Online Program Home
  My Program

All Times EDT

Abstract Details

Activity Number: 524 - Emerging Statistical Learning Methods in Modern Data Science
Type: Invited
Date/Time: Thursday, August 6, 2020 : 1:00 PM to 2:50 PM
Sponsor: Section on Statistical Learning and Data Science
Abstract #309205
Title: A Powerful AI Tool for CHD Screening
Author(s): Wenxuan Zhong*
Companies: Department of Statistics, University of Georgia
Keywords: AI; Coronary Heart Disease; Computation Resource; efficient statistical method

Coronary heart disease (CHD) is a global epidemic that leads to 17.92 million (~1/3) of deaths worldwide in 2016. It is reported by the American College of Cardiology that ischemic heart disease, a late stage of CHD, kills 8.92 million people in 2015 and is ranked No. 1 killer among all diseases. The growing mortality rate of CHD not only causes a significant loss on human resources but also causes many social problems. There is an urgent need for preventive methods to reduce the social burden caused by CHD. However, there is no effective CHD screening methods to date due to the high operational cost, the requirement of expensive and high-maintenance equipment, the need of well trained medical staff and, most importantly, the potential surgical risk and radiology side effect on subjects. With the fast development of AI technology, many traditional medical practices are substantially simplified with AI assistance. Unfortunately, most existing AI methods, such as CNN, require extensive computation resources and huge training data as input, which limit the clinical applications of many AI algorithm. In this talk, I will introduce a computational efficient statistical leverage method

Authors who are presenting talks have a * after their name.

Back to the full JSM 2020 program