Person:

Savova, Guergana

Objective: To optimally leverage the scalability and unique features of the electronic health records (EHR) for research that would ultimately improve patient care, we need to accurately identify patients and extract clinically meaningful measures. Using multiple sclerosis (MS) as a proof of principle, we showcased how to leverage routinely collected EHR data to identify patients with a complex neurological disorder and derive an important surrogate measure of disease severity heretofore only available in research settings. Methods: In a cross-sectional observational study, 5,495 MS patients were identified from the EHR systems of two major referral hospitals using an algorithm that includes codified and narrative information extracted using natural language processing. In the subset of patients who receive neurological care at a MS Center where disease measures have been collected, we used routinely collected EHR data to extract two aggregate indicators of MS severity of clinical relevance multiple sclerosis severity score (MSSS) and brain parenchymal fraction (BPF, a measure of whole brain volume). Results: The EHR algorithm that identifies MS patients has an area under the curve of 0.958, 83% sensitivity, 92% positive predictive value, and 89% negative predictive value when a 95% specificity threshold is used. The correlation between EHR-derived and true MSSS has a mean R2 = 0.38±0.05, and that between EHR-derived and true BPF has a mean R2 = 0.22±0.08. To illustrate its clinical relevance, derived MSSS captures the expected difference in disease severity between relapsing-remitting and progressive MS patients after adjusting for sex, age of symptom onset and disease duration (p = 1.56×10−12). Conclusion: Incorporation of sophisticated codified and narrative EHR data accurately identifies MS patients and provides estimation of a well-accepted indicator of MS severity that is widely used in research settings but not part of the routine medical records. Similar approaches could be applied to other complex neurological disorders.

Objective: We aimed to mine the data in the Electronic Medical Record to automatically discover patients' Rheumatoid Arthritis disease activity at discrete rheumatology clinic visits. We cast the problem as a document classification task where the feature space includes concepts from the clinical narrative and lab values as stored in the Electronic Medical Record. Materials and Methods The Training Set consisted of 2792 clinical notes and associated lab values. Test Set 1 included 1749 clinical notes and associated lab values. Test Set 2 included 344 clinical notes for which there were no associated lab values. The Apache clinical Text Analysis and Knowledge Extraction System was used to analyze the text and transform it into informative features to be combined with relevant lab values. Results: Experiments over a range of machine learning algorithms and features were conducted. The best performing combination was linear kernel Support Vector Machines with Unified Medical Language System Concept Unique Identifier features with feature selection and lab values. The Area Under the Receiver Operating Characteristic Curve (AUC) is 0.831 (σ = 0.0317), statistically significant as compared to two baselines (AUC = 0.758, σ = 0.0291). Algorithms demonstrated superior performance on cases clinically defined as extreme categories of disease activity (Remission and High) compared to those defined as intermediate categories (Moderate and Low) and included laboratory data on inflammatory markers. Conclusion: Automatic Rheumatoid Arthritis disease activity discovery from Electronic Medical Record data is a learnable task approximating human performance. As a result, this approach might have several research applications, such as the identification of patients for genome-wide pharmacogenetic studies that require large sample sizes with precise definitions of disease activity and response to therapies.

Background: Typically, algorithms to classify phenotypes using electronic medical record (EMR) data were developed to perform well in a specific patient population. There is increasing interest in analyses which can allow study of a specific outcome across different diseases. Such a study in the EMR would require an algorithm that can be applied across different patient populations. Our objectives were: (1) to develop an algorithm that would enable the study of coronary artery disease (CAD) across diverse patient populations; (2) to study the impact of adding narrative data extracted using natural language processing (NLP) in the algorithm. Additionally, we demonstrate how to implement CAD algorithm to compare risk across 3 chronic diseases in a preliminary study. Methods and Results: We studied 3 established EMR based patient cohorts: diabetes mellitus (DM, n = 65,099), inflammatory bowel disease (IBD, n = 10,974), and rheumatoid arthritis (RA, n = 4,453) from two large academic centers. We developed a CAD algorithm using NLP in addition to structured data (e.g. ICD9 codes) in the RA cohort and validated it in the DM and IBD cohorts. The CAD algorithm using NLP in addition to structured data achieved specificity >95% with a positive predictive value (PPV) 90% in the training (RA) and validation sets (IBD and DM). The addition of NLP data improved the sensitivity for all cohorts, classifying an additional 17% of CAD subjects in IBD and 10% in DM while maintaining PPV of 90%. The algorithm classified 16,488 DM (26.1%), 457 IBD (4.2%), and 245 RA (5.0%) with CAD. In a cross-sectional analysis, CAD risk was 63% lower in RA and 68% lower in IBD compared to DM (p<0.0001) after adjusting for traditional cardiovascular risk factors. Conclusions: We developed and validated a CAD algorithm that performed well across diverse patient populations. The addition of NLP into the CAD algorithm improved the sensitivity of the algorithm, particularly in cohorts where the prevalence of CAD was low. Preliminary data suggest that CAD risk was significantly lower in RA and IBD compared to DM.

