The goal of this trial is to pilot a portable ultrasound device that uses artificial intelligence to screen for hip dysplasia. Researchers will gather data to understand the feasibility of performing a larger trial in birthing hospitals. It will also seek to collect initial data on how well the scan compares to the standard hip screening performed soon after birth.
Participants will:
* Have the portable ultrasound performed on their baby before they are discharged from hospital * Have a diagnostic ultrasound performed on their baby at 6-weeks of age * Complete a short questionnaire about the experience of having the measurement performed on their baby
Enrolled in the Victorian Hip Dysplasia Registry (VicHip) study
Infant born at term (≥37 weeks gestation)
Infant and caregiver admitted to the post-natal ward
Caregivers indicate they are willing to attend a 6-week ultrasound
Any known congenital anomalies in the infant precluding examination of the hips
Any known congenital neuromuscular conditions in the infant
Single group
Artificial intelligence augmented ultrasound
DeviceThe hip ultrasound is performed using a handheld device (Exo Iris) that is 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.
Feasibility of the AI-ultrasound method as determined by a study-specific questionnaire administered to care givers at Day 1
Caregiver perspectives will be captured via a study-specific questionnaire administered at Day 1 and this will enable determination of the feasibility of the AI-ultrasound method.
Number of infants unable to be scanned with the AI ultrasound
The proportion of infants unable to be successfully scanned with the AI-ultrasound will be calculated.
Reasons for failure to obtain AI ultrasound scan as determined by the performing research assistant
The reasons why infants were unable to be scanned as determined by the research assistant performing the AI scan will be documented as follows: Unsettled baby, technical failure, body habitus or other.
Proportion of infants lost to follow-up between the AI-ultrasound and 6-week (corrected) diagnostic scan
The proportion of infants that had an initial AI scan at Day 1 but did not return for a scan at Week 6 will be calculated.
Specificity of AI-ultrasound device as determined by comparison of the geometric measures (femoral head coverage and alpha angle) and expert reviews between the Day 1 and Week 6 scans
AI-ultrasound results will be compared to 6-week diagnostic 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). Hips will be classified according to the AI-recommendations, "unremarkable" i.e. no follow-up required or "follow-up recommended" to define negative and positive cases; those that receive an "unremarkable" classification will be defined as negative cases, and those that receive a "follow-up recommended" scan will be considered as positive cases for the reliability calculations. Diagnosis will be defined from the 6-week ultrasound scan and will be defined by both expert conclusion and geometric measures (femoral head coverage and alpha angle). Calculations will be performed at both the hip and individual level.
Sensitivity of AI-ultrasound measure determined by comparison of the geometric measures (femoral head coverage and alpha angle) and expert reviews between the Day 1 and Week 6 scans
AI-ultrasound results will be compared to 6-week diagnostic 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). Hips will be classified according to the AI-recommendations, "unremarkable" i.e. no follow-up required or "follow-up recommended" to define negative and positive cases; those that receive an "unremarkable" classification will be defined as negative cases, and those that receive a "follow-up recommended" scan will be considered as positive cases for the reliability calculations. Diagnosis will be defined from the 6-week ultrasound scan and will be defined by both expert conclusion and geometric measures (femoral head coverage and alpha angle). Calculations will be performed at both the hip and individual level.
The correlation between the alpha angle degree as reported by the AI-ultrasound analysis and expert analysis of the 6-week diagnostic ultrasound scan
Dependent on the distribution of the data Pearsons or Spearman's Rho correlation coefficients will be reported.
The correlation between the percentage femoral head coverage as reported by the AI-ultrasound analysis and expert analysis of the 6-week diagnostic ultrasound scan
Dependent on the distribution of the data Pearsons or Spearman's Rho correlation coefficients will be reported.
Difference in specificity of standard neonatal screening and the AI-ultrasound scan to discriminate for DDH
The specificity of standard neonatal screening and the AI-ultrasound screening will be compared.
Difference in specificity of Retuve and the AI-ultrasound scan to discriminate for DDH
The specificity of an alternate AI-analysis platform will be compared to the AI-ultrasound scan results.
Click on the lead sponsor to view all of their trials.
Murdoch Childrens Research Institute
Lead sponsor
Monash Health
Collaborator
University of Alberta
Collaborator
This trial is not recruiting at the moment. You can still explore other options:
