DOCUMENT

14 Headlines EARLY DETECTION MATTERS AI app to identify cerebral palsy in infants Machine learning and AI are playing a crucial role in medical research and diagnostics, and the field of neurology is no exception. D r Hamid Abbasi is leading a project at the University of Auckland Bioengineering Institute using AI to detect possible development of neurological disorders, including cerebral palsy, in early infancy. Following their recent success in developing robust algorithms for tracking infants’ general movements, his team is focused on developing an app for handheld devices that can pick up cerebral palsy in infants aged two-to-five months. By analysing video footage, the app will detect subtle movements in the hand, arm, leg, and neck which are proven to be the indicators for infants that are at risk of developing neurological disorders. A successful algorithm is already in place, based on the video archives of a significant number of babies that have been clinically screened at Te Whatu Ora Health New Zealand Waikato (Waikato Hospital). The goal is for the app to be made publicly available to parents and caregivers across the nation and globally, enabling them to use it remotely at home or in rural areas with limited access to specialists, making diagnosis much quicker and easier. Long term, researchers hope for a universal early infant movement screening programme based on the technology. “Early detection is vital, as the brain’s plasticity in the early months means interventions are much more effective,” Dr Abbasi explains. “It could be the difference between spending your life in a wheelchair or being able to take care of yourself independently.” Cerebral palsy, along with many other neurological disorders, is often caused by oxygen deprivation during birth. Efforts are still underway to establish diagnosis guidelines for the early initiation of treatment in at-risk newborns shortly after birth. This type of brain damage can develop and lead to significant life-long disorders, which may only be identified months or years later if left untreated. Currently, if cerebral palsy is suspected in an older baby, they are taken to a clinic or hospital for screening by a specialist. Dr Abbasi says this process can be difficult and time-consuming for parents, and subject to human limitations. “Our eyes cannot focus on the arm, leg and eyes at the same time, but a machine can learn the connectivity in the limbs’ movements,” Dr Abbasi says, adding, “In a new environment like a hospital setting, baby may be stressed or over- stimulated, which can affect baby’s natural state of mind and their normal movements. “Powerful supercomputers and machine learning platforms like those that we are developing can significantly reduce the time and resources needed to build advanced diagnosis tools, which can track and analyse inter-connected movements between 24 anatomical landmarks including the