HipScreen mobile app for the measurement of hip migration percentage in children with cerebral palsy: Accuracy, reliability, and discriminatory ability.
Vedant A Kulkarni, Nina Q Cung-Shahlaie, Anita M Bagley and 3 others
PMID 37143284WHAT IT FOUND
Trained users measured hip displacement risk in children with cerebral palsy with an average error of 5.72% versus an expert measurement, but the app correctly cleared only 66% of hips not above the 30% referral threshold.
Key findings
01Across all users, the app measured hip migration percentage with an average error of 5.72% compared with the reference standard.
02The app identified 94% of hips above the 30% referral threshold, but correctly cleared only 66% of hips not above it.
03Reliability was good at 0.83, and there was no significant difference between expert and novice users.
STILL TO COME
How it was doneWhat they foundWhat it means for PTs
Read the rest of this summary
You get three full summaries a month, free, and we do not ask for a card. Search, the TL;DRs and your library stay unlimited either way.
What it does not show
Only 37 users measured 40 hips from 20 radiographs, so the study cannot show how the app performs across many patients or settings. Users were recruited through professional networks and had to score at least 80% on a competency test after 30 minutes of tutorials, so untrained users may not achieve the same accuracy. All radiographs were obtained at a facility using hip surveillance positioning protocols, so poor positioning or image quality may change results. There were too few users without a health-care background to test whether the app is accurate for the general public.
Declared interests
No author conflicts of interest are stated in the supplied text. The HipScreen app is distributed free by Shriners Children's, and the article is listed as supported by NIH extramural and non-U.S. government research support.
The easy way to misread this
Do not conclude that anyone can use the app safely. Every user had to pass an 80% competency test after training, and too few non-health-care users were studied to support general public use.