Using Artificial Intelligence to Screen for Hip Dysplasia

Artificial Intelligence Augmented Ultrasound for Developmental Dysplasia of the Hip: a Validity Study

The goal of this clinical trial is to learn if an ultrasound scan using artificial intelligence can accurately screen for hip dysplasia. Researchers will compare the artificial intelligence ultrasound results to the standard ultrasound measures to see if the artificial intelligence ultrasound scan can accurately screen for hip dysplasia.

It will also seek to understand how parents feel about their children undergoing this scan.

Participants will:

• Have an additional ultrasound performed on their child at their scheduled outpatient's appointment for hip dysplasia
• Complete a short questionnaire about the experience of having the measurement performed on their child

Study Overview

• Status: Recruiting
• Conditions: Developmental Dysplasia of Hip
• Intervention / Treatment: Device: Artificial intelligence augmented ultrasound

Detailed Description

Initial screening for Developmental Dysplasia of the Hip (DDH) in Australia is performed most often by general practitioners and paediatricians shortly after birth and by maternal child health care nurses (MCHN) throughout the first year of life. These physical examinations consist of the Ortolani and Barlow tests and the examination of the thigh and gluteal creases. A recent meta-analysis reported the sensitivity of these tests as 36%, which indicates there is potential for a large proportion of cases to go undetected when solely relying on these examinations. Moreover, there currently are no formalised processes by which standards of practice are taught, assessed, or maintained. Thus, there is a clear need for a less operator-dependent screening protocol that can be performed within the current models of infant care. While some countries utilise universal ultrasound screening, this too is limited by access to care, as devices are not portable and thus cannot be used in current care models. Furthermore, it requires a specialist operator, substantially increasing cost. The screening program's limited nature, combined with the need for more consensus among international healthcare providers regarding the best method for managing DDH, has produced highly mixed clinical practices.

One part of the solution is optimising screening protocols for DDH in existing care models. Each state in Australia has established MCHN care protocols that provide access care for young children. While physical screening for DDH in these visits is standard practice, there remains considerable scope for improvement in the accuracy and reliability of these screening methods. Selective screening relies on several clinical associations with DDH to identify which patients receive ultrasound screening. Still, it has been shown to detect only 50% of infants with dysplasia. The MCHN screening program relies on clinical examination alone to detect dysplasia, an inferior identification method. Universal screening has a higher rate of detection of dysplasia but is expensive, single point in time (so misses the development of dysplasia) and results in higher levels of treatment.

A possible solution is portable artificial intelligence (AI)-augmented ultrasound. Recently technology has been developed to support a portable ultrasound device to screen DDH that uses AI-enabled technology to screen for DDH rapidly and accurately. Prior data has demonstrated that physicians and nurses could operate the device following training from expert sonographers. With its low-cost and ease of operation (with simple training) by healthcare providers such as MCHNs, it could significantly augment the physical screening. Thus, there is clear potential for an affordable, repeatable, and accessible screening methodology to be translated into clinical care. Initial Canadian data is promising. Pilot data suggests that DDH detection rates with this technology is on par with the detection rates of orthopaedic specialists. However, as this study was performed in a community setting and only those participants referred to orthopaedic clinics had a standard ultrasound measure performed, this pilot was unable to compare this screening technique with current gold standard diagnostic measures across the whole cohort, nor determine device sensitivity or predictive values. To demonstrate that this technology is fit for purpose, it is imperative that the rate of false negatives is also understood, as this is what will lead to late presentation, - which is what screening ultimately endeavours to prevent. Moreover, in an Australian context an important consideration in a wider roll-out is whether this technology would be accepted for uptake by clinicians and parents.

The proposed project will seek to gather pilot data to assess the validity and feasibility of this technology within a population of infants aged 4-20 weeks flagged at risk for DDH and referred to the Royal Children's Hospital. This will enable the recruitment of a sufficient number of cases of DDH to determine the sensitivity of the device. While the sensitivity and specificity of the device in this at-risk population may not be generalizable to the wider community the information gathered will then inform and refine a larger study of this technology in a community setting such as tertiary (birthing hospitals) and primary (MCHN clinics) care. If it can be demonstrated that it is feasible to implement this technology into existing care models, there is clear scope for this technology to revolutionize DDH screening. Thus, this project seeks to determine how well the device performs (sensitivity, specificity and predictive value) and the the clinical acceptability of this measure within the patient population.

• Study Type: Interventional
• Enrollment (Estimated): 240
• Phase: Not Applicable

Contacts and Locations

• Study Contact: Name: Melissa Formosa; Email: melissa.formosa@mcri.edu.au
• Study Contact Backup: Name: Natalie K Hyde, BBiomedSc (Hons), PhD; Phone Number: 61 3 9936 6246; Email: natalie.hyde@mcri.edu.au

Study Locations

• Australia
  • Victoria
    • Parkville, Victoria, Australia, 3052
      • Recruiting
      • Royal Children's Hospital
      • Contact: Natalie K Hyde, BBiomedSc, PhD; Phone Number: +61 3 9936 6246; Email: natalie.hyde@mcri.edu.au

Participation Criteria

Eligibility Criteria

• Ages Eligible for Study: Child
• Accepts Healthy Volunteers: Yes

Description

Inclusion Criteria:

• Enrolled in the VicHip study
• Is 4-20 weeks of age at enrolment
• Is attending The Royal Children's Hospital for the purpose of the potential diagnosis of DDH
• Has a diagnostic (standard) hip ultrasound on the day of their out-patient appointment
• Has a legally acceptable representative capable of understanding the informed consent document and providing consent on the participant's behalf.

