Using Machine Learning to Predict Problematic Prescription Opioid Use and Opioid Overdose

PI: Walid Gellad, MD, MPH
Funding Source: NIH/NIDA
September 2017 - June 2022

This R01 project improves on traditional methods for predicting risk of overdose from prescription opioids by applying machine learning techniques.  The study team developed prediction algorithms to identify patients who are at risk of opioid overdose, and after testing and refining the algorithm, compared the accuracy of an approach integrating Medicaid claims data with clinical data to an approach using claims data alone.

Read about this project in the media

Read published results from this project

Developing and validating a machine-learning algorithm to predict opioid overdose in Medicaid beneficiaries in two US states: a prognostic modelling study
Wei-Hsuan Lo-Ciganic, Julie M Donohue, Qingnan Yang, James L Huang, Ching-Yuan Chang, Jeremy C Weiss, Jingchuan Guo, Hao H Zhang, Gerald Cochran, Adam J Gordon, Daniel C Malone, Chian K Kwoh, Debbie L Wilson, Courtney C Kuza, Walid F Gellad
The Lancet Digital Health, May 24, 2022

Predicting Mortality Risk After a Hospital or Emergency Department Visit for Nonfatal Opioid Overdose
Jingchuan Guo, Wei-Hsuan Lo-Ciganic, Qingnan Yang, James L Huang, Jeremy C Weiss, Gerald Cochran, Daniel C Malone, Courtney C Kuza, Adam J Gordon, Julie M Donohue, Walid F Gellad
Journal of General Internal Medicine, January 22, 2021

Occupational Patterns of Opioid-Related Overdose Deaths Among Arizona Medicaid Enrollees, 2008-2017
Rohan Chalasani, Wei-Hsuan Lo-Ciganic MS, PhD, James L. Huang PhD, Jingchuan Guo PhD, MD, MPH, Jeremy C. Weiss MD, PhD, Courtney C. Kuza PhD, MPH, & Walid F. Gellad MD, MPH
Journal of General Internal Medicine, February 10, 2020

Evaluation of Machine-Learning Algorithms for Predicting Opioid Overdose Risk Among Medicare Beneficiaries With Opioid Prescriptions
Wei-Hsuan Lo-Ciganic, PhD; James L. Huang, PhD; Hao H. Zhang, PhD; Jeremy C. Weiss, MD, PhD; Yonghui Wu, PhD; C. Kent Kwoh, MD; Julie M. Donohue, PhD; Gerald Cochran, PhD; Adam J. Gordon, MD, MPH; Daniel C. Malone, PhD; Courtney C. Kuza, PhD; Walid F. Gellad, MD, MPH
JAMA Network Open, March 22, 2019