Artificial Intelligence (AI) in Diagnosis, Preterm Birth
Conditions
Keywords
Preterm birth, Premature birth, Diagnostic calibration, Diagnostic accuracy, Diagnostic confidence, Artificial intelligence
Brief summary
The goal of this randomized questionnaire-based study is to evaluate how different presentations of artificial intelligence (AI) decision support influence clinical judgment among medical doctors working in obstetrics and gynecology when assessing the risk of spontaneous preterm birth using clinical case vignettes with cervical ultrasound images. The study specifically compares two AI presentation formats: a binary classification (preterm vs term birth) and an individualized risk estimate of preterm birth. The main questions it aims to answer are: * Which AI presentation format leads to better alignment between clinicians' confidence and decision accuracy (diagnostic calibration)? * Do different AI presentation formats lead to helpful or harmful changes in clinical decisions? Participants will complete an online questionnaire in which they review clinical cases, make diagnostic and management decisions, rate their diagnostic confidence before and after seeing the AI output, and report their trust in the AI.
Interventions
BEHAVIORALAI prediction (binary)
AI decision support based on cervical ultrasound providing a binary classification (preterm birth before 37 weeks or term birth) in addition to standard clinical information.
BEHAVIORALAI risk estimate (%)
AI decision support based on cervical ultrasound providing an estimate of preterm birth risk (%) in addition to standard clinical information.
Sponsors
Rigshospitalet, Denmark
Technical University of Denmark
The Foundation of 17.12.1981
Department of Computer Science, University of Copenhagen, Denmark
Copenhagen Academy for Medical Education and Simulation
Study design
Allocation
RANDOMIZED
Intervention model
PARALLEL
Primary purpose
OTHER
Masking
SINGLE (Subject)
Masking description
Participants (clinicians) are blinded to randomized allocation and are unaware that different versions of the AI decision support are being compared. They view only the AI output presented within their assigned condition. No independent outcome assessors are involved. Outcomes are derived using pre-specified, objective scoring rules.
Eligibility
Sex/Gender
ALL
Healthy volunteers
Yes
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.
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| Clinician diagnostic calibration (accuracy-confidence alignment) after AI exposure. | Immediately after AI exposure during a single questionnaire session (approximately 20 minutes). | Agreement between post-AI decision correctness (0/1) and post-AI confidence rating (0-10) will be quantified using the Brier score. Confidence will be rescaled to 0-1 and squared differences between confidence and correctness will be averaged across cases to produce a participant-level score. Lower scores indicate better diagnostic calibration. Results will be compared between randomized arms. |
Secondary
| Measure | Time frame | Description |
|---|---|---|
| Helpful switch rate and harmful switch rate. | Baseline (pre-AI) and immediately after AI exposure during a single questionnaire session (approximately 20 minutes). | Proportion of cases with helpful and harmful switches calculated for each participant and compared between study arms. Helpful switch = incorrect pre-AI decision changing to correct post-AI decision. Harmful switch = correct pre-AI decision changing to incorrect post-AI decision. |
| Change in decision accuracy, confidence, and diagnostic calibration from pre-AI to post-AI. | Baseline (pre-AI) and immediately after AI exposure during a single questionnaire session (approximately 20 minutes). | Within-participant change from pre-AI to post-AI in decision accuracy (proportion of correct decisions), confidence rating, and diagnostic calibration. Differences will be compared between randomized arms and stratified by AI correctness. |
| Association between self-rated trust in AI and behavioral reliance on AI. | Immediately after AI exposure during a single questionnaire session (approximately 20 minutes). | Self-rated trust in the AI output will be measured using a numeric rating scale (0-10) after AI exposure for each case. Behavioral reliance will be quantified as the proportion of post-AI decisions concordant with the AI output. The relationship between trust ratings and behavioral reliance, including concordance when the AI is correct and incorrect, will be evaluated at the participant level and compared between randomized arms. |
| Follow-up cervical ultrasound planning. | Baseline (pre-AI) and immediately after AI exposure during a single questionnaire session (approximately 20 minutes). | Proportion of cases in which clinicians plan an additional cervical ultrasound (yes/no), summarized per participant and compared pre-post AI and between randomized arms. |
Countries
Denmark
Contacts
CONTACTEmilie Pi F Sejer, MD
STUDY_CHAIRMartin G Tolsgaard, MD, PhD, DMSc
Department of Obstetrics and Gynecology, Copenhagen University Hospital - Rigshospitalet, Copenhagen, Denmark
Outcome results
None listed