Search

Objective In response to COVID-19, the informatics community united to aggregate as much clinical data as possible to characterize this new disease and reduce its impact through collaborative analytics. The National COVID Cohort Collaborative (N3C) is now the largest publicly available HIPAA limited dataset in US history with over 6.4 million patients and is a testament to a partnership of over 100 organizations. Materials and Methods We developed a pipeline for ingesting, harmonizing, and centralizing data from 56 contributing data partners using 4 federated Common Data Models. N3C data quality (DQ) review involves both automated and manual procedures. In the process, several DQ heuristics were discovered in our centralized context, both within the pipeline and during downstream project-based analysis. Feedback to the sites led to many local and centralized DQ improvements. Results Beyond well-recognized DQ findings, we discovered 15 heuristics relating to source Common Data Model conformance, demographics, COVID tests, conditions, encounters, measurements, observations, coding completeness, and fitness for use. Of 56 sites, 37 sites (66%) demonstrated issues through these heuristics. These 37 sites demonstrated improvement after receiving feedback. Discussion We encountered site-to-site differences in DQ which would have been challenging to discover using federated checks alone. We have demonstrated that centralized DQ benchmarking reveals unique opportunities for DQ improvement that will support improved research analytics locally and in aggregate. Conclusion By combining rapid, continual assessment of DQ with a large volume of multisite data, it is possible to support more nuanced scientific questions with the scale and rigor that they require.

Background Numerous publications describe the clinical manifestations of post-acute sequelae of SARS-CoV-2 (PASC or "long COVID"), but they are difficult to integrate because of heterogeneous methods and the lack of a standard for denoting the many phenotypic manifestations. Patient-led studies are of particular importance for understanding the natural history of COVID-19, but integration is hampered because they often use different terms to describe the same symptom or condition. This significant disparity in patient versus clinical characterization motivated the proposed ontological approach to specifying manifestations, which will improve capture and integration of future long COVID studies. Methods The Human Phenotype Ontology (HPO) is a widely used standard for exchange and analysis of phenotypic abnormalities in human disease but has not yet been applied to the analysis of COVID-19. Findings We identified 303 articles published before April 29, 2021, curated 59 relevant manuscripts that described clinical manifestations in 81 cohorts three weeks or more following acute COVID-19, and mapped 287 unique clinical findings to HPO terms. We present layperson synonyms and definitions that can be used to link patient self-report questionnaires to standard medical terminology. Long COVID clinical manifestations are not assessed consistently across studies, and most manifestations have been reported with a wide range of synonyms by different authors. Across at least 10 cohorts, authors reported 31 unique clinical features corresponding to HPO terms; the most commonly reported feature was Fatigue (median 45.1%) and the least commonly reported was Nausea (median 3.9%), but the reported percentages varied widely between studies. Interpretation Translating long COVID manifestations into computable HPO terms will improve analysis, data capture, and classification of long COVID patients. If researchers, clinicians, and patients share a common language, then studies can be compared/pooled more effectively. Furthermore, mapping lay terminology to HPO will help patients assist clinicians and researchers in creating phenotypic characterizations that are computationally accessible, thereby improving the stratification, diagnosis, and treatment of long COVID. Funding U24TR002306; UL1TR001439; P30AG024832; GBMF4552; R01HG010067; UL1TR002535; K23HL128909; UL1TR002389; K99GM145411 .

BackgroundPost-acute sequelae of SARS-CoV-2 infection (PASC), otherwise known as long-COVID, have severely impacted recovery from the pandemic for patients and society alike. This new disease is characterized by evolving, heterogeneous symptoms, making it challenging to derive an unambiguous long-COVID definition. Electronic health record (EHR) studies are a critical element of the NIH Researching COVID to Enhance Recovery (RECOVER) Initiative, which is addressing the urgent need to understand PASC, accurately identify who has PASC, and identify treatments.MethodsUsing the National COVID Cohort Collaborative’s (N3C) EHR repository, we developed XGBoost machine learning (ML) models to identify potential long-COVID patients. We examined demographics, healthcare utilization, diagnoses, and medications for 97,995 adult COVID-19 patients. We used these features and 597 long-COVID clinic patients to train three ML models to identify potential long-COVID patients among (1) all COVID-19 patients, (2) patients hospitalized with COVID-19, and (3) patients who had COVID-19 but were not hospitalized.FindingsOur models identified potential long-COVID patients with high accuracy, achieving areas under the receiver operator characteristic curve of 0.91 (all patients), 0.90 (hospitalized); and 0.85 (non-hospitalized). Important features include rate of healthcare utilization, patient age, dyspnea, and other diagnosis and medication information available within the EHR. Applying the “all patients” model to the larger N3C cohort identified 100,263 potential long-COVID patients.InterpretationPatients flagged by our models can be interpreted as “patients likely to be referred to or seek care at a long-COVID specialty clinic,” an essential proxy for long-COVID diagnosis in the current absence of a definition. We also achieve the urgent goal of identifying potential long-COVID patients for clinical trials. As more data sources are identified, the models can be retrained and tuned based on study needs.FundingThis study was funded by NCATS and NIH through the RECOVER Initiative.

