Clinicians' Trust in AI-Based Fetal Growth Estimates

NCT07401368 | Not Yet Recruiting

• 1 other identifier: F-25022462
• Study Type: interventional
• Target: 308
• Locations: 1 country
• Sites: 1

Brief Summary

This study examines how clinicians trust and use artificial intelligence (AI) when estimating fetal weight during pregnancy. Accurate assessment of fetal growth is important for identifying growth problems that may affect pregnancy management. New AI-based tools can estimate fetal weight from ultrasound images, but little is known about how clinicians trust these estimates or how uncertainty information influences their decisions. In this study, clinicians will review anonymized ultrasound cases and compare fetal weight estimates generated by an AI model with traditional estimates. Some clinicians will also be shown information about the AI model's performance and uncertainty, while others will not. Participants will be asked to choose which estimate they find most reliable, indicate their level of confidence, and decide whether they would recommend follow-up scans. The study aims to better understand how AI and uncertainty information affect clinical decision-making and trust among clinicians with different levels of experience.

Conditions

Obstetric Ultrasonography; Fetal Growth; Pregnancy; Clinical Decision-making

Keywords

Clinical decision-making; Artificial intelligence; Fetal weight estimation; Obstetric ultrasound; Trust; Human-AI interaction; Questionnaire study

Outcome Measures

Primary Outcomes (1)

• Clinicians' choice of fetal weight estimation method

  The proportion of cases in which clinicians choose the AI-based fetal weight estimate rather than the traditional Hadlock estimate when assessing anonymized ultrasound cases.

  Immediately after questionnaire completion

Secondary Outcomes (3)

• Clinicians' confidence in selected fetal weight estimate

  Immediately after questionnaire completion

• Recommendation of follow-up growth scan

  Immediately after questionnaire completion

• Impact of uncertainty information on model preference

  Immediately after questionnaire completion

Study Arms (2)

Control - No AI Performance Information

NO INTERVENTION

Participants complete the questionnaire without receiving information about the AI model's overall performance.

ntervention - AI Performance Information

OTHER

Participants receive brief information about the AI model's overall performance before completing the questionnaire.

Other: Intervention - AI Performance Information

Interventions

Intervention - AI Performance Information OTHER

Participants receive brief information about the AI model's overall performance before completing the questionnaire.

ntervention - AI Performance Information

Eligibility Criteria

• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Child (0-17), Adult (18-64), Older Adult (65+)

You may qualify if:

• Clinicians working in obstetrics and gynecology departments.
• Regular use of obstetric ultrasound in clinical practice.
• Willingness to participate in a questionnaire-based study.

You may not qualify if:

• Clinicians who do not perform obstetric ultrasound examinations.
• Clinicians with a known conflict of interest related to the AI system being evaluated.

Sponsors & Collaborators

• Rigshospitalet, Denmark: lead
• Slagelse Hospital: collaborator
• Copenhagen Academy for Medical Education and Simulation: collaborator

Study Sites (1)

Department of Obstetrics and Gynecology, Slagelse Hospital

Slagelse, 4200, Denmark

Location

Central Study Contacts

Zahra Bashir, MD

CONTACT

004574871407; zab@regsj.dk

Study Design

• Study Type: interventional
• Phase: not applicable
• Allocation: RANDOMIZED
• Masking: SINGLE
• Who Masked: PARTICIPANT
• Masking Details: Participants are unaware of their allocation to the control or intervention group and are not informed that different versions of the questionnaire exist.
• Purpose: HEALTH SERVICES RESEARCH
• Intervention Model: PARALLEL
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Dr.

Model Details: Participants are randomized to either an intervention group receiving information about AI model performance or a control group without such information. Groups are assessed in parallel.

Study Record Dates

• First Submitted: January 23, 2026
• First Posted: February 10, 2026
• Study Start: June 1, 2026
• Primary Completion (Estimated): December 1, 2027
• Study Completion (Estimated): December 1, 2028
• Last Updated: February 10, 2026

Record last verified: 2026-02

Data Sharing

• IPD Sharing: Will not share

Locations

DK (1)