Identification of recurrent atrial fibrillation using natural language processing applied to electronic health records.

AIMS: This study aimed to develop and apply natural language processing (NLP) algorithms to identify recurrent atrial fibrillation (AF) episodes following rhythm control therapy initiation using electronic health records (EHRs). METHODS AND RESULTS: We included adults with new-onset AF who initiated rhythm control therapies (ablation, cardioversion, or antiarrhythmic medication) within two US integrated healthcare delivery systems. A code-based algorithm identified potential AF recurrence using diagnosis and procedure codes. An automated NLP algorithm was developed and validated to capture AF recurrence from electrocardiograms, cardiac monitor reports, and clinical notes. Compared with the reference standard cases confirmed by physicians' adjudication, the F-scores, sensitivity, and specificity were all above 0.90 for the NLP algorithms at both sites. We applied the NLP and code-based algorithms to patients with incident AF (n = 22 970) during the 12 months after initiating rhythm control therapy. Applying the NLP algorithms, the percentages of patients with AF recurrence for sites 1 and 2 were 60.7% and 69.9% (ablation), 64.5% and 73.7% (cardioversion), and 49.6% and 55.5% (antiarrhythmic medication), respectively. In comparison, the percentages of patients with code-identified AF recurrence for sites 1 and 2 were 20.2% and 23.7% for ablation, 25.6% and 28.4% for cardioversion, and 20.0% and 27.5% for antiarrhythmic medication, respectively. CONCLUSION: When compared with a code-based approach alone, this study's high-performing automated NLP method identified significantly more patients with recurrent AF. The NLP algorithms could enable efficient evaluation of treatment effectiveness of AF therapies in large populations and help develop tailored interventions.

Identifying Cases of Shoulder Injury Related to Vaccine Administration (SIRVA) in the United States: Development and Validation of a Natural Language Processing Method.

BACKGROUND: Shoulder injury related to vaccine administration (SIRVA) accounts for more than half of all claims received by the National Vaccine Injury Compensation Program. However, due to the difficulty of finding SIRVA cases in large health care databases, population-based studies are scarce. OBJECTIVE: The goal of the research was to develop a natural language processing (NLP) method to identify SIRVA cases from clinical notes. METHODS: We conducted the study among members of a large integrated health care organization who were vaccinated between April 1, 2016, and December 31, 2017, and had subsequent diagnosis codes indicative of shoulder injury. Based on a training data set with a chart review reference standard of 164 cases, we developed an NLP algorithm to extract shoulder disorder information, including prior vaccination, anatomic location, temporality and causality. The algorithm identified 3 groups of positive SIRVA cases (definite, probable, and possible) based on the strength of evidence. We compared NLP results to a chart review reference standard of 100 vaccinated cases. We then applied the final automated NLP algorithm to a broader cohort of vaccinated persons with a shoulder injury diagnosis code and performed manual chart confirmation on a random sample of NLP-identified definite cases and all NLP-identified probable and possible cases. RESULTS: In the validation sample, the NLP algorithm had 100% accuracy for identifying 4 SIRVA cases and 96 cases without SIRVA. In the broader cohort of 53,585 vaccinations, the NLP algorithm identified 291 definite, 124 probable, and 52 possible SIRVA cases. The chart-confirmation rates for these groups were 95.5% (278/291), 67.7% (84/124), and 17.3% (9/52), respectively. CONCLUSIONS: The algorithm performed with high sensitivity and reasonable specificity in identifying positive SIRVA cases. The NLP algorithm can potentially be used in future population-based studies to identify this rare adverse event, avoiding labor-intensive chart review validation.

Risk for Shoulder Conditions After Vaccination: A Population-Based Study Using Real-World Data.

