Speaker: Dr. William Cheung

Time: 1:00-2:00 p.m., 3 Dec 2020 (Thu)

Online platform: Zoom（ID: 630 6232 9665）

Language: English

Abstract:

The data analytics and artificial intelligence approaches, due to the wide adoption of electronic health records (EHR), have recently been heavily explored to transform the healthcare sector so that healthcare providers can be assisted to make better decisions and to deliver care of higher quality. EHR data is complex and contains a large variety of structured and unstructured information, including diagnoses, medications, laboratory tests, progress notes, vital signs, radiology images, etc. Uncovering their interactions embedded in EHR data to achieve highly accurate predictive analytics is challenging. In this talk, I will present some of challenges and our recent works where novel tensor factorization and representation learning methods were developed for computational phenotyping and learning dynamic patient representations based on structured EHR data and medical ontologies

About the speaker:

William K. Cheung is an Associate Professor and Head of the Computer Science Department, Hong Kong Baptist University. He received the BSc and MPhil degrees in electronic engineering from the Chinese University of Hong Kong and PhD degree in computer science from the Hong Kong University of Science and Technology.  He has served as programme committee members and co-chairs of a number of international conferences/workshops for areas including web intelligence, e-commerce, data mining, intelligent systems, etc. He is currently the Managing Editor of the IEEE Intelligent Informatics Bulletin.