Natural Language Processing Combined with ICD-9-CM Codes as a Novel Method to Study the Epidemiology of Allergic Drug Reactions.

BACKGROUND: Allergic drug reaction epidemiologic data are sparse because it remains difficult to identify true cases in large data sets using manual chart review. OBJECTIVE: To develop and validate a novel informatics method based on natural language processing (NLP) in combination with International Classification of Diseases, Ninth Revision, Clinical Modification (ICD-9-CM) codes that identifies allergic drug reactions in the electronic health record. METHODS: Previously studied and high-yield ICD-9-CM codes were used to screen for possible allergic drug reactions among all inpatients admitted in 2007 and 2008. A random sample was selected for manual chart review to identify true cases of allergic drug reactions. A rule-based NLP algorithm was then developed to identify allergic drug reactions using free-text clinical notes and discharge summaries from the filtered cases. The performance of using manual chart review of ICD-9-CM codes alone was compared with ICD-9-CM codes in combination with NLP. RESULTS: Of 3907 cases identified by ICD-9-CM codes, 725 (19%) were randomly selected for manual chart review; 335 were confirmed as allergic drug reactions, resulting in a positive predictive value (PPV) of 46% (range: 18%-79%) when using ICD-9-CM codes alone. Our NLP algorithm in combination with ICD-9-CM codes achieved a PPV of 86% (range: 69%-100%). Among the 335 confirmed positive cases, NLP identified 259 true cases, resulting in a recall/sensitivity of 77% (range: 26%-100%). Among the 390 negative cases, NLP achieved a specificity of 89% (range: 69%-100%). CONCLUSION: Using NLP with ICD-9-CM codes improved identification of allergic drug reactions. The resulting decrease in manual chart review effort will facilitate large epidemiology studies of this understudied area.

How often do prescribers include indications in drug orders? Analysis of 4 million outpatient prescriptions.

PURPOSE: To examine the extent to which outpatient clinicians currently document drug indications in prescription instructions. METHODS: Free-text sigs were extracted from all outpatient prescriptions generated by the computerized prescriber order entry system of a major academic institution during a 5-year period. Natural language processing was used to identify drug indications. The data set was analyzed to determine the rates at which prescribers included indications. It was stratified by provider specialty, drug class, and specific medications, to determine how often these indications were in prescriptions for as-needed (PRN) versus non-PRN medications. RESULTS: During the study period, 4,356,086 prescriptions were ordered. Indications were included in 322,961 orders (7.41%). From these orders, 249,262 indications (77.18%) were written for PRN orders. Although internal medicine prescribers generated the highest number of medication orders, they included indications in only 6.26% of their prescriptions, whereas orthopedic surgery providers had the highest rate of documenting indications (33.41%). Pain was the most common indication, accounting for 30.35% of all documented indications. The drug class with the highest number of sigs-containing indications was narcotic analgesics. Non-PRN chronic medication prescriptions rarely included the indication. CONCLUSION: Prescribers rarely included drug indications in electronic free-text prescription instructions, and, when they did, it was mostly for PRN uses such as pain.

Quality of Documentation of Contrast Agent Allergies in Electronic Health Records.

PURPOSE: To describe and appraise contrast agent allergy documentation in the electronic health record (EHR). METHODS: We systematically identified medical imaging drugs and class terms in an integrated EHR allergy repository for patients seen at a large health care system between 2000 and 2013. Structured and free-text contrast allergy records were normalized and categorized by inciting agent and nature of adverse reaction. Allergen records were evaluated by their level of specificity. Reaction records were evaluated by whether the reaction was known or unknown and whether known reactions would be categorized as allergic-like or physiologic. RESULTS: Among 2.7 million patients, we identified 36,144 patients (1.3%) with at least one of 40,669 contrast allergy records associated with 49,000 reactions. Contrast allergens were more likely than other allergens to be entered as free text (15.2% versus 6.3%; odds ratio 2.69, 95% confidence interval 2.61-2.76). There were 1,305 unique contrast allergen records, which we grouped into 141 concepts. Most contrast allergen records were ambiguous contrast concepts (69.1%), rather than imaging modality-specific class terms (19.4%) or specific contrast agents (11.5%). Contrast reactions were occasionally entered as free text (24.8%), which together with structured entries were grouped into 183 concepts. A known reaction was documented in 71.8% of cases; however, 12.2% were non-allergic-like reactions. CONCLUSION: Contrast allergy records in EHRs are diverse and commonly low quality. Continued EHR enhancements and training are needed to support contrast allergy documentation to facilitate improved patient care and medical research.

