A large review of studies looked at how artificial intelligence (AI) can help read hip ultrasounds in babies. The goal was to see if AI could accurately identify developmental dysplasia of the hip (DDH), a condition where a baby's hip joint doesn't form properly. The review included over 6,000 hip ultrasounds from nine different studies.
The main finding was that AI-assisted ultrasounds were very good at finding true cases of DDH. About 92 out of 100 babies with the condition were correctly identified. The AI was also very good at ruling out the condition in healthy babies, correctly identifying about 96 out of 100. These results suggest AI can help make hip screening more consistent.
The review also noted that using AI might make ultrasounds faster and easier for non-expert operators to learn. However, the studies had some weaknesses, and more research is needed to confirm these findings in real-world settings. The authors caution that AI should not be seen as a replacement for specialist doctors without more testing.
In summary, AI-assisted ultrasound shows promise for helping detect hip problems in infants, but further validation is required before widespread use.