ImportanceSARS-CoV-2ObjectiveTo determine the characteristics, changes over time, outcomes, and severity risk factors of SARS-CoV-2 affected children within the National COVID Cohort Collaborative (N3C)DesignProspective cohort study of patient encounters with end dates before May 27th, 2021.Setting45 N3C institutionsParticipantsChildren Main Outcomes and MeasuresCase incidence and severity over time, demographic and comorbidity severity risk factors, vital sign and laboratory trajectories, clinical outcomes, and acute COVID-19 vs MIS-C contrasts for children infected with SARS-CoV-2.Results728,047 children in the N3C were tested for SARS-CoV-2; of these, 91,865 (12.6%) were positive. Among the 5,213 (6%) hospitalized children, 685 (13%) met criteria for severe disease: mechanical ventilation (7%), vasopressor/inotropic support (7%), ECMO (0.6%), or death/discharge to hospice (1.1%). Male gender, African American race, older age, and several pediatric complex chronic condition (PCCC) subcategories were associated with higher clinical severity (p≤0.05). Vital signs (all p≤0.002) and many laboratory tests from the first day of hospitalization were predictive of peak disease severity. Children with severe (vs moderate) disease were more likely to receive antimicrobials (71% vs 32%, pCompared to those with acute COVID-19, children with MIS-C were more likely to be male, Black/African American, 1-to-12-years-old, and less likely to have asthma, diabetes, or a PCCC (p<0.04). MIS-C cases demonstrated a more inflammatory laboratory profile and more severe clinical phenotype with higher rates of invasive ventilation (12% vs 6%) and need for vasoactive-inotropic support (31% vs 6%) compared to acute COVID-19 cases, respectively (pConclusionsIn the largest U.S. SARS-CoV-2-positive pediatric cohort to date, we observed differences in demographics, pre-existing comorbidities, and initial vital sign and laboratory test values between severity subgroups. Taken together, these results suggest that early identification of children likely to progress to severe disease could be achieved using readily available data elements from the day of admission. Further work is needed to translate this knowledge into improved outcomes.

BackgroundThe majority of U.S. reports of COVID-19 clinical characteristics, disease course, and treatments are from single health systems or focused on one domain. Here we report the creation of the National COVID Cohort Collaborative (N3C), a centralized, harmonized, high-granularity electronic health record repository that is the largest, most representative U.S. cohort of COVID-19 cases and controls to date. This multi-center dataset supports robust evidence-based development of predictive and diagnostic tools and informs critical care and policy.Methods and FindingsIn a retrospective cohort study of 1,926,526 patients from 34 medical centers nationwide, we stratified patients using a World Health Organization COVID-19 severity scale and demographics; we then evaluated differences between groups over time using multivariable logistic regression. We established vital signs and laboratory values among COVID-19 patients with different severities, providing the foundation for predictive analytics. The cohort included 174,568 adults with severe acute respiratory syndrome associated with SARS-CoV-2 (PCR >99% or antigen ConclusionsThis is the first description of an ongoing longitudinal observational study of patients seen in diverse clinical settings and geographical regions and is the largest COVID-19 cohort in the United States. Such data are the foundation for ML models that can be the basis for generalizable clinical decision support tools. The N3C Data Enclave is unique in providing transparent, reproducible, easily shared, versioned, and fully auditable data and analytic provenance for national-scale patient-level EHR data. The N3C is built for intensive ML analyses by academic, industry, and citizen scientists internationally. Many observational correlations can inform trial designs and care guidelines for this new disease.