Drug Hypersensitivity Reactions Documented in Electronic Health Records within a Large Health System.

BACKGROUND: Hypersensitivity reactions (HSRs) are immunologic responses to drugs. Identification of HSRs documented in the electronic health record (EHR) is important for patient safety. OBJECTIVE: To examine HSR epidemiology using longitudinal EHR data from a large United States health care system. METHODS: Patient demographic information and drug allergy data were obtained from the Partners Enterprise-wide Allergy Repository for 2 large tertiary care hospitals from 2000 to 2013. Drug-induced HSRs were categorized into immediate and delayed HSRs based on typical phenotypes. Causative drugs and drug groups were assessed. The prevalence of HSRs was determined, and sex and racial differences were analyzed. RESULTS: Among 2.7 million patients, 377,474 (13.8%) reported drug-induced HSRs, of whom 70.3% were female and 77.5% were white. A total of 580,456 HSRs were reported, of which 53.1% were immediate reaction phenotypes. Common immediate HSRs included hives (48.8%), itching (15.0%), and angioedema (14.1%). Delayed HSR phenotypes (46.9%) were largely rash (99.0%). Penicillins were associated with the most immediate (33.0%) and delayed (39.0%) HSRs. Although most HSRs were more prevalent in females and white patients, notable differences were identified for certain rare HSRs including acute interstitial nephritis, which appeared more commonly in males (0.02% vs 0.01%, P < .001). Asian patients had more fixed drug eruptions (0.007% vs 0.002%, P = .021) and severe cutaneous adverse reactions (0.05% vs 0.04%, P < .001). CONCLUSIONS: Drug HSRs were reported in 13.8% of patients. Almost one-half of reported immediate HSR phenotypes were hives, and almost all reported delayed HSR phenotypes were rash. HSRs largely affected female and white patients, but differences were identified for specific rare HSRs.

A value set for documenting adverse reactions in electronic health records.

Objective: To develop a comprehensive value set for documenting and encoding adverse reactions in the allergy module of an electronic health record. Materials and Methods: We analyzed 2 471 004 adverse reactions stored in Partners Healthcare's Enterprise-wide Allergy Repository (PEAR) of 2.7 million patients. Using the Medical Text Extraction, Reasoning, and Mapping System, we processed both structured and free-text reaction entries and mapped them to Systematized Nomenclature of Medicine - Clinical Terms. We calculated the frequencies of reaction concepts, including rare, severe, and hypersensitivity reactions. We compared PEAR concepts to a Federal Health Information Modeling and Standards value set and University of Nebraska Medical Center data, and then created an integrated value set. Results: We identified 787 reaction concepts in PEAR. Frequently reported reactions included: rash (14.0%), hives (8.2%), gastrointestinal irritation (5.5%), itching (3.2%), and anaphylaxis (2.5%). We identified an additional 320 concepts from Federal Health Information Modeling and Standards and the University of Nebraska Medical Center to resolve gaps due to missing and partial matches when comparing these external resources to PEAR. This yielded 1106 concepts in our final integrated value set. The presence of rare, severe, and hypersensitivity reactions was limited in both external datasets. Hypersensitivity reactions represented roughly 20% of the reactions within our data. Discussion: We developed a value set for encoding adverse reactions using a large dataset from one health system, enriched by reactions from 2 large external resources. This integrated value set includes clinically important severe and hypersensitivity reactions. Conclusion: This work contributes a value set, harmonized with existing data, to improve the consistency and accuracy of reaction documentation in electronic health records, providing the necessary building blocks for more intelligent clinical decision support for allergies and adverse reactions.

Prevalence of food allergies and intolerances documented in electronic health records.