Phenotypes are the foundation for clinical and genetic studies of disease risk and outcomes. The growth of biobanks linked to electronic medical record (EMR) data has both facilitated and increased the demand for efficient, accurate, and robust approaches for phenotyping millions of patients. Challenges to phenotyping using EMR data include variation in the accuracy of codes, as well as the high level of manual input required to identify features for the algorithm and to obtain gold standard labels. To address these challenges, we developed PheCAP, a high-throughput semi-supervised phenotyping pipeline. PheCAP begins with data from the EMR, including structured data and information extracted from the narrative notes using natural language processing (NLP). The standardized steps integrate automated procedures reducing the level of manual input, and machine learning approaches for algorithm training. PheCAP itself can be executed in 1-2 days if all data are available; however, the timing is largely dependent on the chart review step which typically requires at least 2 weeks. The final products of PheCAP include a phenotype algorithm, the probability of the phenotype for all patients, and a phenotype classification (yes/no).

Introduction Prior studies identifying patients with inflammatory bowel disease (IBD) utilizing administrative codes have yielded inconsistent results. Our objective was to develop a robust electronic medical record (EMR) based model for classification of IBD leveraging the combination of codified data and information from clinical text notes using natural language processing (NLP).

Methods Using the EMR of 2 large academic centers, we created data marts for Crohn’s disease (CD) and ulcerative colitis (UC) comprising patients with ≥ 1 ICD-9 code for each disease. We utilized codified (i.e. ICD9 codes, electronic prescriptions) and narrative data from clinical notes to develop our classification model. Model development and validation was performed in a training set of 600 randomly selected patients for each disease with medical record review as the gold standard. Logistic regression with the adaptive LASSO penalty was used to select informative variables.

Results We confirmed 399 (67%) CD cases in the CD training set and 378 (63%) UC cases in the UC training set. For both, a combined model including narrative and codified data had better accuracy (area under the curve (AUC) for CD 0.95; UC 0.94) than models utilizing only disease ICD-9 codes (AUC 0.89 for CD; 0.86 for UC). Addition of NLP narrative terms to our final model resulted in classification of 6–12% more subjects with the same accuracy.

Conclusion Inclusion of narrative concepts identified using NLP improves the accuracy of EMR case-definition for CD and UC while simultaneously identifying more subjects compared to models using codified data alone.

Introduction Vitamin D may have an immunological role in Crohn’s disease (CD) and ulcerative colitis (UC). Retrospective studies suggested a weak association between vitamin D status and disease activity but have significant limitations.

Methods Using a multi-institution inflammatory bowel disease (IBD) cohort, we identified all CD and UC patients who had at least one measured plasma 25-hydroxy vitamin D [25(OH)D]. Plasma 25(OH)D was considered sufficient at levels ≥ 30ng/mL. Logistic regression models adjusting for potential confounders were used to identify impact of measured plasma 25(OH)D on subsequent risk of IBD-related surgery or hospitalization. In a subset of patients where multiple measures of 25(OH)D were available, we examined impact of normalization of vitamin D status on study outcomes.

Results Our study included 3,217 patients (55% CD, mean age 49 yrs). The median lowest plasma 25(OH)D was 26ng/ml (IQR 17–35ng/ml). In CD, on multivariable analysis, plasma 25(OH)D < 20ng/ml was associated with an increased risk of surgery (OR 1.76 (1.24 – 2.51) and IBD-related hospitalization (OR 2.07, 95% CI 1.59 – 2.68) compared to those with 25(OH)D ≥ 30ng/ml. Similar estimates were also seen for UC. Furthermore, CD patients who had initial levels < 30ng/ml but subsequently normalized their 25(OH)D had a reduced likelihood of surgery (OR 0.56, 95% CI 0.32 – 0.98) compared to those who remained deficient.

Conclusion Low plasma 25(OH)D is associated with increased risk of surgery and hospitalizations in both CD and UC and normalization of 25(OH)D status is associated with a reduction in the risk of CD-related surgery.