Toluni Ghandi-Olaoye
Pronouns: she/her
Research Mentor(s): Winston Zhang
Research Mentor School/College/Department: DCMB / Medicine
Program: UROPF
Session: Session 7 (4:40pm – 5:30pm)
Authors: Winston Zhang, Toluni Ghandi-Olaoye, Mohid Durani
Abstract
My project works to use smart technology for Preventative Monitoring using Unobtrusive Sensor Data. I chose to be part of the Apple watch project. This is where we are trying to configure a watch to collect data from patients at the Michigan hospital. The purpose of this research is to investigate cardiac event prediction methodologies using consumer-grade wearable sensors. Machine learning models will be developed utilizing a previously collected retrospective database of wearable sensor data to predict the onset of severe instances of cardiac events such as hypertension, hypotension, and tachycardia. The study will use the database BigIdeasLab_STEP, made publicly available on Physionet, with ECG collected from Michigan Medicine cardiac patients with a BodyGuardian portable ECG monitor during Phase II of the Toyota project “Development and Assessment of an In-Vehicle Cardiac Monitoring and Severe Event Prediction Systemâ€. The database contains hourly records of de-identified heart rate data from multiple commercial smartwatch devices including the Apple Watch. Data was collected from 53 individuals recruited by Duke University over the course of July to August 2019. Patients with hypertension, hypotension, and abnormally high heart rates have been identified and their signals annotated by clinicians.
