Identifying high-dose opioid prescription risks using machine learning: A focus on sociodemographic characteristics

Olabode B. Ogundele; Butros M. Dahu; Praveen Rao; Xing Song; Timothy Haithcoat; Mutiyat Hameed; Douglas Burgess; Tracy Greever-Rice; Mirna Becevic

doi:10.5055/jom.0924

Authors

Olabode B. Ogundele, PhD
Butros M. Dahu, PhD
Praveen Rao, PhD
Xing Song, PhD
Timothy Haithcoat, PhD
Mutiyat Hameed, MHA
Douglas Burgess, MD
Tracy Greever-Rice, PhD
Mirna Becevic, PhD https://orcid.org/0000-0001-6520-1581

DOI:

https://doi.org/10.5055/jom.0924

Keywords:

opioid-related disorders, opioid analgesics, physician prescribing patterns, machine learning, electronic medical records

Abstract

Objective: The objective of this study was to leverage machine learning techniques to analyze administrative claims and socioeconomic data, with the aim of identifying and interpreting the risk factors associated with high-dose opioid prescribing.

Design: We applied six machine learning algorithms to a dataset integrating Medicaid claims from Missouri (2017-2021) and 2018 United States Census Bureau data. High-dose prescribing was defined as dosages ≥120 morphine milligram equivalent/day. SHapely Additive exPlanations methods were utilized to enhance model interpretability, ensuring transparent insights into the predictors of high-dose prescription risks.

Results: Our findings reveal that sociodemographic factors like age, race, and sex, along with socioeconomic variables such as percentages of veterans, disability, and primary care physicians (PCPs) per capita, have associations with high-dose prescription risks. Notably, higher percentage of veterans and PCPs per capita within counties correspond with increased high-dose prescriptions, while older age groups and patient sex also predict a greater risk.

Conclusion: This analysis underscores the significant influence of sociodemographic variables on high-dose opioid prescriptions. The interplay of these factors highlights the need for multifaceted public health strategies to address the underlying complexities of the opioid crisis. The integration of machine learning methods with traditional epidemiological techniques represents a promising approach for gaining a comprehensive understanding of intricate patterns not captured in traditional statistical analysis, thereby enabling effective mitigation of the opioid crisis.

Author Biographies

Olabode B. Ogundele, PhD

Institute for Data Science and Informatics (MUIDSI); Missouri Telehealth Network (MTN), University of Missouri, Columbia, Missouri

Butros M. Dahu, PhD

Institute for Data Science and Informatics (MUIDSI), University of Missouri, Columbia, Missouri

Praveen Rao, PhD

Department of Electrical Engineering and Computer Science; Institute for Data Science and Informatics (MUIDSI), University of Missouri, Columbia, Missouri

Xing Song, PhD

Biomedical Informatics, Biostatistics and Medical Epidemiology (BBME); Institute for Data Science and Informatics (MUIDSI), University of Missouri, Columbia, Missouri

Timothy Haithcoat, PhD

Institute for Data Science and Informatics (MUIDSI), University of Missouri, Columbia, Missouri

Mutiyat Hameed, MHA

Sisters of St. Mary (SSM) Health, St. Louis, Missouri

Douglas Burgess, MD

Department of Psychiatry, University of Missouri Kansas City (UMKC), Kansas City, Missouri

Tracy Greever-Rice, PhD

College of Health Sciences, Center for Health Policy, University of Missouri, Columbia, Missouri

Mirna Becevic, PhD

Department of Dermatology; Institute for Data Science and Informatics (MUIDSI); Missouri Telehealth Network (MTN), University of Missouri, Columbia, Missouri

References

CDC: Understanding the opioid overdose epidemic: Opioids. 2023. Available at https://www.cdc.gov/opioids/basics/epidemic.html. Accessed October 10, 2023.

Volkow ND, McLellan AT: Opioid abuse in chronic pain–misconceptions and mitigation strategies. N Engl J Med. 2016; 374(13): 1253-1263. DOI: 10.1056/NEJMra1507771.

Dowell D: CDC clinical practice guideline for prescribing opioids for pain—United States, 2022. MMWR Recomm Rep. 2022; 71: 1-95. DOI: 10.15585/mmwr.rr7103a1.

Busse J: The 2017 Canadian guideline for opioids for chronic non-cancer pain. 2017. Appendix to: Busse J, Craigie S, Juurlink D, et al. Guideline for opioid therapy and chronic noncancer pain. CMAJ 2017. DOI: 10.1503/cmaj.170363.

Merrill JO, Von Korff M, Banta-Green CJ, et al.: Prescribed opioid difficulties, depression, and opioid dose among chronic opioid therapy patients. Gen Hosp Psychiatry. 2012; 34(6): 581-587. DOI: 10.1016/j.genhosppsych.2012.06.018.

Morasco BJ, Yarborough BJ, Smith NX, et al.: Higher prescription opioid dose is associated with worse patient-reported pain outcomes and more health care utilization. J Pain. 2017; 18(4): 437-445. DOI: 10.1016/j.jpain.2016.12.004.

