Department of Computer Science Seminar: Conducted by Dr. Trung Le
Biomedical Engineering Department
International University – HCMC National University, Vietnam
This Thursday (12th January 2017) we are delighted to have Dr. Trung Le visit the Department of Computer Science to give a seminar on Nonlinear Dynamics Forecasting of Obstructive Sleep Apnea Onsets using Point-of-care Biosensor System.
More on the topic:
Recent advances in sensor technologies and predictive analytics are fueling the growth in point-of-care (POC) therapies for obstructive sleep apnea (OSA) and other sleep disorders. The effectiveness of POC therapies can be enhanced by providing personalized and real-time prediction of OSA episode onsets. Previous attempts at OSA prediction are limited to capturing the nonlinear, nonstationary dynamics of the underlying physiological processes. We report an investigation using wireless, multi-sensor, wearable device to estimate and benchmark the cardiorespiratory dynamics aiming to predict in real time the onsets of OSA episode before the clinical symptoms appear. A prognosis method based on a nonparametric statistical Dirichlet-Process Mixture-Gaussian-Process (DPMG) model to estimate the transition from normal states to an anomalous (apnea) state is utilized to estimate the remaining time until the onset of an impending OSA episode.
The approach was tested using three datasets including:
- 20 records from 14 OSA subjects in benchmark ECG apnea databases (Physionet.org);
- Records of 10 OSA patients from the University of Dublin OSA database;
- Records of eight subjects from previous work.
On-going research focuses on the clinical testing of the technology in a larger OSA patient’s population with the benchmarks from the Polysomnography system.
Biography of Dr. Trung Le:
Dr. Trung Le is a Lecturer of Biomedical Engineering Department at the International University – HCMC National University, Vietnam. He received his PhD degree from Oklahoma State University, USA and was a Postdoctoral research associate of Industrial Systems Engineering and a Research scientist of Biomedical Engineering at Texas A&M University, USA. He collaborates closely with cardiologists, sleep physician, health scientists and bio-medical researchers to perform his research in three complementary directions including: (1) point of care wearable sensor technology for the monitoring and prognostics of cardiorespiratory and sleep disorders; (2) high-specificity diagnostic methods for identifying and localizing cardiovascular disorders to mine unstructured content from the vital signs in healthcare to convert it into clinically significant information interpretable by physicians and doctors, and (3) analytics approaches to forecast the time to the impending risks or disorders before they actually happen for warning control applications and/or preventive medicines. His work was published in IEEE Transaction of Biomedical Engineering, Medical Engineering and Physics, IEEE Journal of Translational Engineering in Health and Medicine, and PLOSOne. His works have led to several US and International patents.