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.