BACKGROUND: Although shoulder conditions have been reported as an adverse event after intramuscular vaccination in the deltoid muscle, epidemiologic data on shoulder conditions after vaccination are limited. OBJECTIVE: To estimate the risk for shoulder conditions after vaccination and assess possible risk factors. DESIGN: Retrospective cohort study. SETTING: Kaiser Permanente Southern California, a large integrated health care organization. PARTICIPANTS: Kaiser Permanente Southern California members aged 3 years or older who had an intramuscular vaccination administered in the deltoid muscle between 1 April 2016 and 31 December 2017. MEASUREMENTS: A natural language processing (NLP) algorithm was used to identify potential shoulder conditions among vaccinated persons with shoulder disorder diagnosis codes. All NLP-identified cases were manually chart confirmed on the basis of our case definition. The characteristics of vaccinated persons with and without shoulder conditions were compared. RESULTS: Among 3 758 764 administered vaccinations, 371 cases of shoulder condition were identified, with an estimated incidence of 0.99 (95% CI, 0.89 to 1.09) per 10 000 vaccinations. The incidence was 1.22 (CI, 1.10 to 1.35) for the adult (aged ≥18 years) and 0.05 (CI, 0.02 to 0.14) for the pediatric (aged 3 to 17 years) vaccinated populations. In the adult vaccinated population, advanced age, female sex, an increased number of outpatient visits in the 6 months before vaccination, lower Charlson Comorbidity Index, and pneumococcal conjugate vaccine were associated with a higher risk for shoulder conditions. Among influenza vaccines, quadrivalent vaccines were associated with an increased risk for shoulder conditions. Simultaneous administration of vaccines was associated with a higher risk for shoulder conditions among elderly persons. LIMITATION: Generalizability to other health care settings, use of administrative data, and residual confounding. CONCLUSION: These population-based data suggest a small absolute risk for shoulder conditions after vaccination. Given the high burden of shoulder conditions, clinicians should pay attention to any factors that may further increase risks. PRIMARY FUNDING SOURCE: Centers for Disease Control and Prevention.

Cardiorespiratory Fitness and Mortality in Patients Aged 60 to 90 Years.

Chronological age alone does not fully reflect a patient's prognosis. We sought to assess the association of cardiorespiratory fitness (quantified by METs) with all-cause mortality among patients aged 60 to 90 years. This retrospective study included patients who underwent exercise treadmill testing at an integrated healthcare system from 2011 to 2019. Patients were categorized into age groups: 60 to <70 years, 70 to <80 years, and 80 to 90 years; and cardiorespiratory fitness level: low (<5 METs), moderate (5 to 10 METs), and high fitness (>10 METs). Mean follow-up was 3.5 years. A total of 40,520 patients were included (mean age 67.7 ± 4.7 years, 48.6% women). Of whom, 27,021 were 60 to <70 years old (66.7%); 12,638 70 to <80 years old (31.2%); and 1,861 80 to 90 years old (4.6%). There were 3,494 patients categorized as low (8.6%), 21,863 as moderate (54%), and 15,163 as high fitness (37.4%). Low fitness level was independently associated with lower survival (hazard ratio [HR] 1.61, 95% confidence interval [CI] 1.15 to 2.24). Using age 60 to 70 group with high fitness level as reference, the age 80 to 90 group with high fitness level had better survival than their younger counterparts with low fitness level (age 80 to 90 years high fitness level: HR 2.9, 95% CI 1.2 to 7.2; age 60 to 70 years low fitness level: HR 4.3, 95% CI 3.1 to 5.9; age 70 to 80 years low fitness level: HR 6.8, 95% CI 5.2 to 8.9) on adjusted analysis. In conclusion, higher cardiorespiratory fitness is associated with better survival. Patients >80 years old with high fitness level have comparable or even better survival than their younger counterparts with submoderate fitness levels. Chronological age alone should not be the only factor when considering prognosis.

Automated interpretation of stress echocardiography reports using natural language processing.