Gomes T, Mamdani MM, Dhalla IA, et al.: Opioid dose and drug-related mortality in patients with nonmalignant pain. Arch Intern Med. 2011; 171(7): 686-691. DOI: 10.1001/archinternmed.2011.117.

Chang HY, Kharrazi H, Bodycombe D, et al.: Healthcare costs and utilization associated with high-risk prescription opioid use: A retrospective cohort study. BMC Med. 2018; 16(1): 69. DOI: 10.1186/s12916-018-1058-y.

Curtis HJ, Croker R, Walker AJ, et al.: Opioid prescribing trends and geographical variation in England, 1998–2018: A retrospective database study. Lancet Psychiatry. 2019; 6(2): 140-150. DOI: 10.1016/S2215-0366(18)30471-1.

Gomes T, Mamdani MM, Michael Paterson J, et al.: Trends in high-dose opioid prescribing in Canada. Can Fam Physician. 2014; 60(9): 826-832.

Lalic S, Gisev N, Bell JS, et al.: Transition to high-dose or strong opioids: A population-based study of people initiating opioids in Australia. Addiction. 2020; 115(6): 1088-1097. DOI: 10.1111/add.14926.

Frenk SM, Porter KS, Paulozzi LJ: Prescription opioid analgesic use among adults: United States, 1999-2012. NCHS Data Brief. 2015; 189: 1-8.

Campbell CI, Weisner C, Leresche L, et al.: Age and gender trends in long-term opioid analgesic use for noncancer pain. Am J Public Health. 2010; 100(12): 2541-2547. DOI: 10.2105/AJPH.2009.180646.

Volkow ND, McLellan TA, Cotto JH, et al.: Characteristics of opioid prescriptions in 2009. JAMA. 2011; 305(13): 1299-1301. DOI: 10.1001/jama.2011.401.

Craven P, Cinar O, Fosnocht D, et al.: Prospective, 10-year evaluation of the impact of Hispanic ethnicity on pain management practices in the ED. Am J Emerg Med. 2014; 32(9): 1055-1059. DOI: 10.1016/j.ajem.2014.06.026.

Singhal A, Tien YY, Hsia RY: Racial-Ethnic disparities in opioid prescriptions at emergency department visits for conditions commonly associated with prescription drug abuse. PloS One. 2016; 11(8): e0159224. DOI: 10.1371/journal.pone.0159224.

Ringwalt C, Roberts AW, Gugelmann H, et al.: Racial disparities across provider specialties in opioid prescriptions dispensed to Medicaid beneficiaries with chronic noncancer pain. Pain Med. 2015; 16(4): 633-640. DOI: 10.1111/pme.12555.

Pletcher MJ, Kertesz SG, Kohn MA, et al.: Trends in opioid prescribing by race/ethnicity for patients seeking care in US emergency departments. JAMA. 2008; 299(1): 70-78. DOI: 10.1001/jama.2007.64.

McDonald DC, Carlson KE: The ecology of prescription opioid abuse in the USA: Geographic variation in patients’ use of multiple prescribers (“doctor shopping”). Pharmacoepidemiol Drug Saf. 2014; 23(12): 1258-1267. DOI: 10.1002/pds.3690.

Spiller H, Lorenz DJ, Bailey EJ, et al.: Epidemiological trends in abuse and misuse of prescription opioids. J Addict Dis. 2009; 28(2): 130-136. DOI: 10.1080/10550880902772431.

McDonald DC, Carlson K, Izrael D: Geographic variation in opioid prescribing in the US. J Pain. 2012; 13(10): 988-996. DOI: 10.1016/j.jpain.2012.07.007.

Grigoras CA, Karanika S, Velmahos E, et al.: Correlation of opioid mortality with prescriptions and social determinants: A cross-sectional study of Medicare enrollees. Drugs. 2018; 78(1): 111-121. DOI: 10.1007/s40265-017-0846-6.

Wright ER, Kooreman HE, Greene MS, et al.: The iatrogenic epidemic of prescription drug abuse: County-level determinants of opioid availability and abuse. Drug Alcohol Depend. 2014; 138: 209-215. DOI: 10.1016/j.drugalcdep.2014.03.002.

Lipkin JS, Thorpe JM, Gellad WF, et al.: Identifying sociodemographic profiles of veterans at risk for high-dose opioid prescribing using classification and regression trees. J Opioid Manag. 2020; 16(6): 409-424. DOI: 10.5055/jom.2020.0599.

Edlund MJ, Steffick D, Hudson T, et al.: Risk factors for clinically recognized opioid abuse and dependence among veterans using opioids for chronic non-cancer pain. Pain. 2007; 129(3): 355-362. DOI: 10.1016/j.pain.2007.02.014.

Shi J, Fu R, Hamilton H, et al.: A machine learning approach to predict e-cigarette use and dependence among Ontario youth. Health Promot Chronic Dis Prev Can. 2022; 42(1): 21-28. DOI: 10.24095/hpcdp.42.1.04.

