Kenneth H. Lai

Rising drug allergy alert overrides in electronic health records: an observational retrospective study of a decade of experience

OBJECTIVE There have been growing concerns about the impact of drug allergy alerts on patient safety and provider alert fatigue. The authors aimed to explore the common drug allergy alerts over the last 10 years and the reasons why providers tend to override these alerts. DESIGN Retrospective observational cross-sectional study (2004-2013). MATERIALS AND METHODS Drug allergy alert data (n = 611,192) were collected from two large academic hospitals in Boston, MA (USA). RESULTS Overall, the authors found an increase in the rate of drug allergy alert overrides, from 83.3% in 2004 to 87.6% in 2013 (P < .001). Alarmingly, alerts for immune mediated and life threatening reactions with definite allergen and prescribed medication matches were overridden 72.8% and 74.1% of the time, respectively. However, providers were less likely to override these alerts compared to possible (cross-sensitivity) or probable (allergen group) matches (P < .001). The most common drug allergy alerts were triggered by allergies to narcotics (48%) and other analgesics (6%), antibiotics (10%), and statins (2%). Only slightly more than one-third of the reactions (34.2%) were potentially immune mediated. Finally, more than half of the overrides reasons pointed to irrelevant alerts (i.e., patient has tolerated the medication before, 50.9%) and providers were significantly more likely to override repeated alerts (89.7%) rather than first time alerts (77.4%, P < .001). DISCUSSION AND CONCLUSIONS These findings underline the urgent need for more efforts to provide more accurate and relevant drug allergy alerts to help reduce alert override rates and improve alert fatigue.

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.

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 Shannons 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.

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 organizations 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 EHRs 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.

Automated identification of wound information in clinical notes of patients with heart diseases: Developing and validating a natural language processing application.

BACKGROUND Electronic health records are being increasingly used by nurses with up to 80% of the health data recorded as free text. However, only a few studies have developed nursing-relevant tools that help busy clinicians to identify information they need at the point of care. OBJECTIVE This study developed and validated one of the first automated natural language processing applications to extract wound information (wound type, pressure ulcer stage, wound size, anatomic location, and wound treatment) from free text clinical notes. METHODS AND DESIGN First, two human annotators manually reviewed a purposeful training sample (n=360) and random test sample (n=1100) of clinical notes (including 50% discharge summaries and 50% outpatient notes), identified wound cases, and created a gold standard dataset. We then trained and tested our natural language processing system (known as MTERMS) to process the wound information. Finally, we assessed our automated approach by comparing system-generated findings against the gold standard. We also compared the prevalence of wound cases identified from free-text data with coded diagnoses in the structured data. RESULTS The testing dataset included 101 notes (9.2%) with wound information. The overall system performance was good (F-measure is a compiled measure of systems accuracy=92.7%), with best results for wound treatment (F-measure=95.7%) and poorest results for wound size (F-measure=81.9%). Only 46.5% of wound notes had a structured code for a wound diagnosis. CONCLUSIONS The natural language processing system achieved good performance on a subset of randomly selected discharge summaries and outpatient notes. In more than half of the wound notes, there were no coded wound diagnoses, which highlight the significance of using natural language processing to enrich clinical decision making. Our future steps will include expansion of the applications information coverage to other relevant wound factors and validation of the model with external data.

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 Healthcares 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.

Studying Associations Between Heart Failure Self-Management and Rehospitalizations Using Natural Language Processing

This study developed an innovative natural language processing algorithm to automatically identify heart failure (HF) patients with ineffective self-management status (in the domains of diet, physical activity, medication adherence, and adherence to clinician appointments) from narrative discharge summary notes. We also analyzed the association between self-management status and preventable 30-day hospital readmissions. Our natural language system achieved relatively high accuracy (F-measure = 86.3%; precision = 95%; recall = 79.2%) on a testing sample of 300 notes annotated by two human reviewers. In a sample of 8,901 HF patients admitted to our healthcare system, 14.4% (n = 1,282) had documentation of ineffective HF self-management. Adjusted regression analyses indicated that presence of any skill-related self-management deficit (odds ratio [OR] = 1.3, 95% confidence interval [CI] = [1.1, 1.6]) and non-specific ineffective self-management (OR = 1.5, 95% CI = [1.2, 2]) was significantly associated with readmissions. We have demonstrated the feasibility of identifying ineffective HF self-management from electronic discharge summaries with natural language processing.

Medical Malpractice Trends: Errors in Automated Speech Recognition

Automated speech recognition (SR) technology—defined as computer-assisted transcription of spoken language into readable text in real or near-real time—is becoming ubiquitous in everyday life. SR has been already integrated into many electronic devices (e.g., personal computers, mobile phones, smart homes) and is envisioned to revolutionize the way we interact with technology in the near future [1]. In medicine, SR was adopted early in several fields, such as radiology [2], but was not accepted uniformly across all clinical settings. Today however, with the widespread adoption of electronic health records, SR is becoming increasingly prevalent across many types of clinicians in multiple healthcare settings. Previously, SR technologies in healthcare were adopted with caution because of safety concerns and the potential for errors. With the rapid proliferation of SR into different domains of healthcare, only a few studies have examined the safety and accuracy of these systems. For example, a systematic review published in 2016 [3] found that only ten studies to date have focused on the safety of SR systems. Although the accuracy of SR systems has grown over the years [3], their safety is still a significant concern. For example, a recent study has found that an SR system in the emergency room made 1.3 errors per note on average and 15% of the errors were judged clinically significant [4]. Another study conducted in 2017 found that the rate of errors in SR-system-generated clinical notes was more than four times higher than that in non-SR notes [5]. However, our literature review did not find any studies on whether SR errors have led to actual patient harm. To bridge this gap in knowledge, we analyzed a large database of medical malpractice claims to assess patient harm related to SR.