Aims: Stress echocardiography (SE) findings and interpretations are commonly documented in free-text reports. Reusing SE results requires laborious manual reviews. This study aimed to develop and validate an automated method for abstracting SE reports in a large cohort. Methods and results: This study included adult patients who had SE within 30 days of their emergency department visit for suspected acute coronary syndrome in a large integrated healthcare system. An automated natural language processing (NLP) algorithm was developed to abstract SE reports and classify overall SE results into normal, non-diagnostic, infarction, and ischaemia categories. Randomly selected reports (n = 140) were double-blindly reviewed by cardiologists to perform criterion validity of the NLP algorithm. Construct validity was tested on the entire cohort using abstracted SE data and additional clinical variables. The NLP algorithm abstracted 6346 consecutive SE reports. Cardiologists had good agreements on the overall SE results on the 140 reports: Kappa (0.83) and intraclass correlation coefficient (0.89). The NLP algorithm achieved 98.6% specificity and negative predictive value, 95.7% sensitivity, positive predictive value, and F-score on the overall SE results and near-perfect scores on ischaemia findings. The 30-day acute myocardial infarction or death outcomes were highest among patients with ischaemia (5.0%), followed by infarction (1.4%), non-diagnostic (0.8%), and normal (0.3%) results. We found substantial variations in the format and quality of SE reports, even within the same institution. Conclusions: Natural language processing is an accurate and efficient method for abstracting unstructured SE reports. This approach creates new opportunities for research, public health measures, and care improvement.

Natural Language Processing to Identify Pulmonary Nodules and Extract Nodule Characteristics From Radiology Reports.

BACKGROUND: There is an urgent need for population-based studies on managing patients with pulmonary nodules. RESEARCH QUESTION: Is it possible to identify pulmonary nodules and associated characteristics using an automated method? STUDY DESIGN AND METHODS: We revised and refined an existing natural language processing (NLP) algorithm to identify radiology transcripts with pulmonary nodules and greatly expanded its functionality to identify the characteristics of the largest nodule, when present, including size, lobe, laterality, attenuation, calcification, and edge. We compared NLP results with a reference standard of manual transcript review in a random test sample of 200 radiology transcripts. We applied the final automated method to a larger cohort of patients who underwent chest CT scan in an integrated health care system from 2006 to 2016, and described their demographic and clinical characteristics. RESULTS: In the test sample, the NLP algorithm had very high sensitivity (98.6%; 95% CI, 95.0%-99.8%) and specificity (100%; 95% CI, 93.9%-100%) for identifying pulmonary nodules. For attenuation, edge, and calcification, the NLP algorithm achieved similar accuracies, and it correctly identified the diameter of the largest nodule in 135 of 141 cases (95.7%; 95% CI, 91.0%-98.4%). In the larger cohort, the NLP found 217,771 reports with nodules among 717,304 chest CT reports (30.4%). From 2006 to 2016, the number of reports with nodules increased by 150%, and the mean size of the largest nodule gradually decreased from 11 to 8.9 mm. Radiologists documented the laterality and lobe (90%-95%) more often than the attenuation, calcification, and edge characteristics (11%-14%). INTERPRETATION: The NLP algorithm identified pulmonary nodules and associated characteristics with high accuracy. In our community practice settings, the documentation of nodule characteristics is incomplete. Our results call for better documentation of nodule findings. The NLP algorithm can be used in population-based studies to identify pulmonary nodules, avoiding labor-intensive chart review.

Higher Emergency Physician Chest Pain Hospitalization Rates Do Not Lead to Improved Patient Outcomes.

