Unstable exercise is widely used for early clinical evaluation of neonatal brain developmental disorders such as cerebral palsy, in order to provide ultra early intervention and rehabilitation for newborns at risk. However, clinical practice currently relies heavily on the subjective evaluation of pediatricians, lacking quantitative evaluation methods and requiring a large number of professional doctors and clinical personnel, which limits the possibility of large-scale general screening. Although cameras can be used for capturing and digitizing newborn movements, there are still some issues with privacy and ease of use. Exploring wearable physiological sensor networks for assessing neonatal restlessness has significant application value.
Recently, Yang Hongbo's team from Suzhou Institute of Biomedical Engineering Technology, Chinese Academy of Sciences, and Cheng Huanyu's team from Pennsylvania State University proposed a sparse sensor network composed of flexible wireless IMU sensors, which is used for the ultra early rapid automatic screening of newborn cerebral palsy, and can conduct accurate ultra early rapid screening of newborn infants within 20 weeks within 15 minutes.
Among them, the sparse sensor network with motor ability evaluation is composed of only 5 sensor nodes, and each sensor node adopts an island bridge structure and biocompatible material design, which has excellent mechanical performance and biocompatibility, ensuring the comfort and safety of newborns. Research has shown that the overall system can continuously and stably obtain information on newborn acceleration and angular velocity, provided that the newborn's skin is not damaged and there is no interference in movement. Excellent wearable mechanical electrical characteristics, with the potential to monitor human mechanical sound and physiological information such as respiratory rate, heart rate, pulse, etc. The team collaborated with the First Affiliated Hospital of Jilin University, Suzhou Children's Hospital, and Quwo County Traditional Chinese Medicine Hospital in Shanxi Province to complete conceptual and clinical validation of 23 newborns, confirming the reliability of this system. In addition, combined with small and easily deployable machine learning algorithms, the system can automatically and reliably identify newborns with high levels of brain development risk, with an accuracy rate of over 99%.
This achievement provides a new digital method and automation technology for the large-scale and rapid screening of brain developmental diseases in newborns, which is of great significance for the ultra early intervention and rehabilitation of newborns with cerebral palsy. The relevant research results are titled "Intelligence Sparse Sensor Network for Automatic Early Evaluation of General Movements in Infants" and published in Advanced Science. The research work has been supported by the International Partnership Program of the Chinese Academy of Sciences, the National Key Research and Development Program, the National Natural Science Foundation of China and the Key Research and Development Program of Jiangsu Province.
Paper link
Design and Application Diagram of Intelligent Sparse Sensor Network System
