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.
APA Citation
Workman, T., Zeng-Treitler, Q., Shao, Y., Kupersmith, J., Sandbrink, F., Goulet, J., Shaar, N., Spevak, C., Brandt, C., & Blackman, M. (2019). Explainable Deep Learning Applied to Understanding Opioid Use Disorder and Its Risk Factors. Proceedings - 2019 IEEE International Conference on Big Data, Big Data 2019, (). http://dx.doi.org/10.1109/BigData47090.2019.9006297