Exclusion Criteria:

Participants will be excluded from enrolment if:

• They are currently receiving treatment for DDH

Study Plan

How is the study designed?

Design Details

• Primary Purpose: Screening
• Allocation: N/A
• Interventional Model: Single Group Assignment
• Masking: None (Open Label)

Number of Arms

1

Arms and Interventions

Participant Group / Arm

Intervention / Treatment

Other: All active participants; All participants will undergo an AI-augmented ultrasound and there will be no active comparator

Device: Artificial intelligence augmented ultrasound; The hip ultrasound is performed using a handheld device (Exo Iris) that uses a pocket-sized ultrasound probe and is run through an application on an IoS (Apple mobile) operation system. . A real-time algorithm detects and records the anatomical landmarks. When there are enough images for analysis the operator is notified that the scan is complete.

What is the study measuring?

Primary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Artificial Intelligence augmented ultrasound screening test capability: Sensitivity	Artificial intelligence (AI) augmented ultrasound results will be compared to standard ultrasound imaging to calculate sensitivity ([number of true positive cases detected/(number of true positive cases detected + number of false negative cases detected)] X 100). Groups will be defined as follows: True positive cases: Flagged for follow-up after the AI assessment of ultrasound sweeps from the portable probe and have a diagnosis of DDH from traditional ultrasound reports.; False positive cases: Flagged for follow-up after the AI assessment of the ultrasound sweeps and do not have a diagnosis of DDH from the traditional ultrasound reports; False negative cases: Return a "normal hips" assessment after the AI assessment of the ultrasound probe and have a diagnosis of DDH from traditional ultrasound reports; True negative cases: Return a "normal hips" assessment after the AI assessment of the ultrasound probe and do not have a diagnosis of DDH from traditional ultrasound reports	1 day, both ultrasound scans will be performed on the same day
Artificial Intelligence augmented ultrasound screening test capability: Specificity	Artificial intelligence (AI) augmented ultrasound results will be compared to standard ultrasound imaging to calculate specificity ([number of true negative cases detected/(number of false positive cases detected + number of true negatives cases detected] X 100). Groups will be defined as follows: True positive cases: Flagged for follow-up after the AI assessment of ultrasound sweeps from the portable probe and have a diagnosis of DDH from traditional ultrasound reports.; False positive cases: Flagged for follow-up after the AI assessment of the ultrasound sweeps and do not have a diagnosis of DDH from the traditional ultrasound reports; False negative cases: Return a "normal hips" assessment after the AI assessment of the ultrasound probe and have a diagnosis of DDH from traditional ultrasound reports; True negative cases: Return a "normal hips" assessment after the AI assessment of the ultrasound probe and do not have a diagnosis of DDH from traditional ultrasound reports	1 day, both ultrasound scans will be performed on the same day
Artificial Intelligence augmented ultrasound screening test capability: Positive predictive value (PPV)	Artificial intelligence (AI) augmented ultrasound will be compared to standard ultrasound to calculate PPV ([number of true positive cases detected/(number of true positive cases detected + number of false positive cases predicted) X 100). Groups will be defined as follows: True positive cases: Flagged for follow-up after the AI assessment of ultrasound sweeps from the portable probe and have a diagnosis of DDH from traditional ultrasound reports.; False positive cases: Flagged for follow-up after the AI assessment of the ultrasound sweeps and do not have a diagnosis of DDH from the traditional ultrasound reports; False negative cases: Return a "normal hips" assessment after the AI assessment of the ultrasound probe and have a diagnosis of DDH from traditional ultrasound reports; True negative cases: Return a "normal hips" assessment after the AI assessment of the ultrasound probe and do not have a diagnosis of DDH from traditional ultrasound reports	1 day, both ultrasound scans will be performed on the same day
Artificial Intelligence augmented ultrasound screening test capability: Negative predictive value (NPV)	Artificial intelligence (AI) augmented ultrasound will be compared to standard ultrasound to calculate NPV [number of true negative cases detected/(number of false negatives detected + number of true negative cases detected) X 100. Groups will be defined as follows: True positive cases: Flagged for follow-up after the AI assessment of ultrasound sweeps from the portable probe and have a diagnosis of DDH from traditional ultrasound reports.; False positive cases: Flagged for follow-up after the AI assessment of the ultrasound sweeps and do not have a diagnosis of DDH from the traditional ultrasound reports; False negative cases: Return a "normal hips" assessment after the AI assessment of the ultrasound probe and have a diagnosis of DDH from traditional ultrasound reports; True negative cases: Return a "normal hips" assessment after the AI assessment of the ultrasound probe and do not have a diagnosis of DDH from traditional ultrasound reports	1 day, both ultrasound scans will be performed on the same day