BACKGROUND: Wide variation exists for hospital admission rates for the evaluation of possible acute coronary syndrome, but there are limited data on physician-level variation. Our aim is to describe physicians' rates of admission for suspected acute coronary syndrome and associated 30-day major adverse events. METHODS: We conducted a retrospective analysis of adult emergency department chest pain encounters from January 2016 to December 2017 across 15 community emergency departments within an integrated health system in Southern California. The unit of analysis was the Emergency physician. The primary outcome was the proportion of patients admitted/observed in the hospital. Secondary analysis described the 30-day incidence of death or acute myocardial infarction. RESULTS: Thirty-eight thousand seven hundred seventy-eight patients encounters were included among 327 managing physicians. The median number of encounters per physician was 123 (interquartile range, 82-157) with an overall admission/observation rate of 14.0%. Wide variation in individual physician admission rates were observed (unadjusted, 1.5%-68.9%) and persisted after case-mix adjustments (adjusted, 5.5%-27.8%). More clinical experience was associated with a higher likelihood of hospital care. There was no difference in 30-day death or acute myocardial infarction between high- and low-admitting physician quartiles (unadjusted, 1.70% versus 0.82% and adjusted, 1.33% versus 1.29%). CONCLUSIONS: Wide variation persists in physician-level admission rates for emergency department chest pain evaluation, even in a well-integrated health system. There was no associated benefit in 30-day death or acute myocardial infarction for patients evaluated by high-admitting physicians. This suggests an additional opportunity to investigate the safe reduction of physician-level variation in the use of hospital care.

Early Noninvasive Cardiac Testing After Emergency Department Evaluation for Suspected Acute Coronary Syndrome.

Importance: Professional guidelines recommend noninvasive cardiac testing (NIT) within 72 hours of an emergency department (ED) evaluation for suspected acute coronary syndrome. However, there is inexact evidence that this strategy reduces the risk of future death or acute myocardial infarction (MI). Objective: To evaluate the effectiveness of early NIT in reducing the risk of death or acute MI within 30 days. Design, Setting, and Participants: This retrospective, multicenter cohort study within the Kaiser Permanente Southern California integrated health care delivery system compared the effectiveness of early noninvasive cardiac testing vs no testing in patients with chest pain and in whom acute MI was ruled out who presented to an ED from January 2015 to December 2017. Patients were followed up for up to 30 days after emergency department discharge. Exposures: Noninvasive cardiac testing performed within 3 days of an ED evaluation for suspected acute coronary syndrome. Main Outcomes and Measures: The primary outcome was composite risk of death or acute MI, within 30 days of an ED discharge. Results: A total of 79 040 patients were evaluated in this study, of whom 57.7% were female. The mean (SD) age of the cohort was 57 (16) years, and 16 164 patients (21%) had completed early NIT. The absolute risk of death or MI within 30 days was low (<1%). Early NIT had the minor benefit of reducing the absolute composite risk of death or MI (0.4% [95% CI, -0.6% to -0.3%]), and, separately, of death (0.2% [95% CI, -0.2% to -0.1%]), MI (-0.3% [95% CI, -0.5% to -0.1%]), and major adverse cardiac event (-0.5% [95% CI, -0.7% to -0.3%]). The number needed to treat was 250 to avoid 1 death or MI, 500 to avoid 1 death, 333 to avoid 1 MI, and 200 to avoid 1 major adverse cardiovascular event within 30 days. Subgroup analysis revealed a number needed to treat of 14 to avoid 1 death or MI in the subset of patients with elevated troponin. Conclusions and Relevance: Early NIT was associated with a small decrease in the risk of death or MI in patients admitted to the ED with suspected acute coronary syndrome, but this clinical strategy may not be optimal for most patients given the large number needed to treat.

Evaluation of Outpatient Cardiac Stress Testing After Emergency Department Encounters for Suspected Acute Coronary Syndrome.