Presentation to the International Society of Environmental Epidemiology 2020 Virtual Meeting (ISEE) August 2020

Objective COVID-19 poses societal challenges that require expeditious data and knowledge sharing. Though organizational clinical data are abundant, these are largely inaccessible to outside researchers. Statistical, machine learning, and causal analyses are most successful with large-scale data beyond what is available in any given organization. Here, we introduce the National COVID Cohort Collaborative (N3C), an open science community focused on analyzing patient-level data from many centers. Methods The Clinical and Translational Science Award (CTSA) Program and scientific community created N3C to overcome technical, regulatory, policy, and governance barriers to sharing and harmonizing individual-level clinical data. We developed solutions to extract, aggregate, and harmonize data across organizations and data models, and created a secure data enclave to enable efficient, transparent, and reproducible collaborative analytics. Organized in inclusive workstreams, in two months we created: legal agreements and governance for organizations and researchers; data extraction scripts to identify and ingest positive, negative, and possible COVID-19 cases; a data quality assurance and harmonization pipeline to create a single harmonized dataset; population of the secure data enclave with data, machine learning, and statistical analytics tools; dissemination mechanisms; and a synthetic data pilot to democratize data access. Discussion The N3C has demonstrated that a multi-site collaborative learning health network can overcome barriers to rapidly build a scalable infrastructure incorporating multi-organizational clinical data for COVID-19 analytics. We expect this effort to save lives by enabling rapid collaboration among clinicians, researchers, and data scientists to identify treatments and specialized care and thereby reduce the immediate and long-term impacts of COVID-19. LAY SUMMARY COVID-19 poses societal challenges that require expeditious data and knowledge sharing. Though medical records are abundant, they are largely inaccessible to outside researchers. Statistical, machine learning, and causal research are most successful with large datasets beyond what is available in any given organization. Here, we introduce the National COVID Cohort Collaborative (N3C), an open science community focused on analyzing patient-level data from many clinical centers to reveal patterns in COVID-19 patients. To create N3C, the community had to overcome technical, regulatory, policy, and governance barriers to sharing patient-level clinical data. In less than 2 months, we developed solutions to acquire and harmonize data across organizations and created a secure data environment to enable transparent and reproducible collaborative research. We expect the N3C to help save lives by enabling collaboration among clinicians, researchers, and data scientists to identify treatments and specialized care needs and thereby reduce the immediate and long-term impacts of COVID-19.

Background Environmental health risks for individuals with heart failure ( HF ) have been inadequately studied, as these individuals are not well represented in traditional cohort studies. To address this we studied associations between long‐term air pollution exposure and mortality in HF patients. Methods and Results The study population was a hospital‐based cohort of individuals diagnosed with HF between July 1, 2004 and December 31, 2016 compiled using electronic health records. Individuals were followed from 1 year after initial diagnosis until death or the end of the observation period (December 31, 2016). We used Cox proportional hazards models to evaluate the association of annual average fine particulate matter ( PM 2.5 ) exposure at the time of initial HF diagnosis with all‐cause mortality, adjusted for age, race, sex, distance to the nearest air pollution monitor, and socioeconomic status indicators. Among 23 302 HF patients, a 1 μg/m 3 increase in annual average PM 2.5 was associated with an elevated risk of all‐cause mortality (hazard ratio 1.13; 95% CI, 1.10–1.15). As compared with people with exposures below the current national PM 2.5 exposure standard (12 μg/m 3 ), those with elevated exposures experienced 0.84 (95% CI, 0.73–0.95) years of life lost over a 5‐year period, an observation that persisted even for those residing in areas with PM 2.5 concentrations below current standards. Conclusions Residential exposure to elevated concentrations of PM 2.5 is a significant mortality risk factor for HF patients. Elevated PM 2.5 exposures result in substantial years of life lost even at concentrations below current national standards.

