Modular design, application architecture, and usage of a self-service model for enterprise data delivery: the Duke Enterprise Data Unified Content Explorer (DEDUCE).

PURPOSE: Data generated in the care of patients are widely used to support clinical research and quality improvement, which has hastened the development of self-service query tools. User interface design for such tools, execution of query activity, and underlying application architecture have not been widely reported, and existing tools reflect a wide heterogeneity of methods and technical frameworks. We describe the design, application architecture, and use of a self-service model for enterprise data delivery within Duke Medicine. METHODS: Our query platform, the Duke Enterprise Data Unified Content Explorer (DEDUCE), supports enhanced data exploration, cohort identification, and data extraction from our enterprise data warehouse (EDW) using a series of modular environments that interact with a central keystone module, Cohort Manager (CM). A data-driven application architecture is implemented through three components: an application data dictionary, the concept of "smart dimensions", and dynamically-generated user interfaces. RESULTS: DEDUCE CM allows flexible hierarchies of EDW queries within a grid-like workspace. A cohort "join" functionality allows switching between filters based on criteria occurring within or across patient encounters. To date, 674 users have been trained and activated in DEDUCE, and logon activity shows a steady increase, with variability between months. A comparison of filter conditions and export criteria shows that these activities have different patterns of usage across subject areas. CONCLUSIONS: Organizations with sophisticated EDWs may find that users benefit from development of advanced query functionality, complimentary to the user interfaces and infrastructure used in other well-published models. Driven by its EDW context, the DEDUCE application architecture was also designed to be responsive to source data and to allow modification through alterations in metadata rather than programming, allowing an agile response to source system changes.

Use of Natural Language Processing to Improve Identification of Patients With Peripheral Artery Disease.

BACKGROUND: Peripheral artery disease (PAD) is underrecognized, undertreated, and understudied: each of these endeavors requires efficient and accurate identification of patients with PAD. Currently, PAD patient identification relies on diagnosis/procedure codes or lists of patients diagnosed or treated by specific providers in specific locations and ways. The goal of this research was to leverage natural language processing to more accurately identify patients with PAD in an electronic health record system compared with a structured data-based approach. METHODS: The clinical notes from a cohort of 6861 patients in our health system whose PAD status had previously been adjudicated were used to train, test, and validate a natural language processing model using 10-fold cross-validation. The performance of this model was described using the area under the receiver operating characteristic and average precision curves; its performance was quantitatively compared with an administrative data-based least absolute shrinkage and selection operator (LASSO) approach using the DeLong test. RESULTS: The median (SD) of the area under the receiver operating characteristic curve for the natural language processing model was 0.888 (0.009) versus 0.801 (0.017) for the LASSO-based approach alone (DeLong P<0.0001). The median (SD) of the area under the precision curve was 0.909 (0.008) versus 0.816 (0.012) for the structured data-based approach. When sensitivity was set at 90%, the precision for LASSO was 65% and the machine learning approach was 74%, while the specificity for LASSO was 41% and for the machine learning approach was 62%. CONCLUSIONS: Using a natural language processing approach in addition to partial cohort preprocessing with a LASSO-based model, we were able to meaningfully improve our ability to identify patients with PAD compared with an approach using structured data alone. This model has potential applications to both interventions targeted at improving patient care as well as efficient, large-scale PAD research. Graphic Abstract: A graphic abstract is available for this article.

Health system utilization before age 1 among children later diagnosed with autism or ADHD.

