Rehabilitation Technology and Relapse-Detecting Software for Recovering Opioid Addiction Patients


  • Diego Valencia Aspiring Scientists' Summer Internship Program, 2019
  • Kendall Johnson Department of Mathematical Sciences, College of Science, George Mason University
  • Dr. Holly Matto Department of Social Work, College of Health and Human Services ,George Mason University in Fairfax, Virginia
  • Dr. Padmanabhan Seshaiyer Department of Mathematical Sciences, College of Science, George Mason University



Opioid addiction rates in the United States have been on the rise for decades, but the expansion of rehabilitation programs cannot keep up. In 2013, an estimated 20.4 million people out of 22.7 million who required treatment for illicit drug addiction failed to receive proper treatment at specialty facilities. Without proper rehabilitation, patients can fall back into a cycle of substance abuse. Considering the societal stigma of addiction and seeking treatment therefor, technological rehabilitation provides a more conservative alternative for these patients in terms of cost, privacy, and convenience. The goal of this mathematical modeling project is to develop a discreet wearable device that will determine whether a patient is having a response to a stressor, which indicates the potential for a relapse event. In this project, we created a prototype with a heart rate sensor and Raspberry Pi Zero with the Python module scikit-learn to measure heart rate and implement machine learning algorithms. These algorithms were used to perform data analysis that would evaluate Heart Rate Variability (HRV) and make complex predictions. This project has helped us to provide insight into how technology can be used for opioid addiction treatment. In addition, it has helped to substantiate how heart rate values can be used to evaluate HRV, a more accurate determinant of emotional responses to stimuli. We hope to further develop and deploy our prototype with the user community to validate the mathematical model and computational algorithms.







Abstracts from the 2019 Aspiring Scientists' Summer Internship Program