EUVIMEDObjevte EUVIMED
Open access

An Automatically Adaptive Digital Health Intervention to Decrease Opioid-Related Risk While Conserving Counselor Time: Quantitative Analysis of Treatment Decisions Based on Artificial Intelligence and Patient-Reported Risk Measures

John D Piette iD, Laura Thomas iD, Sean Newman iD, Nicolle Marinec iD, Joel Krauss iD, Jenny Chen iD, Zhenke Wu iD, Amy S B Bohnert iD

Journal of Medical Internet Research · 2023

DOI: 10.2196/44165 ↗

At a glance

Journal article in Journal of Medical Internet Research, 2023. Written by John D Piette and 7 co-authors. Institution: Ann Arbor Department of Veterans Affairs Center for Clinical Management Research, Ann Arbor, MI, United States. Major MEDLINE topics: Chronic Pain, Counselors, Opioid-Related Disorders. Cited 13 times so far (Crossref); 43 references. The full text is freely available in PubMed Central. Funded by: NIDDK NIH HHS, NIDA NIH HHS.

AbstraktSubjectsBibliografické údajeCiteRelated studies

Abstract (original language)

Background

Some patients prescribed opioid analgesic (OA) medications for pain experience serious side effects, including dependence, sedation, and overdose. As most patients are at low risk for OA-related harms, risk reduction interventions requiring multiple counseling sessions are impractical on a large scale.

Objective

This study evaluates whether an intervention based on reinforcement learning (RL), a field of artificial intelligence, learned through experience to personalize interactions with patients with pain discharged from the emergency department (ED) and decreased self-reported OA misuse behaviors while conserving counselors’ time.

Methods

We used data representing 2439 weekly interactions between a digital health intervention (“Prescription Opioid Wellness and Engagement Research in the ED” [PowerED]) and 228 patients with pain discharged from 2 EDs who reported recent opioid misuse. During each patient’s 12 weeks of intervention, PowerED used RL to select from 3 treatment options: a brief motivational message delivered via an interactive voice response (IVR) call, a longer motivational IVR call, or a live call from a counselor. The algorithm selected session types for each patient each week, with the goal of minimizing OA risk, defined in terms of a dynamic score reflecting patient reports during IVR monitoring calls. When a live counseling call was predicted to have a similar impact on future risk as an IVR message, the algorithm favored IVR to conserve counselor time. We used logit models to estimate changes in the relative frequency of each session type as PowerED gained experience. Poisson regression was used to examine the changes in self-reported OA risk scores over calendar time, controlling for the ordinal session number (1st to 12th).

Results

Participants on average were 40 (SD 12.7) years of age; 66.7% (152/228) were women and 51.3% (117/228) were unemployed. Most participants (175/228, 76.8%) reported chronic pain, and 46.2% (104/225) had moderate to severe depressive symptoms. As PowerED gained experience through interactions over a period of 142 weeks, it delivered fewer live counseling sessions than brief IVR sessions (P=.006) and extended IVR sessions (P

Subjects

MeSH terms (MEDLINE)

Chronic PainCounselorsOpioid-Related DisordersFemaleHumansMaleAnalgesics, OpioidArtificial IntelligencePatient Reported Outcome MeasuresAdultMiddle Aged

Author keywords

artificial intelligenceopioid safetypain managementreinforcement learningtelehealth

Substances

Analgesics, Opioid

Authors and institutions

  • Ann Arbor Department of Veterans Affairs Center for Clinical Management Research, Ann Arbor, MI, United States.
  • Department of Health Behavior Health Education, School of Public Health, University of Michigan, Ann Arbor, MI, United States.
  • Department of Anesthesiology, School of Medicine, University of Michigan, Ann Arbor, MI, United States.
  • Department of Emergency Medicine, Trinity Health St. Joseph Mercy, Ann Arbor, MI, United States.
  • Department of Biostatistics, School of Public Health, University of Michigan, Ann Arbor, MI, United States.

ORCID profiles: John D Piette, Laura Thomas, Sean Newman, Nicolle Marinec, Joel Krauss, Jenny Chen, Zhenke Wu, Amy S B Bohnert

Funding

  • NIDDK NIH HHS
  • NIDA NIH HHS

Cite

APA

Piette, J. D., Thomas, L., Newman, S., Marinec, N., Krauss, J., Chen, J., Wu, Z., & Bohnert, A. S. B. (2023). An Automatically Adaptive Digital Health Intervention to Decrease Opioid-Related Risk While Conserving Counselor Time: Quantitative Analysis of Treatment Decisions Based on Artificial Intelligence and Patient-Reported Risk Measures. Journal of Medical Internet Research. https://doi.org/10.2196/44165

Vancouver

Piette JD, Thomas L, Newman S, Marinec N, Krauss J, Chen J, et al. An Automatically Adaptive Digital Health Intervention to Decrease Opioid-Related Risk While Conserving Counselor Time: Quantitative Analysis of Treatment Decisions Based on Artificial Intelligence and Patient-Reported Risk Measures. Journal of Medical Internet Research. 2023. doi:10.2196/44165

BibTeX
@article{Piette2023,
  author = {Piette, John D and Thomas, Laura and Newman, Sean and Marinec, Nicolle and Krauss, Joel and Chen, Jenny and Wu, Zhenke and Bohnert, Amy S B},
  title = {An Automatically Adaptive Digital Health Intervention to Decrease Opioid-Related Risk While Conserving Counselor Time: Quantitative Analysis of Treatment Decisions Based on Artificial Intelligence and Patient-Reported Risk Measures},
  journal = {Journal of Medical Internet Research},
  year = {2023},
  doi = {10.2196/44165}
}
Start for free →