A candidate, PhD, for the COH Digital Health tenure-Track Assistant Professor of Health is a postdoctoral research fellow at an AbilityLab and University, working with two mentors. They received their PhD degree in Mechanical Engineering in 2022 and received their BS degree in Instrumental Science in Beijing China. They worked on new product development for real world applications as senior electronics engineer at a company before theirs postdoc training. They specialize in wearable electronics, sensor systems, efficient computing and Artificial Intelligence (AI) using wearable data. Working closely with elderly individuals, clinicians, and patients with conditions such as stroke, spinal cord injury, Parkinson’s disease, and surgical pediatrics, they developed wearable electronics, sensor data processing pipelines, and AI algorithms for applications in gait analysis, motion recognition, clinical assessment automation, fall risk estimation, and postoperative recovery monitoring. One of their past research projects garnered coverages numerous media outlets, where they designed smart insoles and developed a toe-tapping game to capture foot tremors associated with Parkinson's disease, along with AI algorithms to assess falling risks. With the goal of monitoring and improving human health as well as supporting clinicians in decision-making, the vision for their independent research program is to develop smart wearable electronics and predictive AI that provides translational digital health and medicine solutions for the aging population and various patient populations.

Title: 'Tracking Postoperative Recovery in Children with Novel Wearable Biomarkers and Predictive AI'
 

Abstract: Postoperative complications pose significant risks to the well-being of children who undergo surgery. Complications are especially difficult to identify after discharge home, relying predominantly on subjective symptom reports from children and their caregivers to evaluate the need for additional care engagement, which can result in delayed diagnosis and additional treatments. With the development of wearable technologies that provide accurate health measurements on children, it could enable continuous postoperative recovery monitoring to identify complications early. However, there are still gaps in our knowledge about how to capture robust, clinically meaningful predictors of healthy postoperative recovery from these devices, especially given the wide range of physiological and behavioral variations between children. The candidate presents novel clinical-explainable wearable biomarkers based on biorhythms (e.g., circadian or ultradian rhythms quantified from daily, periodical patterns of physical activity and heart rate) and their relationship to postoperative recovery in children with and without complications who underwent appendectomy as the clinical use case, which is the most common cause of emergency abdominal surgery in children. Predictive AI algorithms using wearable data are developed to track postoperative recovery and forecast complications. The framework of novel wearable biomarkers and predictive AI can be adapted for other remote health monitoring in the community as the digital health solution, addressing clinical questions beyond children’s postoperative care, such as tracking neurodegenerative disease progression, automating and complementing clinical assessments and monitoring medication effectiveness.