Using natural language processing to identify problem usage of prescription opioids.

BACKGROUND: Accurate and scalable surveillance methods are critical to understand widespread problems associated with misuse and abuse of prescription opioids and for implementing effective prevention and control measures. Traditional diagnostic coding incompletely documents problem use. Relevant information for each patient is often obscured in vast amounts of clinical text. OBJECTIVES: We developed and evaluated a method that combines natural language processing (NLP) and computer-assisted manual review of clinical notes to identify evidence of problem opioid use in electronic health records (EHRs). METHODS: We used the EHR data and text of 22,142 patients receiving chronic opioid therapy (≥70 days' supply of opioids per calendar quarter) during 2006-2012 to develop and evaluate an NLP-based surveillance method and compare it to traditional methods based on International Classification of Disease, Ninth Edition (ICD-9) codes. We developed a 1288-term dictionary for clinician mentions of opioid addiction, abuse, misuse or overuse, and an NLP system to identify these mentions in unstructured text. The system distinguished affirmative mentions from those that were negated or otherwise qualified. We applied this system to 7336,445 electronic chart notes of the 22,142 patients. Trained abstractors using a custom computer-assisted software interface manually reviewed 7751 chart notes (from 3156 patients) selected by the NLP system and classified each note as to whether or not it contained textual evidence of problem opioid use. RESULTS: Traditional diagnostic codes for problem opioid use were found for 2240 (10.1%) patients. NLP-assisted manual review identified an additional 728 (3.1%) patients with evidence of clinically diagnosed problem opioid use in clinical notes. Inter-rater reliability among pairs of abstractors reviewing notes was high, with kappa=0.86 and 97% agreement for one pair, and kappa=0.71 and 88% agreement for another pair. CONCLUSIONS: Scalable, semi-automated NLP methods can efficiently and accurately identify evidence of problem opioid use in vast amounts of EHR text. Incorporating such methods into surveillance efforts may increase prevalence estimates by as much as one-third relative to traditional methods.

Automated prediction of risk for problem opioid use in a primary care setting.

UNLABELLED: Identification of patients at increased risk for problem opioid use is recommended by chronic opioid therapy (COT) guidelines, but clinical assessment of risks often does not occur on a timely basis. This research assessed whether structured electronic health record (EHR) data could accurately predict subsequent problem opioid use. This research was conducted among 2,752 chronic noncancer pain patients initiating COT (≥70 days' supply of an opioid in a calendar quarter) during 2008 to 2010. Patients were followed through the end of 2012 or until disenrollment from the health plan, whichever was earlier. Baseline risk indicators were derived from structured EHR data for a 2-year period prior to COT initiation. Problem opioid use after COT initiation was assessed by reviewing clinician-documented problem opioid use in EHR clinical notes identified using natural language processing techniques followed by computer-assisted manual review of natural language processing-positive clinical notes. Multivariate analyses in learning and validation samples assessed prediction of subsequent problem opioid use. The area under the receiver operating characteristic curve (c-statistic) for problem opioid use was .739 (95% confidence interval = .688, .790) in the validation sample. A measure of problem opioid use derived from a simple weighted count of risk indicators was found to be comparably predictive of the natural language processing measure of problem opioid use, with 60% sensitivity and 72% specificity for a weighted count of ≥4 risk indicators. PERSPECTIVE: An automated surveillance method utilizing baseline risk indicators from structured EHR data was moderately accurate in identifying COT patients who had subsequent problem opioid use.

The prevalence of problem opioid use in patients receiving chronic opioid therapy: computer-assisted review of electronic health record clinical notes.

To estimate the prevalence of problem opioid use, we used natural language processing (NLP) techniques to identify clinical notes containing text indicating problem opioid use from over 8 million electronic health records (EHRs) of 22,142 adult patients receiving chronic opioid therapy (COT) within Group Health clinics from 2006 to 2012. Computer-assisted manual review of NLP-identified clinical notes was then used to identify patients with problem opioid use (overuse, misuse, or abuse) according to the study criteria. These methods identified 9.4% of patients receiving COT as having problem opioid use documented during the study period. An additional 4.1% of COT patients had an International Classification of Disease, version 9 (ICD-9) diagnosis without NLP-identified problem opioid use. Agreement between the NLP methods and ICD-9 coding was moderate (kappa = 0.61). Over one-third of the NLP-positive patients did not have an ICD-9 diagnostic code for opioid abuse or dependence. We used structured EHR data to identify 14 risk indicators for problem opioid use. Forty-seven percent of the COT patients had 3 or more risk indicators. The prevalence of problem opioid use was 9.6% among patients with 3 to 4 risk indicators, 26.6% among those with 5 to 6 risk indicators, and 55.04% among those with 7 or more risk indicators. Higher rates of problem opioid use were observed among young COT patients, patients who sustained opioid use for more than 4 quarters, and patients who received higher opioid doses. Methods used in this study provide a promising approach to efficiently identify clinically recognized problem opioid use documented in EHRs of large patient populations. Computer-assisted manual review of EHR clinical notes found a rate of problem opioid use of 9.4% among 22,142 COT patients over 7 years.