STUDY OBJECTIVE: Professional guidelines recommend 72-hour cardiac stress testing after an emergency department (ED) evaluation for possible acute coronary syndrome. There are limited data on actual compliance rates and effect on patient outcomes. Our aim is to describe rates of completion of noninvasive cardiac stress testing and associated 30-day major adverse cardiac events. METHODS: We conducted a retrospective analysis of ED encounters from June 2015 to June 2017 across 13 community EDs within an integrated health system in Southern California. The study population included all adults with a chest pain diagnosis, troponin value, and discharge with an order for an outpatient cardiac stress test. The primary outcome was the proportion of patients who completed an outpatient stress test within the recommended 3 days, 4 to 30 days, or not at all. Secondary analysis described the 30-day incidence of major adverse cardiac events. RESULTS: During the study period, 24,459 patients presented with a chest pain evaluation requiring troponin analysis and stress test ordering from the ED. Of these, we studied the 7,988 patients who were discharged home to complete diagnostic testing, having been deemed appropriate by the treating clinicians for an outpatient stress test. The stress test completion rate was 31.3% within 3 days and 58.7% between 4 and 30 days, and 10.0% of patients did not complete the ordered test. The 30-day rates of major adverse cardiac events were low (death 0.0%, acute myocardial infarction 0.7%, and revascularization 0.3%). Rapid receipt of stress testing was not associated with improved 30-day major adverse cardiac events (odds ratio 0.92; 95% confidence interval 0.55 to 1.54). CONCLUSION: Less than one third of patients completed outpatient stress testing within the guideline-recommended 3 days after initial evaluation. More important, the low adverse event rates suggest that selective outpatient stress testing is safe. In this cohort of patients selected for outpatient cardiac stress testing in a well-integrated health system, there does not appear to be any associated benefit of stress testing within 3 days, nor within 30 days, compared with those who never received testing at all. The lack of benefit of obtaining timely testing, in combination with low rates of objective adverse events, may warrant reassessment of the current guidelines.

Effect of a HEART Care Pathway on Chest Pain Management Within an Integrated Health System.

STUDY OBJECTIVE: We describe the association of implementing a History, ECG, Age, Risk Factors, and Troponin (HEART) care pathway on use of hospital care and noninvasive stress testing, as well as 30-day patient outcomes in community emergency departments (EDs). METHODS: We performed a prospective interrupted-time-series study of adult encounters for patients evaluated for suspected acute coronary syndrome. The primary outcome was hospitalization or observation, noninvasive stress testing, or both within 30 days. The secondary outcome was 30-day all-cause mortality or acute myocardial infarction. A generalized estimating equation segmented logistic regression model was used to compare the odds of the primary outcome before and after HEART implementation. All models were adjusted for patient and facility characteristics and fit with physicians as a clustering variable. RESULTS: A total of 65,393 ED encounters (before, 30,522; after, 34,871) were included in the study. Overall, 33.5% (before, 35.5%; after, 31.8%) of ED chest pain encounters resulted in hospitalization or observation, noninvasive stress testing, or both. Primary adjusted results found a significant decrease in the primary outcome postimplementation (odds ratio 0.984; 95% confidence interval [CI] 0.974 to 0.995). This resulted in an absolute adjusted month-to-month decrease of 4.39% (95% CI 3.72% to 5.07%) after 12 months' follow-up, with a continued trend downward. There was no difference in 30-day mortality or myocardial infarction (0.6% [before] versus 0.6% [after]; odds ratio 1.02; 95% CI 0.97 to 1.08). CONCLUSION: Implementation of a HEART pathway in the ED evaluation of patients with chest pain resulted in less inpatient care and noninvasive cardiac testing and was safe. Using HEART to risk stratify chest pain patients can improve the efficiency and quality of care.

Radiotherapy for brain metastases near the end of life in an integrated health care system.

BACKGROUND: To examine radiotherapy (RT) patterns-of-care and utilization at the end of life (EOL) among non-small cell lung cancer (NSCLC) patients with brain metastasis (BrM) in an integrated health care system. METHODS: Central tumor registry identified 5,133 patients diagnosed with NSCLC from 2007-2011. BrM were determined by imaging. Patient and clinical characteristics were obtained by chart abstraction. In addition to abstracted variables, graded prognostic assessment (GPA) score of 0-1 was derived by collected data and tested as a predictor of death within 14 or 30 days of RT. RESULTS: On NSCLC presentation, 10% harbored BrM while 7% developed BrM thereafter. Of 900 BrM patients, 15% were not referred for RT, with median time to death of 21 days. Median time to death for 5% not recommended RT was 48 days. Among those receiving brain RT, 11.9% died within 14 days and 23.3% (cumulatively) died within 30 days of treatment. Over 50% with GPA score 0-1 received RT, 11% within 14 days and 21% within 30 days of death; median survival of GPA score 0-1 patients was 49 days. GPA score 0-1 independently predicted for death within 30 days of RT receipt. CONCLUSIONS: BrM are common in NSCLC, and most patients are referred for brain RT. A surprising proportion of patients received treatment near the EOL, as 23% died within 30 days of RT. GPA score of 0-1 predicted for death within 30 days of treatment. RT referral, recommendation, and timing should be better tailored to life expectancy, and additional benchmarks for quality of care are needed.

