Predicting post-surgical opioid consumption using perioperative surgical data
Author(s)
Yu, Justin,M. Eng.(Justin K.)Massachusetts Institute of Technology.
Download1241197974-MIT.pdf (453.4Kb)
Other Contributors
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science.
Advisor
Peter Szolovits.
Terms of use
Metadata
Show full item recordAbstract
Improper consumption of prescription opioids is a massive public health issue in the United States currently. Here, we propose one approach of tackling this issue through using machine learning techniques to predict opioid consumption post discharge for surgical patients. Through the data collected from surgical patients at BIDMC, relevant features will be identified and used to predict if patients high, outlier consumption. Using logistic regression and gradient boosted decision trees, model performance were evaluated at AUCs of 0.7270 and 0.7289 respectively.
Description
Thesis: M. Eng., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, May, 2020 "May 2020." Date of graduation confirmed by MIT Registrar Office. Cataloged from student-submitted PDF of thesis. Includes bibliographical references (pages 49-50).
Date issued
2020Department
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer SciencePublisher
Massachusetts Institute of Technology
Keywords
Electrical Engineering and Computer Science.