Diagnostic Efficacy Study of AI System in Screening Infants With Developmental Dysplasia of the Hip (ASIDDH)

Blinded Randomized Control Trail of Artificial Intelligence-Assisted Ultrasound Screening for Neonatal Hip Dysplasia in a Clinical Cohort

To ascertain the efficacy of the DeepDDH system, a deep learning framework, in enhancing diagnostic accuracy and curtailing follow-up intervals for infants undergoing screening for developmental dysplasia of the hip (DDH), the researchers are executing a blinded, randomized controlled trial. This trial juxtaposes AI-only and AI-assisted assessments of DDH against sonographer interpretations across various proficiency levels in the preliminary analysis of ultrasound images.

Study Overview

• Status: Completed
• Conditions: Hip Dysplasia, Developmental
• Intervention / Treatment: Other: Junior sonographer measurement of DDH; Other: Automated annotation of the DDH measurement through deep learning; Other: Senior sonographer measurement of DDH; Other: AI-assisted junior sonographer measurement of DDH

Detailed Description

1. Participating centers and doctors:

   The data in the ultrasound screening sequence database in this part of the study were mainly from Renji Hospital and the Sixth People's Hospital in Shanghai between August 2014 and December 2021. Renji Hospital, the Sixth People's Hospital, and the Pediatric Hospital Affiliated to Fudan University, three top-three hospitals in Shanghai, started Graf ultrasound examination earlier, with an average history of more than 10 years. And they are responsible for providing expert sonographers with more than 5-10 years of DDH ultrasound diagnosis experience, and pediatric orthopedic experts with 5-10 years of DDH diagnosis experience to participate in the study. However, several other primary or remote medical institutions with late DDH ultrasound screening and insufficient diagnostic experience were mainly responsible for providing primary sonographers to participate in the study. Before the study, the sonographers involved in this study will be evaluated uniformly and quantitatively through examination papers.

2. Research process:

One week before the start of the study, the sonographers registered in the study received uniform training of the latest DDH ultrasound diagnosis in the form of PPT, video, literature study, and offline instruction.

For the included cases in the ultrasound screening sequence database, they would appear in different control groups in a random form, such as the AI model, the Expert sonographer group, the primary sonographer group, and the primary sonographer with AI 'aid group. All cases in the ultrasound screening sequence database were stratified and block-randomized into the above four groups (primary, experts, AI-independent, AI-assisted primary).

In the AI-assisted group, each sonographer was asked to choose whether to modify or confirm the diagnosis according to the measurement marks, diagnostic angles and typing results provided by the AI device. However, in the Expert sonographer group and junior sonographer unassisted group, the dedicated research assistant will turn off the AI display function to ensure that no additional information is provided to the sonographer. The consensus of two pediatric orthopedic expert with 5-10 years of experience in DDH ultrasound diagnosis was used as the gold standard. In case of disagreement, a third pediatric expert will evaluate the diagnosis results of DDH. The final consensus was used as the gold standard.

Then, the pediatric orthopedic expert group were given the initial annotations diagnosis results of DDH in the above four groups, including diagnostic images, diagnostic measurement marks, diagnostic angles and diagnostic types. And by reviewing the initial annotations, selecting "confirm" or "modify" the initial annotations, the final annotations are made again for those who need to be modified, and the final report results are obtained.

Finally, the operation results of the above different groups were summarized and analyzed by independent research assistants, including α Angle, β Angle, typing results, and the specific follow-up experience of the case including follow-up times, diagnosis time, Bang's index, proportion of studies the annotation is changed, proportion of studies the DDH type is changed in final report, and mean change in alpha angle between preliminary and final report.

• Study Type: Interventional
• Enrollment (Actual): 1789
• Phase: Not Applicable

Contacts and Locations

Study Locations

• China
  • Shanghai Municipality
    • Shanghai, Shanghai Municipality, China, 200127
      • Ren Ji Hospital, Shanghai Jiao Tong University School of Medicine

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Child
• Accepts Healthy Volunteers: No

Description

Inclusion Criteria:

• Infants underwent DDH ultrasound examinations.
• Infants aged 28 days to 6 months.

Exclusion Criteria:

• Infants with lacking or incomplete ultrasound images.
• Infants with poor image quality, including non-compliance with anatomical identification and usability check.
• Infants with hip dysplasia caused by other diseases.

