- September 2, 2021 from 12:00-1:00pm
- Please RSVP by emailing Lisa Maturo at Lisa.M.Maturo@christianacare.org.
- Please include your full name, email address, and institution/organization.
- We will provide instructions on obtaining CME credit for attendance.
Suicide is the 10th leading cause of death in the U.S. and that is prior to the impact of the COVID-19 pandemic. Improving the identification of patients at risk is a critical step for referral for intervention and management of these patients. The wealth of information in electronic health record (EHR) can be tapped for this task using a variety of data science approaches. In this presentation we describe an AI approach using deep learning that leverages information in EHR clinical text for the phenotyping of intentional self-harm and prediction of future suicidal behavior. We will also describe an ongoing cross-institutional project, as well as future directions that may help healthcare providers better identify patients at risk in an effort for to improve suicide prevention.
Meet the Speaker
Dr. Obeid is a Professor in the Department of Public Health Sciences at MUSC and co-director of the Biomedical Informatics Center which supports the translational research infrastructure at MUSC. He oversees several academic and operational informatics initiatives and leads multiple CTSA-related Informatics projects, such as the electronic health records (EHR) Research Data Warehouse, i2b2, REDCap, and several others. He serves as PI, co-investigator, or informatics leader on several federally funded projects. His research focuses on the use of AI/ML applications on EHR data for phenotyping purposes and for the prediction of patient outcomes.
This activity has been approved for AMA PRA Category 1 Credit