Using natural language processing of clinical text to enhance identification of opioid-related overdoses in electronic health records data
Brian Hazlehurst, Carla A Green, Nancy A Perrin, John Brandes, David S Carrell, Andrew Baer, Angela DeVeaugh-Geiss, Paul M Coplan, Brian Hazlehurst, Carla A Green, Nancy A Perrin, John Brandes, David S Carrell, Andrew Baer, Angela DeVeaugh-Geiss, Paul M Coplan
Abstract
Purpose: To enhance automated methods for accurately identifying opioid-related overdoses and classifying types of overdose using electronic health record (EHR) databases.
Methods: We developed a natural language processing (NLP) software application to code clinical text documentation of overdose, including identification of intention for self-harm, substances involved, substance abuse, and error in medication usage. Using datasets balanced with cases of suspected overdose and records of individuals at elevated risk for overdose, we developed and validated the application using Kaiser Permanente Northwest data, then tested portability of the application using Kaiser Permanente Washington data. Datasets were chart-reviewed to provide a gold standard for comparison and evaluation of the automated method.
Results: The method performed well in identifying overdose (sensitivity = 0.80, specificity = 0.93), intentional overdose (sensitivity = 0.81, specificity = 0.98), and involvement of opioids (excluding heroin, sensitivity = 0.72, specificity = 0.96) and heroin (sensitivity = 0.84, specificity = 1.0). The method performed poorly at identifying adverse drug reactions and overdose due to patient error and fairly at identifying substance abuse in opioid-related unintentional overdose (sensitivity = 0.67, specificity = 0.96). Evaluation using validation datasets yielded significant reductions, in specificity and negative predictive values only, for many classifications mentioned above. However, these measures remained above 0.80, thus, performance observed during development was largely maintained during validation. Similar results were obtained when evaluating portability, although there was a significant reduction in sensitivity for unintentional overdose that was attributed to missing text clinical notes in the database.
Conclusions: Methods that process text clinical notes show promise for improving accuracy and fidelity at identifying and classifying overdoses according to type using EHR data.
Trial registration: ClinicalTrials.gov NCT02667197.
Keywords: electronic health records; methods; natural language processing; opioid overdose; pharmacoepidemiology.
Conflict of interest statement
This project was conducted as part of a Food and Drug Administration (FDA)‐required postmarketing study of extended‐release and long‐acting opioid analgesics (https://www.fda.gov/downloads/Drugs/DrugSafety/InformationbyDrugClass/UCM484415.pdf), funded by the Opioid Postmarketing Consortium (OPC). The OPC is comprised of companies that hold NDAs of extended‐release and long‐acting opioid analgesics and at the time of study conduct included the following companies: Allergan; Assertio Therapeutics, Inc.; BioDelivery Sciences, Inc.; Collegium Pharmaceutical, Inc.; Daiichi Sankyo, Inc.; Egalet Corporation; Endo Pharmaceuticals, Inc.; Hikma Pharmaceuticals USA Inc.; Janssen Pharmaceuticals, Inc.; Mallinckrodt Inc.; Pernix Therapeutics Holdings, Inc.; Pfizer, Inc.; Purdue Pharma, LP.
© 2019 The Authors Pharmacoepidemiology and Drug Safety Published by John Wiley & Sons Ltd.
Figures
References
- Okie S. A flood of opioids, a rising tide of deaths. N Engl J Med. 2010;363(21):1981‐1985.
- Johnson EM, Lanier WA, Merrill RM, et al. Unintentional prescription opioid‐related overdose deaths: description of decedents by next of kin or best contact, Utah, 2008‐2009. J Gen Intern Med. 2013;28(4):522‐529.
- Centers for Disease Control and Prevention . Overdose deaths involving prescription opioids among Medicaid enrollees—Washington, 2004‐2007. MMWR. 2009;58(42):1171‐1175.
- Centers for Disease Control and Prevention . Vital signs: overdoses of prescription opioid pain relievers—United States, 199–2008. MMWR. 2011;60(43):1487‐1492.
- Warner M, Chen LH, Makuc DM, Anderson RN, Minino AM. Drug poisoning deaths in the United States, 1980‐2008. NCHS Data Brief. 2011. Dec;(81):1‐8.
- Warner M, Chen LH, Makuc DM. Increase in fatal poisonings involving opioid analgesics in the United States, 1999‐2006. NCHS Data Brief. 2009;22:1‐8.
- Unick GJ, Rosenblum D, Mars S, Ciccarone D. Intertwined epidemics: national demographic trends in hospitalizations for heroin‐ and opioid‐related overdoses, 1993‐2009. PLoS ONE. 2013;8(2):e54496.
- Rudd RA, Paulozzi LJ, Bauer MJ, et al. Increases in heroin overdose deaths–28 states, 2010 to 2012. MMWR. 2014;63(39):849‐854.
- Rudd RA, Aleshire N, Zibbell JE, Gladden M. Increases in drug and opioid overdose deaths—United States, 2000–2014. Morb Mortal Wkly Rep. 2016;64(Early Release):1‐5.
- Chakravarthy B, Shah S, Lotfipour S. Prescription drug monitoring programs and other interventions to combat prescription opioid abuse. West J Emerg Med. 2012;13(5):422‐425.