Children with autism spectrum disorder (ASD) or attention deficit hyperactivity disorder (ADHD) have 2-3 times increased healthcare utilization and annual costs once diagnosed, but little is known about their utilization patterns early in life. Quantifying their early health system utilization could uncover condition-specific health trajectories to facilitate earlier detection and intervention. Patients born 10/1/2006-10/1/2016 with ≥ 2 well-child visits within the Duke University Health System before age 1 were grouped as ASD, ADHD, ASD + ADHD, or No Diagnosis using retrospective billing codes. An additional comparison group was defined by later upper respiratory infection diagnosis. Adjusted odds ratios (AOR) for hospital admissions, procedures, emergency department (ED) visits, and outpatient clinic encounters before age 1 were compared between groups via logistic regression models. Length of hospital encounters were compared between groups via Mann-Whitney U test. In total, 29,929 patients met study criteria (ASD N = 343; ADHD N = 1175; ASD + ADHD N = 140). ASD was associated with increased procedures (AOR = 1.5, p < 0.001), including intubation and ventilation (AOR = 2.4, p < 0.001); and outpatient specialty care, including physical therapy (AOR = 3.5, p < 0.001) and ophthalmology (AOR = 3.1, p < 0.001). ADHD was associated with increased procedures (AOR = 1.41, p < 0.001), including blood transfusion (AOR = 4.7, p < 0.001); hospital admission (AOR = 1.60, p < 0.001); and ED visits (AOR = 1.58, p < 0.001). Median length of stay was increased after birth in ASD (+ 6.5 h, p < 0.001) and ADHD (+ 3.8 h, p < 0.001), and after non-birth admission in ADHD (+ 1.1 d, p < 0.001) and ASD + ADHD (+ 2.4 d, p = 0.003). Each condition was associated with increased health system utilization and distinctive patterns of utilization before age 1. Recognizing these patterns may contribute to earlier detection and intervention.

Assessing electronic health record phenotypes against gold-standard diagnostic criteria for diabetes mellitus.

OBJECTIVE: We assessed the sensitivity and specificity of 8 electronic health record (EHR)-based phenotypes for diabetes mellitus against gold-standard American Diabetes Association (ADA) diagnostic criteria via chart review by clinical experts. MATERIALS AND METHODS: We identified EHR-based diabetes phenotype definitions that were developed for various purposes by a variety of users, including academic medical centers, Medicare, the New York City Health Department, and pharmacy benefit managers. We applied these definitions to a sample of 173 503 patients with records in the Duke Health System Enterprise Data Warehouse and at least 1 visit over a 5-year period (2007-2011). Of these patients, 22 679 (13%) met the criteria of 1 or more of the selected diabetes phenotype definitions. A statistically balanced sample of these patients was selected for chart review by clinical experts to determine the presence or absence of type 2 diabetes in the sample. RESULTS: The sensitivity (62-94%) and specificity (95-99%) of EHR-based type 2 diabetes phenotypes (compared with the gold standard ADA criteria via chart review) varied depending on the component criteria and timing of observations and measurements. DISCUSSION AND CONCLUSIONS: Researchers using EHR-based phenotype definitions should clearly specify the characteristics that comprise the definition, variations of ADA criteria, and how different phenotype definitions and components impact the patient populations retrieved and the intended application. Careful attention to phenotype definitions is critical if the promise of leveraging EHR data to improve individual and population health is to be fulfilled.

Using electronic health record data for substance use Screening, Brief Intervention, and Referral to Treatment among adults with type 2 diabetes: Design of a National Drug Abuse Treatment Clinical Trials Network study.

BACKGROUND: The Affordable Care Act encourages healthcare systems to integrate behavioral and medical healthcare, as well as to employ electronic health records (EHRs) for health information exchange and quality improvement. Pragmatic research paradigms that employ EHRs in research are needed to produce clinical evidence in real-world medical settings for informing learning healthcare systems. Adults with comorbid diabetes and substance use disorders (SUDs) tend to use costly inpatient treatments; however, there is a lack of empirical data on implementing behavioral healthcare to reduce health risk in adults with high-risk diabetes. Given the complexity of high-risk patients' medical problems and the cost of conducting randomized trials, a feasibility project is warranted to guide practical study designs. METHODS: We describe the study design, which explores the feasibility of implementing substance use Screening, Brief Intervention, and Referral to Treatment (SBIRT) among adults with high-risk type 2 diabetes mellitus (T2DM) within a home-based primary care setting. Our study includes the development of an integrated EHR datamart to identify eligible patients and collect diabetes healthcare data, and the use of a geographic health information system to understand the social context in patients' communities. Analysis will examine recruitment, proportion of patients receiving brief intervention and/or referrals, substance use, SUD treatment use, diabetes outcomes, and retention. DISCUSSION: By capitalizing on an existing T2DM project that uses home-based primary care, our study results will provide timely clinical information to inform the designs and implementation of future SBIRT studies among adults with multiple medical conditions.

Prevalence and Access of Secondary Source Medication Data: Evaluation of the Southeastern Diabetes Initiative (SEDI).

