A longitudinal observational study with ecological momentary assessment and deep learning to predict non-prescribed opioid use, treatment retention, and medication nonadherence among persons receiving medication treatment for opioid use disorder.

Michael V Heinz¹, George D Price², Avijit Singh², Sukanya Bhattacharya², Ching-Hua Chen³, Asma Asyyed⁴, Monique B Does⁵, Saeed Hassanpour⁶, Emily Hichborn⁷, David Kotz⁸, Chantal A Lambert-Harris⁷, Zhiguo Li³, Bethany McLeman⁷, Varun Mishra⁹, Catherine Stanger⁷, Geetha Subramaniam¹⁰, Weiyi Wu⁶, Cynthia I Campbell¹¹, Lisa A Marsch⁷, Nicholas C Jacobson⁶

¹Center for Technology and Behavioral Health, Geisel School of Medicine, Dartmouth College, Lebanon, NH, United States; Department of Psychiatry, Geisel School of Medicine, Dartmouth College, Hanover, NH, United States. Electronic address: michael.v.heinz@dartmouth.edu.

²Quantitative Biomedical Sciences Program, Dartmouth College, Hanover, NH, United States.

³Center for Computational Health, International Business Machines (IBM) Research, Yorktown Heights, NY, United States.

⁴The Permanente Medical Group, Northern California, Addiction Medicine and Recovery Services, Oakland, CA, United States.

⁵Division of Research, Kaiser Permanente Northern California, Oakland, CA, United States.

⁶Center for Technology and Behavioral Health, Geisel School of Medicine, Dartmouth College, Lebanon, NH, United States; Department of Biomedical Data Science, Geisel School of Medicine, Dartmouth College, Lebanon, NH, United States.

⁷Center for Technology and Behavioral Health, Geisel School of Medicine, Dartmouth College, Lebanon, NH, United States.

⁸Center for Technology and Behavioral Health, Geisel School of Medicine, Dartmouth College, Lebanon, NH, United States; Department of Computer Science, Dartmouth College, Hanover, NH, United States.

⁹Khoury College of Computer Sciences, Northeastern University, Boston, MA, United States; Department of Health Sciences, Bouvé College of Health Sciences, Northeastern University, Boston, MA, United States.

¹⁰Center for Clinical Trials Network, National Institute on Drug Abuse, Bethesda, MD, United States.

¹¹Division of Research, Kaiser Permanente Northern California, Oakland, CA, United States; Department of Psychiatry and Behavioral Sciences, University of California San Francisco, San Francisco, CA, United States; Kaiser Permanente Bernard J. Tyson School of Medicine, Pasadena, CA, United States.

PubMed PMC DOI PDF

Abstract

BACKGROUND: Despite effective treatments for opioid use disorder (OUD), relapse and treatment drop-out diminish their efficacy, increasing the risks of adverse outcomes, including death. Predicting important outcomes, including non-prescribed opioid use (NPOU) and treatment discontinuation among persons receiving medications for OUD (MOUD) can provide a proactive approach to these challenges. Our…

Create a free account to keep reading

Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.

Create Free Account Sign In

Want unlimited research access? See Pro plans

NIH Funding

Grant #11421569
Technology-based Treatments for Substance Use Disorders
DARTMOUTH COLLEGE
$1,511,867 (FY2026)

Other Funding

NIDA NIH HHS(P30 DA029926)
United States
NCI NIH HHS(T32 CA134286)
United States
NIDA NIH HHS(UG1 DA040309)
United States
NIDA NIH HHS(UG1 DA040314)
United States

MeSH Terms

Humans0Opioid-Related Disorders*Ecological Momentary Assessment*Male0Female0Adult0Deep Learning*Longitudinal Studies0Middle Aged0Medication Adherence*Opiate Substitution Treatment*Electronic Health Records0Analgesics, Opioid0

Keywords

Deep learningDense longitudinal time seriesEMAEcological momentary assessmentOpioid addictionOpioid relapseOpioid treatmentOpioid use disorderRelapse prediction

Article Info

PMID: 40127869
PMCID: PMC12602038
DOI: 10.1016/j.josat.2025.209685
Received: May 15, 2024
Accepted: March 18, 2025

How to Cite

Heinz MV et al. A longitudinal observational study with ecological momentary assessment and deep learning to predict non-prescribed opioid use, treatment retention, and medication nonadherence among persons receiving medication treatment for opioid use disorder. J Subst Use Addict Treat2025;173209685. doi:10.1016/j.josat.2025.209685

Data Accuracy Notice: Research intelligence on Health AI Central is aggregated from public sources (PubMed, ClinicalTrials.gov, FDA, NIH, CMS, and others) and refreshed nightly. Classifications and derived metrics are produced by automated methods described in our Methodology. We recommend verifying critical data points against the primary sources before making decisions.