INFORMS Open Forum

INFORMS Boston Chapter Meeting and Talk hosted by Bentley University, Data Analytics Research Team (DART), Wednesday January 15th at 6PM

  • 1.  INFORMS Boston Chapter Meeting and Talk hosted by Bentley University, Data Analytics Research Team (DART), Wednesday January 15th at 6PM

    Posted 10 days ago
    Please join INFORMS Boston Chapter for the first talk of 2020 by Agni Orfanoudaki, MIT PhD candidate, title of the talk is Personalized Treatment for Coronary Artery Disease Patients: A Machine Learning Approach. The talk will be hosted by DART Bentley University from 6-8pm, Wednesday January 15th, 2020 at CMT (Morrison 200). Please find more information, the abstract, and speaker bio below.

    We are looking forward to seeing you on Wednesday 1/15!

    Personalized Treatment for Coronary Artery Disease Patients: A Machine Learning Approach

    Speaker: Agni Orfanoudaki, PhD candidate at the MIT Operations Research Center, advised by Prof. Dimitris Bertsimas
    Time: 01/15/2020 6:00pm to 8:00pm. Location: CMT (MOR 200), Bentley University

    Abstract: The clinical condition of Coronary Artery Disease (CAD) is present when a patient presents symptoms or complications from an inadequate blood supply to the heart. CAD remains the number one cause of death in the United States, accounting for over 360,000 annual casualties. It is mostly prevalent in older patients (above the age of 50 years) in the form of a chronic disease which requires a principal intervention and subsequent systematic medical therapy and monitoring. Current clinical practice guidelines for managing CAD account for general cardiovascular risk factors. However, they do not present a framework that considers personalized patient specific characteristics. Using the electronic health records of 21,460 patients, we created data-driven models for personalized CAD management that significantly improves health outcomes relative to the standard of care. We present ML4CAD, a novel prescriptive algorithm, that identifies for every patient the therapy with the best expected outcome using a voting mechanism. Its performance is measured with respect to both its prescription effectiveness and robustness under alternative ground truths. Finally, we developed an interactive interface, providing physicians with an intuitive, accurate, readily implementable, and effective tool.

    Speaker's Bio: Agni Orfanoudaki is a fourth year PhD student at the MIT Operations Research Center, advised by Prof. Dimitris Bertsimas. Her research interests lie at the intersection of machine learning and optimization, with applications to healthcare. Particularly, she has worked on problems related to missing data imputation, survival analysis, clustering, personalized risk prediction, and medical therapy prescription. She has collaborated with multiple healthcare organizations, including the Massachusetts General Hospital, the Brigham and Women's Hospital, the Boston Medical Center, and the Hartford Hospital. Prior to joining MIT, Agni worked as a Business Analyst at McKinsey&Company. She received a BS in Management Science and Technology from the Athens University of Economics and Business with a major on Operations Research and Business Analytics.



    ------------------------------
    Daniel Rice
    Senior Principal Scientist
    FAST Labs™, BAE Systems

    ------------------------------