Warfarin Management and Outcomes in Patients with Nonvalvular Atrial Fibrillation Within an Integrated Health Care System.

BACKGROUND: Warfarin is a common treatment option to manage patients with nonvalvular atrial fibrillation (NVAF) in clinical practice. Understanding current pharmacist-led anticoagulation clinic management patterns and associated outcomes is important for quality improvement; however, currently little evidence associating outcomes with management patterns exists. OBJECTIVES: To (a) describe warfarin management patterns and (b) evaluate associations between warfarin treatment and clinical outcomes for patients with NVAF in an integrated health care system. METHODS: A retrospective cohort study was conducted among NVAF patients with warfarin therapy between January 1, 2006, and December 31, 2011, using Kaiser Permanente Southern California data, and followed until December 31, 2013. Management patterns related to international normalized ratio (INR) monitoring, anticoagulation clinic pharmacist intervention (consultation), and warfarin dose adjustments were investigated along with yearly attrition rates, time-in-therapeutic ranges (TTRs), and clinical outcomes (stroke or systemic embolism and major bleeding). Descriptive statistics and multivariable Cox proportional hazard models were used to determine associations between TTR and clinical outcomes. RESULTS: A total of 32,074 NVAF patients on warfarin treatment were identified and followed for a median of 3.8 years. About half (49%) of the patients were newly initiating warfarin therapy. INR monitoring and pharmacist interventions were conducted roughly every 3 weeks after 6 months of warfarin treatment. Sixty-three percent of the study population had ≥ 1 warfarin dose adjustments with a mean (SD) of 6.7 (6.3) annual dose adjustments. Warfarin dose adjustments occurred at a median of 1 day (interquartile ranges [IQR] 1-3) after the INR measurement. Yearly attrition rate was from 3.3% to 6.3% during the follow-up, and median (IQR) TTR was 61% (46%-73%). Patients who received frequent INR monitoring (≥ 27 times per year), pharmacist interventions (≥ 24 times per year), or frequently adjusted warfarin dose (≥ 11 times per year) consistently showed poor TTRs (mean TTR for the highest quartiles was 45.3%-48.3%). A higher TTR was associated with a lower risk of clinical outcomes regardless of frequency of INR monitoring, pharmacist interventions, or number of dose adjustments. Patients whose TTRs were < 65%, even with frequent pharmacist interventions, had similar stroke or systemic embolism event rates, as compared with patients with TTRs < 65% and less frequent interventions (1.88 vs. 1.54 stroke or systemic embolism rates per 100 person-years, respectively, P = 0.78). The lowest TTR quartile (< 46%) was associated with a 3 times higher risk of stroke or systemic embolism (hazard ratio [HR] = 3.19, 95% CI = 2.71-3.77) and a 2 times higher risk of major bleeding (HR = 2.10, 95% CI = 1.96-2.24) compared with the highest TTR quartile (≥ 73%). CONCLUSIONS: Despite close monitoring with timely warfarin dose adjustments, there were still a substantial number of challenging patients whose TTRs were suboptimal despite a higher number of pharmacist interventions. These patients eventually experienced more stroke or systemic embolism and bleeding events among NVAF patients managed by anticoagulation clinics. New individualized treatment or management strategies for patients who are not able to reach optimal therapeutic ranges are necessary to improve outcomes. DISCLOSURES: This research and manuscript were funded by Bristol-Myers Squibb Company and Pfizer. Authors from Bristol-Myers Squibb Company and Pfizer participated in the design of the study, interpretation of the data, review/revision of the manuscript, and approval of the final version of the manuscript. An received a grant for research support from Bristol-Myers Squibb/Pfizer. Niu, Rashid, and Zheng received a grant from Bristol-Myers Squibb/Pfizer to their institutions for salary reimbursement. Vo, Singh, and Aranda are employed by Bristol-Myers Squibb; Bruno was employed by Bristol-Myers Squibb at the time of this study. Mendes and Dills are employed by Pfizer, and Mendes was a member of the Pfizer Cardiovascular and Metabolic Field Medical Team during the time of this study. Lang, Jazdzewski, and Le have no known conflicts of interest to report. Study concept and design were contributed primarily by An and Rashid, along with the other authors. Niu took the lead in data collection, along with Zheng, and data interpretation was performed by An, along with Mendes and Dills, with assistance from the other authors. The manuscript was written by An and revised by Mendes, Dills, Vo, Singh, Bruno, and Aranda, along with Lang, Le, and Jazdezewski. Part of this study's findings was presented at the CHEST 2015 Annual Meeting in Montreal, Canada, on October 28, 2015.