Medication non-adherence is a major public health issue, and measuring non-adherence is a crucial step toward improving it. A paucity of retrievable data prevents researchers from effectively measuring, tracking and sharing outcomes on medication management. High quality data derived from prescribing patterns, including behavioral and technology-based interventions, is necessary to support meaningful use, improve publicly reported quality metrics, and develop strategies to improve medication management. Electronic health records make medication data more numerous and accessible, yet the reliability and utility of electronically available data elements that reflect adherence has not been well established. We sought to explore the types of medication-related data captured over time in a series of patient encounters (n=5500) in a population-based intervention in four U.S. counties in the SouthEastern Diabetes Initiative (SEDI). The purpose was to evaluate data generated through routine healthcare delivery that are repurposed (ie, "secondary use") for research/QI/population health.

Substance use and mental diagnoses among adults with and without type 2 diabetes: Results from electronic health records data.

BACKGROUND: Comorbid diabetes and substance use diagnoses (SUD) represent a hazardous combination, both in terms of healthcare cost and morbidity. To date, there is limited information about the association of SUD and related mental disorders with type 2 diabetes mellitus (T2DM). METHODS: We examined the associations between T2DM and multiple psychiatric diagnosis categories, with a focus on SUD and related psychiatric comorbidities among adults with T2DM. We analyzed electronic health record (EHR) data on 170,853 unique adults aged ≥18 years from the EHR warehouse of a large academic healthcare system. Logistic regression analyses were conducted to estimate the strength of an association for comorbidities. RESULTS: Overall, 9% of adults (n=16,243) had T2DM. Blacks, Hispanics, Asians, and Native Americans had greater odds of having T2DM than whites. All 10 psychiatric diagnosis categories were more prevalent among adults with T2DM than among those without T2DM. Prevalent diagnoses among adults with T2MD were mood (21.22%), SUD (17.02%: tobacco 13.25%, alcohol 4.00%, drugs 4.22%), and anxiety diagnoses (13.98%). Among adults with T2DM, SUD was positively associated with mood, anxiety, personality, somatic, and schizophrenia diagnoses. CONCLUSIONS: We examined a large diverse sample of individuals and found clinical evidence of SUD and psychiatric comorbidities among adults with T2DM. These results highlight the need to identify feasible collaborative care models for adults with T2DM and SUD related psychiatric comorbidities, particularly in primary care settings, that will improve behavioral health and reduce health risk.

DEDUCE Clinical Text: An Ontology-based Module to Support Self-Service Clinical Notes Exploration and Cohort Development.

Large amounts of information, as well as opportunities for informing research, education, and operations, are contained within clinical text such as radiology reports and pathology reports. However, this content is less accessible and harder to leverage than structured, discrete data. We report on an extension to the Duke Enterprise Data Unified Content Explorer (DEDUCE), a self-service query tool developed to provide clinicians and researchers with access to data within the Duke Medicine Enterprise Data Warehouse (EDW). The DEDUCE Clinical Text module supports ontology-based text searching, enhanced filtering capabilities based on document attributes, and integration of clinical text with structured data and cohort development. The module is implemented with open-source tools extensible to other institutions, including a Java-based search engine (Apache Solr) with complementary full-text indexing library (Lucene) employed with a negation engine (NegEx) modified by clinical users to include to local domain-specific negation phrases.

Framework for Curating and Applying Data Elements within Continuing Use Data: A Case Study from the Durham Diabetes Coalition.

Data within a continuing use context (also known as secondary use) can require translation into the variables necessary for project analysis. We have developed and applied a framework in which: Project objectives inform the curation of data elements. Data elements are rendered into system-readable metadata. Metadata are applied to the source data and used to produce data sets. This process distinguishes between data sets and source data. Data sets contain project-specific variables that are structured for analytic activities. This can differ from source data, which may be stored in a structure dictated by the original source system for data collection, or in a data structure contrary to what is desired for analysis. Data elements mediate this translation, and the process of curation refines their definitions and associated attributes. This framework improves analysis workflow through the application of best practices, consistent processes, and centralized decision-making.

Missing signposts on the roadmap to quality: a call to improve medication adherence indicators in data collection for population research.

