTrials.gov |
What this trial studies
In a randomized, questionnaire-based design obstetricians and trainees review clinical case vignettes that include cervical ultrasound images and make diagnostic and management decisions. Participants rate their confidence before and after seeing one of two AI outputs: a binary classification (preterm vs term) or an individualized percentage risk estimate. The study compares how each AI format affects diagnostic calibration (alignment of confidence with accuracy) and whether AI leads to helpful or harmful changes in clinical decisions. Data are collected online and analyzed to identify differences in decision changes and confidence calibration between the two presentation formats.
Who should consider this trial
Good fit: Ideal participants are medical doctors working in or training in obstetrics and gynecology who have experience performing transvaginal cervical ultrasound examinations.
Not a fit: Clinicians without transvaginal cervical ultrasound experience, non-physician staff, and pregnant patients themselves would not directly benefit from participation in this project.
Why it matters
Potential benefit: If successful, the findings could guide how AI outputs are shown so clinicians make better-calibrated decisions and avoid unnecessary interventions or missed risks.
How similar studies have performed: Prior research on AI decision support has shown mixed results—some work improves accuracy and calibration while other studies report overreliance or automation bias—so this question is partially tested but still active.
Eligibility criteria
Show full inclusion / exclusion criteria
Inclusion Criteria: * Medical doctors currently working in or training within the field of obstetrics and gynecology. * Experience performing transvaginal cervical ultrasound examinations. Exclusion Criteria: \- No prior experience performing transvaginal cervical ultrasound examinations.
Where this trial is running
Copenhagen and 6 other locations
- Copenhagen University Hospital, Rigshospitalet — Copenhagen, Denmark (Not_yet_recruiting)
- Herlev Hospital — Herlev, Denmark (Recruiting)
- Copenhagen University Hospital, North Zealand — Hillerød, Denmark (Recruiting)
- Holbæk Hospital — Holbæk, Denmark (Not_yet_recruiting)
- Hvidovre Hospital — Hvidovre, Denmark (Not_yet_recruiting)
- Zealand University Hospital, Roskilde — Roskilde, Denmark (Recruiting)
- Slagelse Hospital — Slagelse, Denmark (Not_yet_recruiting)
Study contacts
- Study coordinator: Emilie Pi F Sejer, MD
- Email: emilie.pi.fogtmann.sejer.01@regionh.dk
- Phone: 0045 28890690
How to participate
- Review the eligibility criteria above with your treating physician.
- Visit the official trial page on ClinicalTrials.gov for the most current contact information and recruitment status.
- Contact the listed study coordinator or principal investigator to request pre-screening. Pre-screening is free and never obligates you to enroll.