Medication Extraction from Electronic Clinical Notes in an Integrated Health System: A Study on Aspirin Use in Patients with Nonvalvular Atrial Fibrillation.

PURPOSE: The purpose of this study was to investigate whether aspirin use can be captured from the clinical notes in a nonvalvular atrial fibrillation population. METHODS: A total of 29,507 patients with newly diagnosed nonvalvular atrial fibrillation were identified from January 1, 2006, through December 31, 2011, and were followed up through December 31, 2012. More than 3 million clinical notes were retrieved from electronic medical records. A training data set of 2949 notes was created to develop a computer-based method to automatically extract aspirin use status and dosage information using natural language processing (NLP). A gold standard data set of 5339 notes was created using a blinded manual review. NLP results were validated against the gold standard data set. The aspirin data from the structured medication databases were also compared with the results from NLP. Positive and negative predictive values, along with sensitivity and specificity, were calculated. FINDINGS: NLP achieved 95.5% sensitivity and 98.9% specificity when compared with the gold standard data set. The positive predictive value was 93.0%, and the negative predictive value was 99.3%. NLP identified aspirin use for 83.8% of the study population, and 70% of the low dose aspirin use was identified only by the NLP method. IMPLICATIONS: We developed and validated an NLP method specifically designed to identify low dose aspirin use status from the clinical notes with high accuracy. This method can be a valuable tool to supplement existing structured medication data.

Recent Trends in the Identification of Incidental Pulmonary Nodules.

RATIONALE: Pulmonary nodules are common incidental findings, but information about their incidence in the era of computed tomography (CT) is lacking. OBJECTIVES: To examine recent trends in pulmonary nodule identification. METHODS: We used electronic health records and natural language processing to identify members of an integrated health system who had nodules measuring 4 to 30 mm. We calculated rates of chest CT imaging, nodule identification, and receipt of a new lung cancer diagnosis within 2 years of nodule identification, and standardized rates by age and sex to estimate the frequency of nodule identification in the U.S. population in 2010. MEASUREMENTS AND MAIN RESULTS: Between 2006 and 2012, more than 200,000 adult members underwent 415,581 chest CT examinations. The annual frequency of chest CT imaging increased from 1.3 to 1.9% for all adult members, whereas the frequency of nodule identification increased from 24 to 31% for all scans performed. The annual rate of chest CT increased from 15.4 to 20.7 per 1,000 person-years, and the rate of nodule identification increased from 3.9 to 6.6 per 1,000 person-years, whereas the rate of a new lung cancer diagnosis remained stable. By extrapolation, more than 4.8 million Americans underwent at least one chest CT scan and 1.57 million had a nodule identified, including 63,000 who received a new lung cancer diagnosis within 2 years. CONCLUSIONS: Incidental pulmonary nodules are an increasingly common consequence of routine medical care, with an incidence that is much greater than recognized previously. More frequent nodule identification has not been accompanied by increases in the diagnosis of cancerous nodules.

