Developing a Wearable Sensor-Based Digital Biomarker of Opioid Dependence.
Journal
Anesthesia and analgesia
ISSN: 1526-7598
Titre abrégé: Anesth Analg
Pays: United States
ID NLM: 1310650
Informations de publication
Date de publication:
16 Oct 2024
16 Oct 2024
Historique:
medline:
16
10
2024
pubmed:
16
10
2024
entrez:
16
10
2024
Statut:
aheadofprint
Résumé
Repeated opioid exposure leads to a variety of physiologic adaptations that develop at different rates and may foreshadow risk of opioid-use disorder (OUD), including dependence and withdrawal. Digital pharmacovigilance strategies that use noninvasive sensors to identify physiologic adaptations to opioid use represent a novel strategy to facilitate safer opioid prescribing. This study aims to identify wearable sensor-derived features associated with opioid dependence by comparing opioid-naïve individuals to chronic opioid users with acute pain and developing a machine-learning model to distinguish between the 2 groups. Using a longitudinal observational study design, continuous physiologic data were collected on participants with acute pain receiving opioid analgesia. Monitoring continued throughout hospitalization and for up to 7 days posthospital discharge. Opioid administration data were obtained from electronic health record (EHR) and participant self-report. Participants were classified as belonging to 1 of 3 categories based on opioid use history: naïve, occasional, or chronic use. Thirty features were derived from sensor data, and an additional 9 features were derived from participant demographic and treatment characteristics. Physiologic feature behavior immediately postopioid use was compared among naïve and chronic participants, and subsequently features were used to generate machine learning models which were validated using cross-validation and holdout data. Forty-one participants with a combined total of 169 opioid administrations were ultimately included in the final analysis. Four interpretable decision tree-based machine learning models with 14 sensor-based and 5 clinical features were developed to predict class membership on the level of a given observation (dose) and on the participant level. Ranges for model metrics on the participant level were as follows: accuracy 70% to 90%, sensitivity 67% to 100%, and specificity 67% to 100%. Wearable sensor-derived digital biomarkers can be used to predict opioid use status (naïve versus chronic) and the differentiating features may be detecting opioid dependence. Future work should be aimed at further delineating the phenomenon identified in these models (including opioid dependence and/or withdrawal) and at identifying transition states where an individual changes from 1 profile to another with repetitive opioid exposure.
Sections du résumé
BACKGROUND
BACKGROUND
Repeated opioid exposure leads to a variety of physiologic adaptations that develop at different rates and may foreshadow risk of opioid-use disorder (OUD), including dependence and withdrawal. Digital pharmacovigilance strategies that use noninvasive sensors to identify physiologic adaptations to opioid use represent a novel strategy to facilitate safer opioid prescribing. This study aims to identify wearable sensor-derived features associated with opioid dependence by comparing opioid-naïve individuals to chronic opioid users with acute pain and developing a machine-learning model to distinguish between the 2 groups.
METHODS
METHODS
Using a longitudinal observational study design, continuous physiologic data were collected on participants with acute pain receiving opioid analgesia. Monitoring continued throughout hospitalization and for up to 7 days posthospital discharge. Opioid administration data were obtained from electronic health record (EHR) and participant self-report. Participants were classified as belonging to 1 of 3 categories based on opioid use history: naïve, occasional, or chronic use. Thirty features were derived from sensor data, and an additional 9 features were derived from participant demographic and treatment characteristics. Physiologic feature behavior immediately postopioid use was compared among naïve and chronic participants, and subsequently features were used to generate machine learning models which were validated using cross-validation and holdout data.
RESULTS
RESULTS
Forty-one participants with a combined total of 169 opioid administrations were ultimately included in the final analysis. Four interpretable decision tree-based machine learning models with 14 sensor-based and 5 clinical features were developed to predict class membership on the level of a given observation (dose) and on the participant level. Ranges for model metrics on the participant level were as follows: accuracy 70% to 90%, sensitivity 67% to 100%, and specificity 67% to 100%.
CONCLUSIONS
CONCLUSIONS
Wearable sensor-derived digital biomarkers can be used to predict opioid use status (naïve versus chronic) and the differentiating features may be detecting opioid dependence. Future work should be aimed at further delineating the phenomenon identified in these models (including opioid dependence and/or withdrawal) and at identifying transition states where an individual changes from 1 profile to another with repetitive opioid exposure.
Identifiants
pubmed: 39413034
doi: 10.1213/ANE.0000000000007244
pii: 00000539-990000000-00986
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Subventions
Organisme : NIH/NIDA
ID : K23DA045242
Informations de copyright
Copyright © 2024 International Anesthesia Research Society.
Déclaration de conflit d'intérêts
Conflicts of Interest, Funding: Please see DISCLOSURES at the end of this article.
Références
Centers for Disease Control and Prevention. Provisional Data Shows US Drug Overdose Deaths Top 100,000 in 2023. Accessed May 18, 2023. https://blogs.cdc.gov/nchs/2023/05/18/7365/.