Secondary Outcome Measures

Outcome Measure	Measure Description	Time Frame
Device operator reliability in performing successful scans	Device operators' reliability will be recorded as percentage of scans performed that return a suboptimal result. This will be done by graphing number of scans performed by operators (operator experience) (x axis) against proportion of sub-optimal scans (y axis) to visually identify if a steady state is achieved.	12 months or entire study duration
Acquisition of successful scans	The total proportion of infants unable to be scanned with the Artificial Intelligence augmented ultrasound device and reasons why scans were unsuccessful will from the entire sample. A higher frequency of successful scan acquisition will indicate better device performance.	12 months or entire study duration
Time taken to acquire scan	Time to acquire the image will be calculated from the initiation of the scan to the time that the software indicates image acquisition is complete. The time to receive results will be calculated from the time of completion acquisition to the time the final recommendation is provided. A lower successful scan time will be indicative of higher feasibility.	1 day, calculated at time of scan
Caregiver perspectives on their infant undergoing the artificial intelligence augmented ultrasound	Caregivers will be asked to answer a purpose-built survey that has been piloted in Canadian studies (3 questions rated from 0-10, where 10 indicates a more positive experience) in addition to Australian-specific closed and open-ended questions.	1 day, caregivers will be asked to complete immediately following the scan
Operator perspectives on performing the artificial intelligence augmented ultrasound	Operators will be asked to complete the 10-item System Usability Questionnaire which measures the perceived ease of using technological devices. Scores are calculated on a 5-point Likert scale where 1=Strongly disagree and 5=Strongly agree. A single composite score out of 100 is calculated from all 10 items and indicates the overall useability of the device, where a higher score indicates better useability. In addition to this, two open-ended questions (Are there any further comments you would like to make about what you liked about the device?" and "are there any further comments you would like to make about what you didn't like about the device?") will be asked.	At the conclusion of their involvement in the study device (up to 12 months)
Factors associated with differences in device sensitivity	Sensitivity will be calculated between groups: Degree of dysplasia as defined by the Graf classification; Sex; Infant age (categorised as 4-7.99 weeks, 8-11.99 weeks, 12-15.99 weeks, 16-20 weeks); Number of scans performed by device operator (less than or greater than 60 scans).	1 day, all data will be collected from day of scan
Factors associated with differences in device specificity	Analyses will stratified to look at differences in specificity between groups: Degree of dysplasia as defined by the Graf classification; Sex; Infant age (categorised as 4-7.99 weeks, 8-11.99 weeks, 12-15.99 weeks, 16-20 weeks); Number of scans performed by device operator (less than or greater than 60 scans).	1 day, all data will be collected from day of scan
Factors associated with differences in device positive predictive value	Positive predictive value will be compared between groups: Degree of dysplasia as defined by the Graf classification; Sex; Infant age (categorised as 4-7.99 weeks, 8-11.99 weeks, 12-15.99 weeks, 16-20 weeks); Number of scans performed by device operator (less than or greater than 60 scans).	1 day, all data will be collected from day of scan
Factors associated with differences in device negative predictive value	Negative predictive value will be compared between groups: Degree of dysplasia as defined by the Graf classification; Sex; Infant age (categorised as 4-7.99 weeks, 8-11.99 weeks, 12-15.99 weeks, 16-20 weeks); Number of scans performed by device operator (less than or greater than 60 scans).	1 day, all data will be collected from day of scan

Collaborators and Investigators

• Sponsor: Murdoch Childrens Research Institute
• Investigators: Principal Investigator: Leo T Donnan, Murdoch Childrens Research Institute

Study record dates

Study Major Dates

• Study Start (Actual): December 6, 2024
• Primary Completion (Estimated): November 1, 2026
• Study Completion (Estimated): November 1, 2026

Study Registration Dates

• First Submitted: October 14, 2024
• First Submitted That Met QC Criteria: October 16, 2024
• First Posted (Actual): October 17, 2024

Study Record Updates

• Last Update Posted (Actual): April 8, 2026
• Last Update Submitted That Met QC Criteria: April 2, 2026
• Last Verified: April 1, 2026

More Information

Terms related to this study

• Keywords: ultrasound; infants; artificial intelligence; screening; hip dysplasia
• Additional Relevant MeSH Terms: Musculoskeletal Diseases; Wounds and Injuries; Joint Diseases; Hip Injuries; Joint Dislocations; Hip Dislocation
• Other Study ID Numbers: 107227

Plan for Individual participant data (IPD)

• Plan to Share Individual Participant Data (IPD)?: UNDECIDED
• IPD Plan Description: The researchers may choose to share data with other groups that are using the same device, all IPD would be deidentified and would be subject to further ethical approval. The researchers have sought consent from participants to allow data collected to be used for future research.

Drug and device information, study documents

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