The Mount Sinai team trained a deep learning pose-recognition algorithm on video feeds of infants in the NICU to track movements and identify neurologic metrics.
Findings from this AI tool could enable continuous neurologic monitoring in NICUs, providing critical real-time insights into infant health previously unattainable.
Neurologic deterioration in NICUs can occur unexpectedly with devastating consequences, and current intermittent evaluations can miss subacute changes.
Pose AI has been trained on over 16,938,000 seconds of infant video footage, demonstrating the ability to predict sedation and cerebral dysfunction accurately.
Collection
[
|
...
]