Natural language processing to identify lupus nephritis phenotype in electronic health records.

BACKGROUND: Systemic lupus erythematosus (SLE) is a rare autoimmune disorder characterized by an unpredictable course of flares and remission with diverse manifestations. Lupus nephritis, one of the major disease manifestations of SLE for organ damage and mortality, is a key component of lupus classification criteria. Accurately identifying lupus nephritis in electronic health records (EHRs) would therefore benefit large cohort observational studies and clinical trials where characterization of the patient population is critical for recruitment, study design, and analysis. Lupus nephritis can be recognized through procedure codes and structured data, such as laboratory tests. However, other critical information documenting lupus nephritis, such as histologic reports from kidney biopsies and prior medical history narratives, require sophisticated text processing to mine information from pathology reports and clinical notes. In this study, we developed algorithms to identify lupus nephritis with and without natural language processing (NLP) using EHR data from the Northwestern Medicine Enterprise Data Warehouse (NMEDW). METHODS: We developed five algorithms: a rule-based algorithm using only structured data (baseline algorithm) and four algorithms using different NLP models. The first NLP model applied simple regular expression for keywords search combined with structured data. The other three NLP models were based on regularized logistic regression and used different sets of features including positive mention of concept unique identifiers (CUIs), number of appearances of CUIs, and a mixture of three components (i.e. a curated list of CUIs, regular expression concepts, structured data) respectively. The baseline algorithm and the best performing NLP algorithm were externally validated on a dataset from Vanderbilt University Medical Center (VUMC). RESULTS: Our best performing NLP model incorporated features from both structured data, regular expression concepts, and mapped concept unique identifiers (CUIs) and showed improved F measure in both the NMEDW (0.41 vs 0.79) and VUMC (0.52 vs 0.93) datasets compared to the baseline lupus nephritis algorithm. CONCLUSION: Our NLP MetaMap mixed model improved the F-measure greatly compared to the structured data only algorithm in both internal and external validation datasets. The NLP algorithms can serve as powerful tools to accurately identify lupus nephritis phenotype in EHR for clinical research and better targeted therapies.

Supermarket Proximity and Risk of Hypertension, Diabetes, and CKD: A Retrospective Cohort Study.

RATIONALE & OBJECTIVE: Living in environments with low access to food may increase the risk of chronic diseases. We investigated the association of household distance to the nearest supermarket (as a measure of food access) with the incidence of hypertension, diabetes, and chronic kidney disease (CKD) in a metropolitan area of the United States. STUDY DESIGN: Retrospective cohort study. SETTING & PARTICIPANTS: 777,994 individuals without hypertension, diabetes, or CKD at baseline within the HealthLNK Data Repository, which contains electronic health records from 7 health care institutions in Chicago, Illinois. EXPOSURE: Zip code-level average distance between households and nearest supermarket. OUTCOME: Incidence of hypertension, diabetes, and CKD based on presence of ICD-9 code and/or blood pressure≥140/90mm Hg, hemoglobin A1c≥6.5%, and eGFR<60mL/min/1.73m2, respectively. ANALYTICAL APPROACH: Average distance to nearest supermarket was aggregated from street-level metrics for 56 Chicagoland zip codes. The cumulative incidence of hypertension, diabetes, and CKD from 2007-2012 was calculated for each zip code in patients free of these diseases in 2006. Spatial analysis of food access and disease incidence was performed using bivariate local indicator of spatial association (BiLISA) maps and bivariate local Moran I statistics. The relationship between supermarket access and outcomes was analyzed using logistic regression. RESULTS: Of 777,994 participants, 408,608 developed hypertension, 51,380 developed diabetes, and 56,365 developed CKD. There was significant spatial overlap between average distance to supermarket and incidence of hypertension and diabetes but not CKD. Zip codes with large average supermarket distances and high incidence of hypertension and diabetes were clustered in southern and western neighborhoods. Models adjusted only for neighborhood factors (zip code-level racial composition, access to vehicles, median income) revealed significant associations between zip code-level average distance to supermarket and chronic disease incidence. Relative to tertile 1 (shortest distance), ORs in tertiles 2 and 3, respectively, were 1.27 (95% CI, 1.23-1.30) and 1.38 (95% CI, 1.33-1.43) for diabetes, 1.03 (95% CI, 1.02-1.05) and 1.04 (95% CI, 1.02-1.06) for hypertension, and 1.18 (95% CI, 1.15-1.21) and 1.33 (95% CI, 1.29-1.37) for CKD. Models adjusted for demographic factors and health insurance showed significant and positive association with greater odds of incident diabetes (tertile 2: 1.29 [95% CI, 1.26-1.33]; tertile 3: 1.35 [95% CI, 1.31-1.39]) but lesser odds of hypertension (tertile 2: 0.95 [95% CI, 0.94-0.97]; tertile 3: 0.91 [95% CI, 0.89-0.92]) and CKD (tertile 2: 0.80 [95% CI, 0.78-0.82]; tertile 3: 0.73 [95% CI, 0.72-0.76]). After adjusting for both neighborhood and individual covariates, supermarket distance remained significantly associated with greater odds of diabetes and lesser odds of hypertension, but there was no significant association with CKD. LIMITATIONS: Unmeasured neighborhood and social confounding variables, zip code-level analysis, and limited individual-level information. CONCLUSIONS: There are significant disparities in supermarket proximity and incidence of hypertension, diabetes, and CKD in Chicago, Illinois. The relationship between supermarket access and chronic disease is largely explained by individual- and neighborhood-level factors.