BACKGROUND: Food allergy prevalence is reported to be increasing, but epidemiological data using patients' electronic health records (EHRs) remain sparse. OBJECTIVE: We sought to determine the prevalence of food allergy and intolerance documented in the EHR allergy module. METHODS: Using allergy data from a large health care organization's EHR between 2000 and 2013, we determined the prevalence of food allergy and intolerance by sex, racial/ethnic group, and allergen group. We examined the prevalence of reactions that were potentially IgE-mediated and anaphylactic. Data were validated using radioallergosorbent test and ImmunoCAP results, when available, for patients with reported peanut allergy. RESULTS: Among 2.7 million patients, we identified 97,482 patients (3.6%) with 1 or more food allergies or intolerances (mean, 1.4 ± 0.1). The prevalence of food allergy and intolerance was higher in females (4.2% vs 2.9%; P < .001) and Asians (4.3% vs 3.6%; P < .001). The most common food allergen groups were shellfish (0.9%), fruit or vegetable (0.7%), dairy (0.5%), and peanut (0.5%). Of the 103,659 identified reactions to foods, 48.1% were potentially IgE-mediated (affecting 50.8% of food allergy or intolerance patients) and 15.9% were anaphylactic. About 20% of patients with reported peanut allergy had a radioallergosorbent test/ImmunoCAP performed, of which 57.3% had an IgE level of grade 3 or higher. CONCLUSIONS: Our findings are consistent with previously validated methods for studying food allergy, suggesting that the EHR's allergy module has the potential to be used for clinical and epidemiological research. The spectrum of severity observed with food allergy highlights the critical need for more allergy evaluations.

Epidemiology of ACE Inhibitor Angioedema Utilizing a Large Electronic Health Record.

BACKGROUND: Angiotensin-converting enzyme inhibitors (ACEIs) are a common cause of drug-induced angioedema in the United States. Most epidemiologic ACEI angioedema data are from large multicenter clinical trials. OBJECTIVE: The objective of this study was to identify the incidence of and risk factors for ACEI angioedema using a large integrated electronic health record (EHR). METHODS: We conducted a retrospective cohort study of all ACEI prescriptions in the outpatient setting of a large academic center between January 1, 2000, and September 30, 2008. We determined frequency, timing, and risk factors for ACEI angioedema within 5 years of prescription. All data were derived from EHR sources, with angioedema defined by EHR reactions of angioedema, swelling, edema, or lip, eye, face, tongue, throat or mouth swelling. RESULTS: Among 134,945 patients prescribed an ACEI, 0.7% (n = 888) developed angioedema during the subsequent 5 years. Sex was similar but patients who developed ACEI angioedema were younger (61.5 vs 62.7 years, P = .007). Patients with ACEI angioedema were more likely to have a history of nonsteroidal anti-inflammatory drug allergy compared with patients who did not develop angioedema (7.1% vs 4.2%, P < .001). We identified a 0.07% incidence of ACEI angioedema within 1 month of prescription and a 0.23% incidence during the first year. Incidence of angioedema was relatively constant annually over the subsequent 4 years (0.10% to 0.12%). CONCLUSIONS: The incidence of ACEI angioedema within a large EHR is consistent with large clinical trial data. We observed a persistent and relatively constant annual risk; however, angioedema risk factors and underlying genetic and pathophysiological mechanisms require further study.

Adverse and Hypersensitivity Reactions to Prescription Nonsteroidal Anti-Inflammatory Agents in a Large Health Care System.

BACKGROUND: Nonsteroidal anti-inflammatory drugs (NSAIDs) are among the most frequently used medications in the United States. NSAID use can be limited by adverse drug reactions (ADRs), including hypersensitivity reactions (HSRs). OBJECTIVE: We aimed to use electronic health record data to determine the incidence and predictors of HSRs to prescription NSAIDs. METHODS: We performed a retrospective cohort study of all adult outpatients in a large health care system prescribed diclofenac, indomethacin, nabumetone, or piroxicam between January 1, 2004, and September 30, 2012. The primary outcome was an ADR or HSR attributed to the prescribed NSAID within 1 year of prescription, determined from a longitudinal allergy database. We used natural language processing to classify known ADRs as either HSRs or side effects. Multivariable logistic regression models were used to identify independent risk factors for NSAID HSRs. RESULTS: Of 62,719 patients prescribed NSAIDs, 1,035 (1.7%) had an ADR, of which 189 (18.3%) were HSRs. Multivariable regression analysis identified that patients with prior drug HSR history (odds ratio [OR] 1.8 [95% CI 1.3, 2.5]), female sex (OR 1.8 [95% CI 1.3, 2.4]), autoimmune disease (OR 1.7 [95% CI 1.1, 2.7]), and those prescribed the maximum standing NSAID dose (OR 1.5 [95% CI 1.1, 2.0]) had increased odds of NSAID HSR. CONCLUSIONS: NSAID therapeutic use can be limited by ADRs; about 1 in 5 NSAID ADRs is an HSR. Both patient and drug factors contribute to HSR risk and are important to guide patient counseling.

