Display options
Cite
Ellis RJ, Wang Z, Genes N, et al. Predicting opioid dependence from electronic health records with machine learning. BioData Min. 2019;12:3doi: 10.1186/s13040-019-0193-0.
Ellis, R. J., Wang, Z., Genes, N., & Ma'ayan, A. (2019). Predicting opioid dependence from electronic health records with machine learning. BioData mining, 123. https://doi.org/10.1186/s13040-019-0193-0
Ellis, Randall J, et al. "Predicting opioid dependence from electronic health records with machine learning." BioData mining vol. 12 (2019): 3. doi: https://doi.org/10.1186/s13040-019-0193-0
Ellis RJ, Wang Z, Genes N, Ma'ayan A. Predicting opioid dependence from electronic health records with machine learning. BioData Min. 2019 Jan 29;12:3. doi: 10.1186/s13040-019-0193-0. eCollection 2019. PMID: 30728857; PMCID: PMC6352440.
Copy Download .nbib Format: NLM
Share it on

BioData Min. 2019 Jan 29;12:3. doi: 10.1186/s13040-019-0193-0. eCollection 2019.

Predicting opioid dependence from electronic health records with machine learning.

BioData mining

Randall J Ellis, Zichen Wang, Nicholas Genes, Avi Ma'ayan

Affiliations

  1. 1Department of Pharmacological Sciences, Mount Sinai Center for Bioinformatics, Icahn School of Medicine at Mount Sinai, New York, NY 10029 USA.
  2. 2Department of Emergency Medicine, Mount Sinai Hospital, New York, NY 10029 USA.

PMID: 30728857 PMCID: PMC6352440 DOI: 10.1186/s13040-019-0193-0

Abstract

BACKGROUND: The opioid epidemic in the United States is averaging over 100 deaths per day due to overdose. The effectiveness of opioids as pain treatments, and the drug-seeking behavior of opioid addicts, leads physicians in the United States to issue over 200 million opioid prescriptions every year. To better understand the biomedical profile of opioid-dependent patients, we analyzed information from electronic health records (EHR) including lab tests, vital signs, medical procedures, prescriptions, and other data from millions of patients to predict opioid substance dependence.

RESULTS: We trained a machine learning model to classify patients by likelihood of having a diagnosis of substance dependence using EHR data from patients diagnosed with substance dependence, along with control patients with no history of substance-related conditions, matched by age, gender, and status of HIV, hepatitis C, and sickle cell disease. The top machine learning classifier using all features achieved a mean area under the receiver operating characteristic (AUROC) curve of ~ 92%, and analysis of the model uncovered associations between basic clinical factors and substance dependence. Additionally, diagnoses, prescriptions, and procedures prior to the diagnoses of substance dependence were analyzed to elucidate the clinical profile of substance-dependent patients, relative to controls.

CONCLUSIONS: The predictive model may hold utility for identifying patients at risk of developing dependence, risk of overdose, and opioid-seeking patients that report other symptoms in their visits to the emergency room.

Keywords: Artificial intelligence; Electronic health records; Electronic medical records; Machine learning; Opioid dependence; Opioid epidemic

Conflict of interest statement

This study has been granted exemption from human-subject research by the Program for the Protection of Human Subjects (PPHS) at the Institutional Review Boards (IRB), Mount Sinai Health System. The pr

References

  1. Anesthesiology. 1999 Dec;91(6):1633-8 - PubMed
  2. Am Fam Physician. 2000 Apr 15;61(8):2401-8 - PubMed
  3. Am J Public Health. 2001 Feb;91(2):296-9 - PubMed
  4. Mayo Clin Proc. 2008 Jan;83(1):66-76 - PubMed
  5. Hepatogastroenterology. 2007 Dec;54(80):2216-20 - PubMed
  6. Fam Pract Manag. 2008 Apr;15(4):A3-5 - PubMed
  7. Clin Infect Dis. 2009 Aug 15;49(4):561-73 - PubMed
  8. Pain Med. 2012 Sep;13(9):1162-73 - PubMed
  9. PLoS Comput Biol. 2012;8(12):e1002823 - PubMed
  10. Ann Emerg Med. 2013 Oct;62(4):281-9 - PubMed
  11. AMIA Annu Symp Proc. 2013 Nov 16;2013:527-36 - PubMed
  12. Drug Alcohol Depend. 2014 May 1;138:202-8 - PubMed
  13. JAMA Psychiatry. 2015 Feb;72(2):143-51 - PubMed
  14. J Pain. 2015 Apr;16(4):380-7 - PubMed
  15. Am J Psychiatry. 2015 Apr;172(4):316-20 - PubMed
  16. Annu Rev Public Health. 2016;37:61-81 - PubMed
  17. Am J Med. 2016 Jul;129(7):699-705.e4 - PubMed
  18. Crit Care Med. 2016 Aug;44(8):1545-52 - PubMed
  19. Sci Rep. 2016 May 17;6:26094 - PubMed
  20. Med Care. 2016 Oct;54(10):901-6 - PubMed
  21. IEEE J Biomed Health Inform. 2017 Jan;21(1):22-30 - PubMed
  22. MMWR Morb Mortal Wkly Rep. 2016 Dec 30;65(50-51):1445-1452 - PubMed
  23. J Biomed Inform. 2017 Dec;76:59-68 - PubMed
  24. Aust N Z J Surg. 1979 Dec;49(6):738-42 - PubMed
  25. Ann Intern Med. 1978 Mar;88(3):424-6 - PubMed
  26. Radiology. 1982 Apr;143(1):29-36 - PubMed
  27. Acta Anaesthesiol Scand. 1993 Apr;37(3):245-9 - PubMed

Publication Types

Grant support