Centers for Disease Control and Prevention. Understanding the Opioid Overdose Epidemic. 2024. https://www.cdc.gov/overdose-prevention/about/understanding-the-opioid-overdose-epidemic.html
Kolodny A, Courtwright DT, Hwang CS, et al. The prescription opioid and heroin crisis: a public health approach to an epidemic of addiction. Annu Rev Public Health. 2015;36:559–574.
Muhuri P, Gfroerer J, Davies C. Associations of nonmedical pain reliever use and initiation of heroin use in the United States. CBHSQ Data Rev. 2013:1. https://img3.reoveme.com/m/25e062e91894208c.pdf.
Atkinson TJ, Schatman ME, Fudin J. The damage done by the war on opioids: the pendulum has swung too far. J Pain Res. 2014;7:265–268.
Pergolizzi JV Jr, Raffa RB, Rosenblatt MH. Opioid withdrawal symptoms, a consequence of chronic opioid use and opioid use disorder: current understanding and approaches to management. J Clin Pharm Ther. 2020;45:892–903.
Lai JT, Goldfine CE, Chapman BP, et al. Nobody wants to be Narcan’d: a pilot qualitative analysis of drug users’ perspectives on naloxone. West J Emerg Med. 2021;22:339–345.
Vasudevan S, Saha A, Tarver ME, Patel B. Digital biomarkers: convergence of digital health technologies and biomarkers. NPJ Digit Med. 2022;5:36.
Carreiro S, Wittbold K, Indic P, Fang H, Zhang J, Boyer EW. Wearable biosensors to detect physiologic change during opioid use. J Med Toxicol. 2016;12:255–262.
Gullapalli BT, Carreiro S, Chapman BP, Ganesan D, Sjoquist J, Rahman T. OpiTrack: a wearable-based clinical opioid use tracker with temporal convolutional attention net-works. Proc ACM Interact Mob Wearable Ubiquitous Technol. 2021;5:1–29.
Chintha KK, Indic P, Chapman B, Boyer EW, Carreiro S. Wearable biosensors to evaluate recurrent opioid toxicity after naloxone administration: a Hilbert transform approach. Proc Annu Hawaii Int Conf Syst Sci. 2018:3247–3252.
Kulman E, Chapman B, Venkatasubramanian K, Carreiro S. Identifying opioid withdrawal using wearable biosensors. Proc Annu Hawaii Int Conf Syst Sci. 2021;54:3583–3592.
Cuschieri S. The STROBE guidelines. Saudi J Anaesth. 2019;13(suppl 1):S31–S34.
Harris PA, Taylor R, Minor BL, et al.; REDCap Consortium. The REDCap consortium: Building an inter- national community of software platform partners. J Biomed Inform. 2019;95:103208.
University of North Carolina Pharmacy and Therapeutics Committee. Opiate equianalgesic dosing chart. Accessed May 22, 2019. https://www.med.unc.edu/aging/wp-content/uploads/sites/753/2018/06/Analgesic-Equivalent-Chart.pdf.
Hayden JA, Ellis J, Asbridge M, et al. Prolonged opioid use among opioid-naive individuals after prescription for nonspecific low back pain in the emergency department. Pain. 2021;162:740–748.
Lail S, Sequeira K, Lieu J, Dhalla IA. Prescription of opioids for opioid-naive medical inpatients. Can J Hosp Pharm. 2014;67:337–342.
Pino C, Wakeman S. Prescription of opioids for acute pain in opioid naïve patients. Accessed January 15, 2024. https://www.uptodate.com/contents/prescription-of-opioids-for-acute-pain-in-opioid-naive-patients.
Chapman BP, Gullapalli BT, Rahman T, Smelson D, Boyer EW, Carreiro S. Impact of individual and treatment characteristics on wearable sensor-based digital biomarkers of opioid use. NPJ Digit Med. 2022;5:123.
García FIS, Indic P, Stapp J, et al. Using wearable technology to detect prescription opioid use self-administration. Pain. 2021;163:e357–e367.
Carreiro S, Chintha KK, Shrestha S, Chapman B, Smelson D, Indic P. Wearable sensor- based detection of stress and craving in patients during treatment for substance use disorder: a mixed methods pilot study. Drug Alcohol Depend. 2020;209:107929.
Shrestha S, Stapp J, Taylor M, Leach R, Carreiro S, Indic P. Towards device agnostic detection of stress and craving in patients with substance use disorder. Proc Annu Hawaii Int Conf Syst Sci. 2023;2023:3156–3163.
Zacharaki EI, Wang S, Chawla S, et al. Classification of brain tumor type and grade using MRI texture and shape in a machine learning scheme. Magn Reson Med. 2009;62:1609–1618.
Hu YJ, Ku TH, Jan RH, Wang K, Tseng YC, Yang SF. Decision tree-based learning to predict patient controlled analgesia consumption and readjustment. BMC Med Inform Decis Mak. 2012;12:1–15.
Mathworks. Select data and validation for classification problem—MATLAB & Simulink. Accessed January 15, 2024. https://www.mathworks.com/help/stats/select-data-and-validation-for-classification-problem.html.
Bent B, Goldstein BA, Kibbe WA, Dunn JP. Investigating sources of inaccuracy in wearable optical heart rate sensors. NPJ Digit Med. 2020;3:18.