Highlights • U.S. diabetes surveillance based on surveys may not reliably distinguish by type. • We married surveys from adults with a gold standard diagnoses based on EHR data. • Our algorithm uses self-reported type and use of insulin to identify type. • Use of our algorithm with large federal health surveys may improve surveillance., Objectives Surveys for U.S. diabetes surveillance do not reliably distinguish between type 1 and type 2 diabetes, potentially obscuring trends in type 1 among adults. To validate survey-based algorithms for distinguishing diabetes type, we linked survey data collected from adult patients with diabetes to a gold standard diabetes type. Research design and methods We collected data through a telephone survey of 771 adults with diabetes receiving care in a large healthcare system in North Carolina. We tested 34 survey classification algorithms utilizing information on respondents’ report of physician-diagnosed diabetes type, age at onset, diabetes drug use, and body mass index. Algorithms were evaluated by calculating type 1 and type 2 sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) relative to a gold standard diagnosis of diabetes type determined through analysis of EHR data and endocrinologist review of selected cases. Results Algorithms based on self-reported type outperformed those based solely on other data elements. The top-performing algorithm classified as type 1 all respondents who reported type 1 and were prescribed insulin, as “other diabetes type” all respondents who reported “other,” and as type 2 the remaining respondents (type 1 sensitivity 91.6%, type 1 specificity 98.9%, type 1 PPV 82.5%, type 1 NPV 99.5%). This algorithm performed well in most demographic subpopulations. Conclusions The major federal health surveys should consider including self-reported diabetes type if they do not already, as the gains in the accuracy of typing are substantial compared to classifications based on other data elements. This study provides much-needed guidance on the accuracy of survey-based diabetes typing algorithms.

Electronic Health Record (EHR) systems typically define laboratory test results using the Laboratory Observation Identifier Names and Codes (LOINC) and can transmit them using Fast Healthcare Interoperability Resource (FHIR) standards. LOINC has not yet been semantically integrated with computational resources for phenotype analysis. Here, we provide a method for mapping LOINC-encoded laboratory test results transmitted in FHIR standards to Human Phenotype Ontology (HPO) terms. We annotated the medical implications of 2923 commonly used laboratory tests with HPO terms. Using these annotations, our software assesses laboratory test results and converts each result into an HPO term. We validated our approach with EHR data from 15,681 patients with respiratory complaints and identified known biomarkers for asthma. Finally, we provide a freely available SMART on FHIR application that can be used within EHR systems. Our approach allows readily available laboratory tests in EHR to be reused for deep phenotyping and exploits the hierarchical structure of HPO to integrate distinct tests that have comparable medical interpretations for association studies.

Objective Querying electronic health records (EHRs) to find patients meeting study criteria is an efficient method of identifying potential study participants. We aimed to measure the effectiveness of EHR-driven recruitment in the context of ADAPTABLE (Aspirin Dosing: A Patient-centric Trial Assessing Benefits and Long-Term Effectiveness)—a pragmatic trial aiming to recruit 15 000 patients. Materials and Methods We compared the participant yield of 4 recruitment methods: in-clinic recruitment by a research coordinator, letters, direct email, and patient portal messages. Taken together, the latter 2 methods comprised our EHR-driven electronic recruitment workflow. Results The electronic recruitment workflow sent electronic messages to 12 254 recipients; 13.5% of these recipients visited the study website, and 4.2% enrolled in the study. Letters were sent to 427 recipients; 5.6% visited the study website, and 3.3% enrolled in the study. Coordinators recruited 339 participants in clinic; 23.6% visited the study website, and 16.8% enrolled in the study. Five-hundred-nine of the 580 UNC enrollees (87.8%) were recruited using an electronic method. Discussion Electronic recruitment reached a wide net of patients, recruited many participants to the study, and resulted in a workflow that can be reused for future studies. In-clinic recruitment saw the highest yield, suggesting that a combination of recruitment methods may be the best approach. Future work should account for demographic skew that may result by recruiting from a pool of patient portal users. Conclusion The success of electronic recruitment for ADAPTABLE makes this workflow well worth incorporating into an overall recruitment strategy, particularly for a pragmatic trial.

ObjectiveThis study aimed to develop a novel, regulatory-compliant approach for openly exposing integrated clinical and environmental exposures data: the Integrated Clinical and Environmental Exposures Service (ICEES).Materials and MethodsThe driving clinical use case for research and development of ICEES was asthma, which is a common disease influenced by hundreds of genes and a plethora of environmental exposures, including exposures to airborne pollutants. We developed a pipeline for integrating clinical data on patients with asthma-like conditions with data on environmental exposures derived from multiple public data sources. The data were integrated at the patient and visit level and used to create de-identified, binned, “integrated feature tables,” which were then placed behind an OpenAPI.ResultsOur preliminary evaluation results demonstrate a relationship between exposure to high levels of particulate matter ≤2.5 µm in diameter (PM2.5) and the frequency of emergency department or inpatient visits for respiratory issues. For example, 16.73% of patients with average daily exposure to PM2.5 >9.62 µg/m3 experienced 2 or more emergency department or inpatient visits for respiratory issues in year 2010 compared with 7.93% of patients with lower exposures (n = 23 093).DiscussionThe results validated our overall approach for openly exposing and sharing integrated clinical and environmental exposures data. We plan to iteratively refine and expand ICEES by including additional years of data, feature variables, and disease cohorts.ConclusionsWe believe that ICEES will serve as a regulatory-compliant model and approach for promoting open access to and sharing of integrated clinical and environmental exposures data.