Food entries in a large allergy data repository.

OBJECTIVE: Accurate food adverse sensitivity documentation in electronic health records (EHRs) is crucial to patient safety. This study examined, encoded, and grouped foods that caused any adverse sensitivity in a large allergy repository using natural language processing and standard terminologies. METHODS: Using the Medical Text Extraction, Reasoning, and Mapping System (MTERMS), we processed both structured and free-text entries stored in an enterprise-wide allergy repository (Partners' Enterprise-wide Allergy Repository), normalized diverse food allergen terms into concepts, and encoded these concepts using the Systematized Nomenclature of Medicine - Clinical Terms (SNOMED-CT) and Unique Ingredient Identifiers (UNII) terminologies. Concept coverage also was assessed for these two terminologies. We further categorized allergen concepts into groups and calculated the frequencies of these concepts by group. Finally, we conducted an external validation of MTERMS's performance when identifying food allergen terms, using a randomized sample from a different institution. RESULTS: We identified 158 552 food allergen records (2140 unique terms) in the Partners repository, corresponding to 672 food allergen concepts. High-frequency groups included shellfish (19.3%), fruits or vegetables (18.4%), dairy (9.0%), peanuts (8.5%), tree nuts (8.5%), eggs (6.0%), grains (5.1%), and additives (4.7%). Ambiguous, generic concepts such as "nuts" and "seafood" accounted for 8.8% of the records. SNOMED-CT covered more concepts than UNII in terms of exact (81.7% vs 68.0%) and partial (14.3% vs 9.7%) matches. DISCUSSION: Adverse sensitivities to food are diverse, and existing standard terminologies have gaps in their coverage of the breadth of allergy concepts. CONCLUSION: New strategies are needed to represent and standardize food adverse sensitivity concepts, to improve documentation in EHRs.

Identifying Patients with Depression Using Free-text Clinical Documents.

About 1 in 10 adults are reported to exhibit clinical depression and the associated personal, societal, and economic costs are significant. In this study, we applied the MTERMS NLP system and machine learning classification algorithms to identify patients with depression using discharge summaries. Domain experts reviewed both the training and test cases, and classified these cases as depression with a high, intermediate, and low confidence. For depression cases with high confidence, all of the algorithms we tested performed similarly, with MTERMS' knowledge-based decision tree slightly better than the machine learning classifiers, achieving an F-measure of 89.6%. MTERMS also achieved the highest F-measure (70.6%) on intermediate confidence cases. The RIPPER rule learner was the best performing machine learning method, with an F-measure of 70.0%, and a higher precision but lower recall than MTERMS. The proposed NLP-based approach was able to identify a significant portion of the depression cases (about 20%) that were not on the coded diagnosis list.

Automated misspelling detection and correction in clinical free-text records.

Accurate electronic health records are important for clinical care and research as well as ensuring patient safety. It is crucial for misspelled words to be corrected in order to ensure that medical records are interpreted correctly. This paper describes the development of a spelling correction system for medical text. Our spell checker is based on Shannon's noisy channel model, and uses an extensive dictionary compiled from many sources. We also use named entity recognition, so that names are not wrongly corrected as misspellings. We apply our spell checker to three different types of free-text data: clinical notes, allergy entries, and medication orders; and evaluate its performance on both misspelling detection and correction. Our spell checker achieves detection performance of up to 94.4% and correction accuracy of up to 88.2%. We show that high-performance spelling correction is possible on a variety of clinical documents.