Lin HC, Wang Z, Hu YH, et al.: Characteristics of statewide prescription drug monitoring programs and potentially inappropriate opioid prescribing to patients with non-cancer chronic pain: A machine learning application. Prev Med. 2022; 161: 107116. DOI: 10.1016/j.ypmed.2022.107116.

Caballero FF, Soulis G, Engchuan W, et al.: Advanced analytical methodologies for measuring healthy ageing and its determinants, using factor analysis and machine learning techniques: The ATHLOS project. Sci Rep. 2017; 7: 43955. DOI: 10.1038/srep43955.

DuBrava S, Mardekian J, Sadosky A, et al.: Using random forest models to identify correlates of a diabetic peripheral neuropathy diagnosis from electronic health record data. Pain Med. 2017; 18(1): 107-115. DOI: 10.1093/pm/pnw096.

Tomasˇev N, Glorot X, Rae JW, et al.: A clinically applicable approach to continuous prediction of future acute kidney injury. Nature. 2019; 572(7767): 116-119. DOI: 10.1038/s41586-019-1390-1.

Luo W, Phung D, Tran T, et al.: Guidelines for developing and reporting machine learning predictive models in biomedical research: A multidisciplinary view. J Med Internet Res. 2016; 18(12): e323. DOI: 10.2196/jmir.5870.

Richards GC, Mahtani KR, Muthee TB, et al.: Factors associated with the prescribing of high-dose opioids in primary care: A systematic review and meta-analysis. BMC Med. 2020; 18(1): 68. DOI: 10.1186/s12916-020-01528-7.

Ahmad MA, Eckert C, Teredesai A: Interpretable machine learning in healthcare. In Proceedings of the 2018 ACM International Conference on Bioinformatics, Computational Biology, and Health Informatics. 2018: 559-560.

Tonekaboni S, Joshi S, McCradden MD: What clinicians want: Contextualizing explainable machine learning for clinical end use. In Proceedings of the 4th Machine Learning for Healthcare Conference. PMLR, 2019: 359-380. Available at https://proceedings.mlr.press/v106/tonekaboni19a.html. Accessed December 11, 2023.

SHAP: An introduction to explainable AI with Shapley values—SHAP latest documentation. Available at https://shap.readthedocs.io/en/latest/example_notebooks/overviews/An%20introduction%20to%20explainable%20AI%20with%20Shapley%20values.html. Accessed November 7, 2023.

United States Census Bureau: S2701: Selected characteristics of …-Census Bureau table. Available at https://data.census.gov/table/ACSST5Y2018.S2701?g=060XX00US3913308168. Accessed December 18, 2023.

Federal Communications Commission: Mapping broadband health in America—For developers. Available at https://www.fcc.gov/health/maps/developers. Accessed December 18, 2023.

Missouri Primary Care Needs Assessment (PCNA): Missouri Department of Health and Senior Services Office of Rural Health and Primary Care. 2020. Available at https://health.mo.gov/living/families/primarycare/pdf/primary-care-needsassessment-2020.pdf. Accessed December 11, 2023.

Sarker IH: Machine learning: Algorithms, real-world applications and research directions. SN Comput Sci. 2021; 2(3): 160. DOI: 10.1007/s42979-021-00592-x.

James G, Witten D, Hastie T, et al.: An Introduction to Statistical Learning: With Applications in R. Berlin: Springer US, 2021. DOI: 10.1007/978-1-0716-1418-1.

Anderson KK, Hendrick F, McClair V: Data analysis brief: National trends in high-dose chronic opioid utilization among dually eligible and Medicare-only beneficiaries (2006-2015). 2018. Available at https://www.cms.gov/medicare-medicaidcoordination/medicare-and-medicaid-coordination/medicare-medicaid-coordination-office/datastatisticalresources/downloads/opioidsdatabrief_2006-2015_10242018.pdf. Accessed November 14, 2023.

Kobus AM, Smith DH, Morasco BJ, et al.: Correlates of higher dose opioid medication use for low back pain in primary care. J Pain Off J Am Pain Soc. 2012; 13(11): 1131-1138. DOI: 10.1016/j.jpain.2012.09.003.

National Institutes of Health (NIH): Men died of overdose at 2-3 times greater a rate than women in the US in 2021. 2020. Available at https://www.nih.gov/news-events/newsreleases/men-died-overdose-2-3-times-greater-rate-womenus-2020-2021. Accessed November 14, 2023.

NIDA: Drug overdose death rates. 2023. Available at https://nida.nih.gov/research-topics/trends-statistics/overdose-deathrates. Accessed November 14, 2023.

Rigg KK, Monnat SM: Urban vs. rural differences in prescription opioid misuse among adults in the United States: Informing region specific drug policies and interventions. Int J Drug Policy. 2015; 26(5): 484-491. DOI: 10.1016/j.drugpo.2014.10.001.

Ogundele OB, Song X, Rao P, et al.: Claims data analysis of provider-to-provider tele-mentoring program impact on opioid prescribing in Missouri. J Opioid Manag. 2024; 20(2): 133-147. DOI: 10.5055/jom.0825.