PURPOSE: Poor adherence to prescribed medicines is associated with increased rates of poor outcomes, including hospitalization, serious adverse events, and death, and is also associated with increased healthcare costs. However, current approaches to evaluation of medication adherence using real-world electronic health records (EHRs) or claims data may miss critical opportunities for data capture and fall short in modeling and representing the full complexity of the healthcare environment. We sought to explore a framework for understanding and improving data capture for medication adherence in a population-based intervention in four U.S. counties. APPROACH: We posited that application of a data model and a process matrix when designing data collection for medication adherence would improve identification of variables and data accessibility, and could support future research on medication-taking behaviors. We then constructed a use case in which data related to medication adherence would be leveraged to support improved healthcare quality, clinical outcomes, and efficiency of healthcare delivery in a population-based intervention for persons with diabetes. Because EHRs in use at participating sites were deemed incapable of supplying the needed data, we applied a taxonomic approach to identify and define variables of interest. We then applied a process matrix methodology, in which we identified key research goals and chose optimal data domains and their respective data elements, to instantiate the resulting data model. CONCLUSIONS: Combining a taxonomic approach with a process matrix methodology may afford significant benefits when designing data collection for clinical and population-based research in the arena of medication adherence. Such an approach can effectively depict complex real-world concepts and domains by "mapping" the relationships between disparate contributors to medication adherence and describing their relative contributions to the shared goals of improved healthcare quality, outcomes, and cost.

A comparison of phenotype definitions for diabetes mellitus.

OBJECTIVE: This study compares the yield and characteristics of diabetes cohorts identified using heterogeneous phenotype definitions. MATERIALS AND METHODS: Inclusion criteria from seven diabetes phenotype definitions were translated into query algorithms and applied to a population (n=173 503) of adult patients from Duke University Health System. The numbers of patients meeting criteria for each definition and component (diagnosis, diabetes-associated medications, and laboratory results) were compared. RESULTS: Three phenotype definitions based heavily on ICD-9-CM codes identified 9-11% of the patient population. A broad definition for the Durham Diabetes Coalition included additional criteria and identified 13%. The electronic medical records and genomics, NYC A1c Registry, and diabetes-associated medications definitions, which have restricted or no ICD-9-CM criteria, identified the smallest proportions of patients (7%). The demographic characteristics for all seven phenotype definitions were similar (56-57% women, mean age range 56-57 years).The NYC A1c Registry definition had higher average patient encounters (54) than the other definitions (range 44-48) and the reference population (20) over the 5-year observation period. The concordance between populations returned by different phenotype definitions ranged from 50 to 86%. Overall, more patients met ICD-9-CM and laboratory criteria than medication criteria, but the number of patients that met abnormal laboratory criteria exclusively was greater than the numbers meeting diagnostic or medication data exclusively. DISCUSSION: Differences across phenotype definitions can potentially affect their application in healthcare organizations and the subsequent interpretation of data. CONCLUSIONS: Further research focused on defining the clinical characteristics of standard diabetes cohorts is important to identify appropriate phenotype definitions for health, policy, and research.

Electronic health records based phenotyping in next-generation clinical trials: a perspective from the NIH Health Care Systems Collaboratory.

Widespread sharing of data from electronic health records and patient-reported outcomes can strengthen the national capacity for conducting cost-effective clinical trials and allow research to be embedded within routine care delivery. While pragmatic clinical trials (PCTs) have been performed for decades, they now can draw on rich sources of clinical and operational data that are continuously fed back to inform research and practice. The Health Care Systems Collaboratory program, initiated by the NIH Common Fund in 2012, engages healthcare systems as partners in discussing and promoting activities, tools, and strategies for supporting active participation in PCTs. The NIH Collaboratory consists of seven demonstration projects, and seven problem-specific working group 'Cores', aimed at leveraging the data captured in heterogeneous 'real-world' environments for research, thereby improving the efficiency, relevance, and generalizability of trials. Here, we introduce the Collaboratory, focusing on its Phenotype, Data Standards, and Data Quality Core, and present early observations from researchers implementing PCTs within large healthcare systems. We also identify gaps in knowledge and present an informatics research agenda that includes identifying methods for the definition and appropriate application of phenotypes in diverse healthcare settings, and methods for validating both the definition and execution of electronic health records based phenotypes.