Red blood cell (RBC) alloimmunization is a significant clinical complication of sickle cell disease (SCD). It can lead to difficulty with cross-matching for future transfusions and may sometimes trigger life-threatening delayed hemolytic transfusion reactions. We conducted a retrospective study to explore the association of clinical complications and age of RBC with alloimmunization in patients with SCD followed at a single institution from 2005 to 2012. One hundred and sixty six patients with a total of 488 RBC transfusions were evaluated. Nineteen patients (11%) developed new alloantibodies following blood transfusions during the period of review. The median age of RBC units was 20 days (interquartile range: 14–27 days). RBC antibody formation was significantly associated with the age of RBC units (P = 0.002), with a hazard ratio of 3.5 (95% CI: 1.71–7.11) for a RBC unit that was 7 days old and 9.8 (95% CI: 2.66–35.97) for a unit that was 35 days old, 28 days after the blood transfusion. No association was observed between RBC alloimmunization and acute vaso-occlusive complications. Although increased echocardiography-derived tricuspid regurgitant jet velocity (TRV) was associated with the presence of RBC alloantibodies (P = 0.02), TRV was not significantly associated with alloimmunization when adjusted for patient age and number of transfused RBC units. Our study suggests that RBC antibody formation is significantly associated with older age of RBCs at the time of transfusion. Prospective studies in patients with SCD are required to confirm this finding. Am. J. Hematol. 90:691–695, 2015. © 2015 Wiley Periodicals, Inc.

Background: Medication nonadherence and misuse are public health and patient safety concerns. With the increased adoption of electronic health records (EHRs), greater opportunities exist to communicate directly with, and collect data from, patients through secure portals linked to EHRs. Objective: The study objectives were to develop and pilot test a method of monitoring patient medication use in outpatient settings and determine the feasibility and acceptability of this approach. Methods: Adult primary care patients on multidrug regimens were recruited from an academic internal medicine clinic by a trained research assistant. After completing a baseline, in-person interview, patients were sent a link to a questionnaire about medication use via the patient portal. One week later, the RA contacted patients to complete a follow-up telephone interview assessing patient satisfaction and experience with the questionnaire. Patient EHRs were also reviewed to determine the questionnaire completion rate. Results: Of 100 patients enrolled, 89 completed the follow-up interview and 82 completed the portal questionnaire. The mean age of the sample was 61.8 (range 31-88) years. Approximately half (54/100, 54%) of the sample was male, two-thirds were white (67/100, 67%) and 26% (26/100) African-American. A total of 44% reported an annual household income of

The use of administrative databases to conduct population-based studies of eosinophilic esophagitis (EoE) in the United States is limited because it is unknown whether the International Classification of Diseases, Ninth Revision (ICD-9) code for EoE, 530.13, accurately identifies those who truly have the disease. The aim of this retrospective study was to validate the ICD-9 code for identifying cases of EoE in administrative data. Confirmed cases of EoE as per consensus guidelines (symptoms of esophageal dysfunction and ≥15 eosinophils per high-power field on biopsy after 8 weeks of twice daily proton pump inhibitor therapy) were identified in the University of North Carolina (UNC) EoE Clinicopathologic Database from 2008 to 2010; 2008 was the first year in which the 530.13 code was approved. Using the Carolina Data Warehouse, the administrative database for patients seen in the UNC system, all diagnostic and procedure codes were obtained for these cases. Then, with the EoE cases as the reference standard, we re-queried the Carolina Data Warehouse over the same time frame for all patients seen in the system (n=308,372) and calculated the sensitivity and specificity of the ICD-9 code 530.13 as a case definition of EoE. To attempt to refine the case definition, we added procedural codes in an iterative fashion to optimize sensitivity and specificity, and restricted our analysis to privately insured patients. We also conducted a sensitivity analysis with 2011 data to identify trends in the operating parameters of the code. We identified 226 cases of EoE at UNC to serve as the reference standard. The ICD-9 code 530.13 yielded a sensitivity of 37% (83/226; 95% confidence interval: 31-43%) and specificity of 99% (308,111/308,146; 95% confidence interval: 98-100%). These operating parameters were not substantially altered if the case definition required a procedure code for endoscopy or if cases were limited to those with commercial insurance. However, in 2011, the sensitivity of the code had increased to 61%, while the specificity remained at 99%. The ICD-9 code for EoE, 530.13, had excellent specificity for identifying cases of EoE in administrative data, although this high specificity was achieved at an academic center. Additionally, the sensitivity of the code appears to be increasing over time, and the threshold at which it will stabilize is not known. While use of this administrative code will still miss a number of cases, those identified in this manner are highly likely to have the disease.

