Cerebral palsy is the most common physical disability in childhood, with a prevalence of 2.1 cases per 1000 in high-income countries. Professor Patterson, working in conjunction with colleagues in Orange County, has been award an NIH grant to develop a computerized hardware-software system capable of identifying preterm infants at high risk of developing cerebral palsy (CP) The technique is based on the systematic identification of specific patterns of movement-derived features. The Cerebral Palsy Risk Identification System (CPRIS) will enable clinical staff with only minimal training to cost effectively implement General Movement Assessment (GMA) for Cramped Synchronous General Movements (CSGMs), with interpretive reporting performed automatically. The CPRIS constitutes a key enabling technology for advancement in the identification, characterization and treatment assessment of CP.
Professor Patterson has worked with this idea in the past with 10 infant participants and received patents for the technique (patent, patent) This grant will enroll up to 200 babies to see if the effect works with larger population.
Machine learning technology is changing and advancing quickly so the Westmont student researchers who are participating on this project are going to be ready to hit the ground running after graduation.
In addition to the previous approaches that have been tried, this time the team is going to add depth camera imagery to the input. These are cameras that are based on the Microsoft Kinect or Apple FaceID that can scan for the distance of an object from the camera. The commercial version of this technology is used for games and face recognition, but the research team wants to use the same technology to scan the shape of the baby. This technique doesn’t require contact with the baby and provides information that is hard to get from a normal video camera. Using this depth information should improve the ability of the computer to recognize when the babies are moving abnormally.
To see the award information visit the NIH website: https://projectreporter.nih.gov/pr_Prj_info_desc_dtls.cfm?icde=0&aid=9621149&print=yes