Under-specification as the source of ambiguity and vagueness in narrative phenotype algorithm definitions.

INTRODUCTION: Currently, one of the commonly used methods for disseminating electronic health record (EHR)-based phenotype algorithms is providing a narrative description of the algorithm logic, often accompanied by flowcharts. A challenge with this mode of dissemination is the potential for under-specification in the algorithm definition, which leads to ambiguity and vagueness. METHODS: This study examines incidents of under-specification that occurred during the implementation of 34 narrative phenotyping algorithms in the electronic Medical Record and Genomics (eMERGE) network. We reviewed the online communication history between algorithm developers and implementers within the Phenotype Knowledge Base (PheKB) platform, where questions could be raised and answered regarding the intended implementation of a phenotype algorithm. RESULTS: We developed a taxonomy of under-specification categories via an iterative review process between two groups of annotators. Under-specifications that lead to ambiguity and vagueness were consistently found across narrative phenotype algorithms developed by all involved eMERGE sites. DISCUSSION AND CONCLUSION: Our findings highlight that under-specification is an impediment to the accuracy and efficiency of the implementation of current narrative phenotyping algorithms, and we propose approaches for mitigating these issues and improved methods for disseminating EHR phenotyping algorithms.

Evaluation of structured data from electronic health records to identify clinical classification criteria attributes for systemic lupus erythematosus.

OBJECTIVE: Our objective was to develop algorithms to identify lupus clinical classification criteria attributes using structured data found in the electronic health record (EHR) and determine whether they could be used to describe a cohort of people with lupus and discriminate them from a defined healthy control cohort. METHODS: We created gold standard lupus and healthy patient cohorts that were fully adjudicated for the American College of Rheumatology (ACR), Systemic Lupus International Collaborating Clinics (SLICC) and European League Against Rheumatism/ACR (EULAR/ACR) classification criteria and had matched EHR data. We implemented rule-based algorithms using structured data within the EHR system for each attribute of the three classification criteria. Individual criteria attribute and classification criteria algorithms as a whole were assessed over our combined cohorts and the overall performance of the algorithms was measured through sensitivity and specificity. RESULTS: Individual classification criteria attributes had a wide range of sensitivities, 7% (oral ulcers) to 97% (haematological disorders) and specificities, 56% (haematological disorders) to 98% (photosensitivity), but all could be identified in EHR data. In general, algorithms based on laboratory results performed better than those primarily based on diagnosis codes. All three classification criteria systems effectively distinguished members of our case and control cohorts, but the SLICC criteria-based algorithm had the highest overall performance (76% sensitivity, 99% specificity). CONCLUSIONS: It is possible to characterise disease manifestations in people with lupus using classification criteria-based algorithms that assess structured EHR data. These algorithms may reduce chart review burden and are a foundation for identifying subpopulations of patients with lupus based on disease presentation to support precision medicine applications.

Assessing the Concordance of Clinical Classification Criteria for Lupus Between Electronic Health Records and a Physician Curated Registry.

We developed a computable phenotype for systemic lupus erythematosus (SLE) based on the Systemic Lupus International Collaborative Clinics clinical classification criteria set for SLE. We evaluated the phenotype over registry and EHR data for the same patient population to determine concordance of criteria detected in both datasets and to assess which types of structured data detected individual classification criteria. We identified a concordance of 68% between registry and EHR data relying solely on structured data.