We aimed to develop an efficient surveillance approach for childhood diabetes. We analyzed EHR data from two independent US academic health care systems. Presumptive diabetes cases were identified as those having >1 of the five diabetes indicators in the past 3.5 years. EHRs of the presumptive cases were manually reviewed. We developed a stepwise surveillance approach using billing codes-based pre-specified algorithms and targeted manual EHRs review. The sensitivity and positive predictive value in both systems were approximately >90%. This stepwise surveillance approach resulted in a >70% reduction in the number of cases requiring manual validation compared to traditional surveillance methods.

Objective To develop an efficient surveillance approach for childhood diabetes by type across 2 large US health care systems, using phenotyping algorithms derived from electronic health record (EHR) data. Materials and Methods Presumptive diabetes cases Results We developed a stepwise surveillance approach using billing code–based prespecified algorithms and targeted manual EHR review, which efficiently and accurately ascertained and classified diabetes cases by type, in both health care systems. The sensitivity and positive predictive values in both systems were approximately ≥90% for ascertaining diabetes cases overall and classifying cases with type 1 or type 2 diabetes. About 80% of the cases with “other” type were also correctly classified. This stepwise surveillance approach resulted in a >70% reduction in the number of cases requiring manual validation compared to traditional surveillance methods. Conclusion EHR data may be used to establish an efficient approach for large-scale surveillance for childhood diabetes by type, although some manual effort is still needed.

Ongoing surveillance of childhood diabetes in the U.S. is needed to understand the trends in incidence and prevalence, and to anticipate health care delivery needs. The SEARCH for Diabetes in Youth Study (SEARCH) (1) documented an increase in the prevalence of type 1 and type 2 diabetes from 2001 to 2009 (2, 3). From 2010 to 2050, the number of youth with type 1 and type 2 diabetes is projected to increase by another 23% and 49%, respectively, even assuming no change in incidence since 2002 (4). Surveillance of childhood diabetes is challenging. First, we are unable to employ existing national surveillance systems such as the National Health and Nutrition Examination Survey (NHANES) because childhood diabetes is uncommon; NHANES (1999-2002) yielded only18 self-reported cases of diabetes among youth aged 12 to 19 years (5). Second, ascertainment of childhood diabetes cases is often costly in terms of time and financial resources. Currently the SEARCH study conducts validation of potential cases by manual review of medical records which is expensive, although the resulting case ascertainment is estimated to be very complete (i.e., >90% for both prevalent and incident cases) based on capture-recapture analyses (6). Third, a useful childhood diabetes surveillance system should be able to discriminate between types of diabetes in different age, and racial/ethnic groups as the distribution of childhood diabetes varies by type, age and race/ethnicity (7, 8); and both etiology and treatment differ by diabetes type (7, 9-11). The increasing utilization of computerized medical information systems may provide timely data for diabetes surveillance with substantially reduced cost relative to traditional approaches (12-14). Approaches to identify diabetes cases and classify type have been explored using administrative data (15-22), and electronic health record (EHR) data (23-26). Among all childhood diabetes algorithms in the literature, only two explored type-specific algorithms (21, 23). None of these studies evaluated algorithm performance according to age and race/ethnicity. In the U.S., it is not known whether administrative and EHR data from a large academic care delivery system can be used to accurately differentiate between childhood type 1 and type 2 diabetes (i.e., through use of type-sensitive algorithms) or whether such data can only identify cases without regard to type (i.e., through use of type-insensitive algorithms). It is also not known whether the performance of automated algorithms differs by age and race/ethnicity. Our objective was to identify algorithms with high performance, as demonstrated by high sensitivity, specificity, and positive predictive value (PPV), with a goal to efficiently identify diabetes cases and classify type in youth, overall and by age and race/ethnicity in a large academic care delivery system caring for patients with all payment sources, utilizing administrative and EHR data from the University of North Carolina Health Care System (UNCHCS).