Explainable Deep Learning Applied to Understanding Opioid Use Disorder and Its Risk Factors

Document Type

Conference Proceeding

Publication Date

12-1-2019

Journal

Proceedings - 2019 IEEE International Conference on Big Data, Big Data 2019

DOI

10.1109/BigData47090.2019.9006297

Keywords

Deep Learning; Explainable AI; Impact Scores; Opioid Use Disorder

Abstract

© 2019 IEEE. Opioid Use Disorder is an international crisis, affecting many populations. Deep learning models can potentially predict opioid use disorder, but provide little insight to how predictions are derived. Impact scores, a new development in explainable artificial intelligence, measure how individual features affect deep learning outcomes. We modeled clinical visits to predict opioid use disorder, computed impact scores, and compared them to odds log ratios from logistic regression. Impact scores were generally comparable to odds log ratios, in providing insight to opioid abuse risk, but from a better-performing method than logistic regression.

Share

COinS