International Seminar Series on Decision Support for Health Systems after COVID-19: Data, Models and Methods
An online seminar series on decision support for health systems after COVID-19 which is designed to provide an open, transparent platform for sharing models, methodologies and data to enable participants to discuss and learn from one another and spark new ideas.
You are invited to join our seminar with guest presenters from MIT on:
Personalized Predictions and Prescriptions for COVID-19 Patients: A Machine Learning Approach
Zoom Meeting, Wednesday 14th October 2020, 13:30 – 15:00 (GMT+1)
Watch a one minute video highlighting what the presentation will cover, or read the abstract of this research further below.
This seminar is free to join, but you need to register in advance. Register for this seminar here. After registering, you will receive a confirmation email containing information about joining the webinar.
Note: Please feel free to join and leave the session as it suits you.
13:30 – 14:00 Personalized Predictions and Prescriptions for COVID-19 Patients: A Machine Learning Approach
Agni Orfanoudaki and Holly Wiberg, MIT Operations Research Center
14:00 – 15:00 Deep Dive Discussion Session
A lively Q&A session where participants will actively engage to discuss the methodology, implementation, assumptions, benefits and challenges of the approach
The COVID-19 pandemic has created unprecedented challenges worldwide. Healthcare providers make difficult decisions on patient triage, treatment and care management on a daily basis. We design analytical tools to support these decisions and combat the pandemic. Leveraging electronic health records and registry data from institutions spanning Europe and the United States, we develop and validate a novel mortality risk calculator for hospitalized COVID-19 patients. Subsequently, we extend our machine learning framework to not only yield predictive insights but also offer actionable prescriptions. In particular, we present a methodology for personalizing the use of ACE inhibitors and ARBs for COVID-19 treatment. Our approach assesses the potential benefit from the use of these drugs at the individual level, providing novel insights into predictors of treatment effectiveness. The proposed models validate known clinical risk factors and uncover the importance of individual clinical characteristics that could guide patient triage and care planning. Our tools are openly available for clinicians and are currently used in hospitals in Spain and Italy.
For further information about joining the session, please contact firstname.lastname@example.org.
This session is hosted by the East of England Population Health Research Hub.