- McCarty D, Bovett R, Burns T, et al. Oregon's strategy to confront prescription opioid misuse: a case study. J Subst Abuse Treat. 2015;48(1):91‐95.
- Chou R, Fanciullo GJ, Fine PG, et al. Clinical guidelines for the use of chronic opioid therapy in chronic noncancer pain. J Pain. 2009;10(2):113‐130.
- Washington State Agency Medical Directors' Group (AMDG) . Interagency Guideline on Prescribing Opioids for Pain 06/2015; 3rd. Available at . Accessed 11/17/2016.
- Dowell D, Haegerich TM, Chou R. CDC guideline for prescribing opioids for chronic pain—United States, 2016. MMWR Recomm Rep. 2016;65(1):1‐49.
- Nelson LS, Perrone J. Curbing the opioid epidemic in the United States: the risk evaluation and mitigation strategy (REMS). JAMA. 2012;308(5):457‐458.
- U. S. Department of Health & Human Services . Abuse‐Deterrent Opioids ‐ Evaluation and Labeling: Guidance for Industry. U.S. Department of Health and Human Services Food and Drug Administration Center for Drug Evaluation and Research (CDER); 2015, Washington DC. Available Online at:
- Franklin GM, Mai J, Turner J, Sullivan M, Wickizer T, Fulton‐Kehoe D. Bending the prescription opioid dosing and mortality curves: impact of the Washington state opioid dosing guideline. Am J Ind Med. 2012;55(4):325‐331.
- Keast SL, Nesser N, Farmer K. Strategies aimed at controlling misuse and abuse of opioid prescription medications in a state Medicaid program: a policymaker's perspective. Am J Drug Alcohol Abuse. 2015;41(1):1‐6.
- Bannwarth B. Will abuse‐deterrent formulations of opioid analgesics be successful in achieving their purpose? Drugs. 2012;72(13):1713‐1723.
- Moorman‐Li R, Motycka CA, Inge LD, Congdon JM, Hobson S, Pokropski B. A review of abuse‐deterrent opioids for chronic nonmalignant pain. Pharm Ther. 2012;37(7):412‐418.
- Green CA, Perrin NA, Janoff SL, Campbell CI, Chilcoat HD, Coplan PM. Assessing the accuracy of opioid overdose and poisoning codes in diagnostic information from electronic health records, claims data, and death records. Pharmacoepidemiol Drug Saf. 2017;26(5):509‐517.
- Dunn KM, Saunders KW, Rutter CM, et al. Opioid prescriptions for chronic pain and overdose: a cohort study. Ann Intern Med. 2010;152(2):85‐92.
- Rowe C, Vittinghoff E, Santos GM, Behar E, Turner C, Coffin PO. Performance measures of diagnostic codes for detecting opioid overdose in the emergency department. Acad Emerg Med. 2017;24(4):475‐483.
- Green CA, Perrin NA, Hazlehurst B, et al. Identifying and classifying opioid‐related overdoses: a validation study. Pharmacoepidemiol Drug Saf. 2019. in press
- Hazlehurst B, Frost HR, Sittig DF, Stevens VJ. MediClass: a system for detecting and classifying encounter‐based clinical events in any electronic medical record. J Am Med Inform Assoc. 2005;12(5):517‐529.
- Hazlehurst B, Sittig DF, Stevens VJ, et al. Natural language processing in the electronic medical record: assessing clinician adherence to tobacco treatment guidelines. Am J Prev Med. 2005;29(5):434‐439.
- Hazlehurst B, Naleway A, Mullooly J. Detecting possible vaccine adverse events in clinical notes of the electronic medical record. Vaccine. 2009;27(14):2077‐2083.
- Hazelhurst B, McBurnie MA, Mularski RA, Puro JE, Chauvie SL. Automating care quality measurement with health information technology. Am J Manag Care. 2012;18(6):313‐319.
- Hazlehurst BL, Lawrence JM, Donahoo WT, et al. Automating assessment of lifestyle counseling in electronic health records. Am J Prev Med. 2014;46(5):457‐464.
- Hazlehurst BL, Kurtz SE, Masica A, et al. CER hub: an informatics platform for conducting comparative effectiveness research using multi‐institutional, heterogeneous, electronic clinical data. Int J Med Inform. 2015;84(10):763‐773.
- Shivade C, Raghavan P, Fosler‐Lussier E, et al. A review of approaches to identifying patient phenotype cohorts using electronic health records. J Am Med Inform Assoc. 2014;21(2):221‐230.
- Carrell DS, Cronkite D, Palmer RE, et al. Using natural language processing to identify problem usage of prescription opioids. Int J Med Inform. 2015. Dec;84(12):1057‐1064.
- Palmer RE, Carrell DS, Cronkite D, et al. The prevalence of problem opioid use in patients receiving chronic opioid therapy: computer‐assisted review of electronic health record clinical notes. Pain. 2015. Jul;156(7):1208‐1214.
- Haller IV, Renier CM, Juusola M, et al. Enhancing risk assessment in patients receiving chronic opioid analgesic therapy using natural language processing. Pain Med. 2016. Dec 29;pnw283.
Source: PubMed