Patient and clinical characteristics associated with gout flares in an integrated healthcare system.

Gout flares have been challenging to identify in retrospective databases due to gout flares not being well documented by diagnosis codes, making it difficult to conduct accurate database studies. Previous studies have used different algorithms, and in this study, we used a computer-based method to identify gout flares. The objectives of this study were to identify gout flares in gout patients newly initiated on urate-lowering therapy and evaluate factors associated with a patient experiencing gout flares after starting drug treatment. This was a retrospective cohort study identifying gout patients newly initiated on a urate-lowering therapy (ULT) during the study time period of January 1, 2007-December 31, 2010. The index date was the first dispensed ULT prescription during the study time period. Patients had to be ≥18 years of age on index date, have no history of prior ULT prescription during 12 months before index date, and were required to have 12 months of continuous membership with drug benefit during pre-/post-index. Electronic chart notes were reviewed to identify gout flares; these reviews helped create a validated computer-based method to further identify patients with gout flares and were categorized into 0 gout flares, 1-2 gout flares, and ≥3 gout flares during the 12 months post-index period. Multivariable logistic regression was used to examine patient and clinical factors associated with gout flares during the 12-month follow-up period. There were 8905 patients identified as the final cohort and 68 % of these patients had one or more gout flares during the 12-month follow-up: 2797 patients (31 %) had 0 gout flares, 4836 (54 %) had 1-2 gout flares, and 1272 patients (14 %) had ≥3 gout flares. Using a multivariate regression analyses, factors independently associated with 1-2 gout flares and ≥3 gout flares versus no gout flares were similar, however, with slight differences, such as younger patients were more likely to have 1-2 gout flares and patients ≥65 years of age had ≥3 gout flares. Factors such as male gender, not attaining sUA goal, having ≥3 comorbidities, diuretics use, no changes in initial ULT dose, and not adhering to ULT all were associated with gout flares versus no gout flares. Using a new method to identify gout flares, we had the opportunity to compare our findings with the previous studies. Our study findings echo other previous studies where older patients, male, diuretics, having a greater number of comorbidities, and non-adherence are more likely to have more gout flares during the first year of newly initiating ULT. There is an unmet need for patients with gout to be educated and managed more closely, especially during the first year.

Automated identification of patients with pulmonary nodules in an integrated health system using administrative health plan data, radiology reports, and natural language processing.

INTRODUCTION: Lung nodules are commonly encountered in clinical practice, yet little is known about their management in community settings. An automated method for identifying patients with lung nodules would greatly facilitate research in this area. METHODS: Using members of a large, community-based health plan from 2006 to 2010, we developed a method to identify patients with lung nodules, by combining five diagnostic codes, four procedural codes, and a natural language processing algorithm that performed free text searches of radiology transcripts. An experienced pulmonologist reviewed a random sample of 116 radiology transcripts, providing a reference standard for the natural language processing algorithm. RESULTS: With the use of an automated method, we identified 7112 unique members as having one or more incident lung nodules. The mean age of the patients was 65 years (standard deviation 14 years). There were slightly more women (54%) than men, and Hispanics and non-whites comprised 45% of the lung nodule cohort. Thirty-six percent were never smokers whereas 11% were current smokers. Fourteen percent of the patients were subsequently diagnosed with lung cancer. The sensitivity and specificity of the natural language processing algorithm for identifying the presence of lung nodules were 96% and 86%, respectively, compared with clinician review. Among the true positive transcripts in the validation sample, only 35% were solitary and unaccompanied by one or more associated findings, and 56% measured 8 to 30 mm in diameter. CONCLUSIONS: A combination of diagnostic codes, procedural codes, and a natural language processing algorithm for free text searching of radiology reports can accurately and efficiently identify patients with incident lung nodules, many of whom are subsequently diagnosed with lung cancer.