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Diagnostic
• Allocation: Randomized
• Interventional Model: Parallel Assignment
• Masking: Double

Number of Arms

4

Arms and Interventions

Participant Group / Arm	Intervention / Treatment
Active Comparator: Junior Sonographer Annotation; Participants will not receive visual cues from the DeepDDH system. Junior sonographer technicians will offer preliminary interpretations before these are subjected to validation and subsequent review by expert's team.	Other: Junior sonographer measurement of DDH; Participants will not receive visual cues from the DeepDDH system. Junior sonographer technicians will offer preliminary interpretations before these are subjected to validation and subsequent review by expert's team.
Experimental: DeepDDH system Annotation; Through randomization, a subset of the preliminary interpretations will be conducted by AI technology, and the study team will evaluate the degree of divergence between these AI-generated preliminary interpretations and the final interpretations.	Other: Automated annotation of the DDH measurement through deep learning; Through randomization, a subset of the preliminary interpretations will be conducted by AI technology, and the study team will evaluate the degree of divergence between these AI-generated preliminary interpretations and the final interpretations.
Experimental: DeepDDH-assist Junior Sonographer Annotation; Participants will receive visual cues from the DeepDDH system.	Other: AI-assisted junior sonographer measurement of DDH; Participants will receive visual cues from the DeepDDH system.
Active Comparator: Senior Sonographer Annotation; Participants will not receive visual cues from the DeepDDH system. Senior sonographer technicians will offer preliminary interpretations before these are subjected to validation and subsequent review by expert's team.	Other: Senior sonographer measurement of DDH; Participants will not receive visual cues from the DeepDDH system. Senior sonographer technicians will offer preliminary interpretations before these are subjected to validation and subsequent review by expert's team.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Average diagnostic accuracy	It is calculated by dividing the number of preliminary interpretations that are consistent with the expert team's grading by the total number of cases that should be diagnosed.	up to 4 weeks

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Average diagnostic sensitivity	It is calculated by dividing the number of true positive cases by the sum of true positive cases and false negative cases.	up to 4 weeks
Average diagnostic specificity	It is calculated by dividing the number of true negative cases by the sum of true negative cases and false positive cases.	up to 4 weeks
Average times of follow-up visits	The average number of follow-up visits for each group is obtained by dividing the total number of follow-up visits for each participating infant within the group by the number of participating infants in that group.	up to 4 weeks
Diagnosis time	Time taken to make ultrasound diagnosis in each group	up to 4 weeks
Bang's index	Bang's index is used to evaluate whether the blind method is implemented successfully	up to 4 weeks
Frequency pediatrician adjusts preliminary annotation	Proportion of studies the annotation is changed	up to 4 weeks
Frequency pediatrician adjusts preliminary DDH type	Proportion of studies the DDH type is changed in final report	up to 4 weeks
Mean change in alpha angle between preliminary and final report	Average change in alpha angle between preliminary and final report	up to 4 weeks

Collaborators and Investigators

• Sponsor: RenJi Hospital

Study record dates

Study Major Dates

• Study Start (Actual): July 18, 2025
• Primary Completion (Actual): August 1, 2025
• Study Completion (Actual): August 20, 2025

Study Registration Dates

• First Submitted: January 20, 2025
• First Submitted That Met QC Criteria: January 26, 2025
• First Posted (Actual): January 31, 2025

Study Record Updates

• Last Update Posted (Estimated): August 28, 2025
• Last Update Submitted That Met QC Criteria: August 22, 2025
• Last Verified: August 1, 2025

More Information

Terms related to this study

• Additional Relevant MeSH Terms: Musculoskeletal Diseases; Joint Diseases; Musculoskeletal Abnormalities; Congenital Abnormalities; Joint Dislocations; Hip Dislocation; Congenital, Hereditary, and Neonatal Diseases and Abnormalities; Developmental Dysplasia of the Hip
• Other Study ID Numbers: LY2025-004-C

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: YES
• IPD Plan Description: The clinical demographic information of the subjects was recorded through the Case Record Form, and the data will be collected and managed electronically through the ResMan platform.
• IPD Sharing Supporting Information Type: STUDY_PROTOCOL; SAP; ANALYTIC_CODE; CSR

Drug and device information, study documents

• Studies a U.S. FDA-regulated drug product: No
• Studies a U.S. FDA-regulated device product: No
• product manufactured in and exported from the U.S.: No