Search

Objectives: Heart failure (HF) impacts millions of patients worldwide, yet the variability in treatment responses remains a major challenge for healthcare professionals. The current treatment strategies, largely derived from population based evidence, often fail to consider the unique characteristics of individual patients, resulting in suboptimal outcomes. This study aims to develop computational models that are patient-specific in predicting treatment outcomes, by utilizing a large Electronic Health Records (EHR) database. The goal is to improve drug response predictions by identifying specific HF patient subgroups that are likely to benefit from existing HF medications., Materials and Methods: A novel, graph-based model capable of predicting treatment responses, combining Graph Neural Network and Transformer was developed. This method differs from conventional approaches by transforming a patient's EHR data into a graph structure. By defining patient subgroups based on this representation via K-Means Clustering, we were able to enhance the performance of drug response predictions., Results: Leveraging EHR data from 11 627 Mayo Clinic HF patients, our model significantly outperformed traditional models in predicting drug response using NT-proBNP as a HF biomarker across five medication categories (best RMSE of 0.0043). Four distinct patient subgroups were identified with differential characteristics and outcomes, demonstrating superior predictive capabilities over existing HF subtypes (best mean RMSE of 0.0032)., Discussion: These results highlight the power of graph-based modeling of EHR in improving HF treatment strategies. The stratification of patients sheds light on particular patient segments that could benefit more significantly from tailored response predictions., Conclusions: Longitudinal EHR data have the potential to enhance personalized prognostic predictions through the application of graph-based AI techniques., (© The Author(s) 2024. Published by Oxford University Press on behalf of the American Medical Informatics Association. All rights reserved. For permissions, please email: journals.permissions@oup.com.)

Background: The incorporation of information from clinical narratives is critical for computational phenotyping. The accurate interpretation of clinical terms highly depends on their associated context, especially the corresponding clinical section information. However, the heterogeneity across different Electronic Health Record (EHR) systems poses challenges in utilizing the section information., Objectives: Leveraging the eMERGE heart failure (HF) phenotyping algorithm, we assessed the heterogeneity quantitatively through the performance comparison of machine learning (ML) classifiers which map clinical sections containing HF-relevant terms across different EHR systems to standard sections in Health Level 7 (HL7) Clinical Document Architecture (CDA)., Methods: We experimented with both random forest models with sentence-embedding features and bidirectional encoder representations from transformers models. We trained MLs using an automated labeled corpus from an EHR system that adopted HL7 CDA standard. We assessed the performance using a blind test set (n = 300) from the same EHR system and a gold standard (n = 900) manually annotated from three other EHR systems., Results: The F-measure of those ML models varied widely (0.00-0.91%), indicating MLs with one tuning parameter set were insufficient to capture sections across different EHR systems. The error analysis indicates that the section does not always comply with the corresponding standardized sections, leading to low performance., Conclusions: We presented the potential use of ML techniques to map the sections containing HF-relevant terms in multiple EHR systems to standard sections. However, the findings suggested that the quality and heterogeneity of section structure across different EHRs affect applications due to the poor adoption of documentation standards., Competing Interests: The authors have declared that no competing interests exist., (Copyright: © 2023 Moon et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.)

Background: Electronic health records (EHRs) are a rich source of longitudinal patient data. However, missing information due to clinical care that predated the implementation of EHR system(s) or care that occurred at different medical institutions impedes complete ascertainment of a patient's medical history., Objective: This study aimed to investigate information discrepancies and to quantify information gaps by comparing the gynecological surgical history extracted from an EHR of a single institution by using natural language processing (NLP) techniques with the manually curated surgical history information through chart review of records from multiple independent regional health care institutions., Methods: To facilitate high-throughput evaluation, we developed a rule-based NLP algorithm to detect gynecological surgery history from the unstructured narrative of the Mayo Clinic EHR. These results were compared to a gold standard cohort of 3870 women with gynecological surgery status adjudicated using the Rochester Epidemiology Project medical records-linkage system. We quantified and characterized the information gaps observed that led to misclassification of the surgical status., Results: The NLP algorithm achieved precision of 0.85, recall of 0.82, and F1-score of 0.83 in the test set (n=265) relative to outcomes abstracted from the Mayo EHR. This performance attenuated when directly compared to the gold standard (precision 0.79, recall 0.76, and F1-score 0.76), with the majority of misclassifications being false negatives in nature. We then applied the algorithm to the remaining patients (n=3340) and identified 2 types of information gaps through error analysis. First, 6% (199/3340) of women in this study had no recorded surgery information or partial information in the EHR. Second, 4.3% (144/3340) of women had inconsistent or inaccurate information within the clinical narrative owing to misinterpreted information, erroneous "copy and paste," or incorrect information provided by patients. Additionally, the NLP algorithm misclassified the surgery status of 3.6% (121/3340) of women., Conclusions: Although NLP techniques were able to adequately recreate the gynecologic surgical status from the clinical narrative, missing or inaccurately reported and recorded information resulted in much of the misclassification observed. Therefore, alternative approaches to collect or curate surgical history are needed., (©Sungrim Moon, Luke A Carlson, Ethan D Moser, Bhavani Singh Agnikula Kshatriya, Carin Y Smith, Walter A Rocca, Liliana Gazzuola Rocca, Suzette J Bielinski, Hongfang Liu, Nicholas B Larson. Originally published in the Journal of Medical Internet Research (https://www.jmir.org), 28.01.2022.)

Purpose: The depth and breadth of clinical data within electronic health record (EHR) systems paired with innovative machine learning methods can be leveraged to identify novel risk factors for complex diseases. However, analysing the EHR is challenging due to complexity and quality of the data. Therefore, we developed large electronic population-based cohorts with comprehensive harmonised and processed EHR data., Participants: All individuals 30 years of age or older who resided in Olmsted County, Minnesota on 1 January 2006 were identified for the discovery cohort. Algorithms to define a variety of patient characteristics were developed and validated, thus building a comprehensive risk profile for each patient. Patients are followed for incident diseases and ageing-related outcomes. Using the same methods, an independent validation cohort was assembled by identifying all individuals 30 years of age or older who resided in the largely rural 26-county area of southern Minnesota and western Wisconsin on 1 January 2013., Findings to Date: For the discovery cohort, 76 255 individuals (median age 49; 53% women) were identified from which a total of 9 644 221 laboratory results; 9 513 840 diagnosis codes; 10 924 291 procedure codes; 1 277 231 outpatient drug prescriptions; 966 136 heart rate measurements and 1 159 836 blood pressure (BP) measurements were retrieved during the baseline time period. The most prevalent conditions in this cohort were hyperlipidaemia, hypertension and arthritis. For the validation cohort, 333 460 individuals (median age 54; 52% women) were identified and to date, a total of 19 926 750 diagnosis codes, 10 527 444 heart rate measurements and 7 356 344 BP measurements were retrieved during baseline., Future Plans: Using advanced machine learning approaches, these electronic cohorts will be used to identify novel sex-specific risk factors for complex diseases. These approaches will allow us to address several challenges with the use of EHR., Competing Interests: Competing interests: None declared., (© Author(s) (or their employer(s)) 2021. Re-use permitted under CC BY-NC. No commercial re-use. See rights and permissions. Published by BMJ.)

Pharmacogenomics (PGx) clinical decision support integrated into the electronic health record (EHR) has the potential to provide relevant knowledge to clinicians to enable individualized care. However, past experience implementing PGx clinical decision support into multiple EHR platforms has identified important clinical, procedural, and technical challenges. Commercial EHRs have been widely criticized for the lack of readiness to implement precision medicine. Herein, we share our experiences and lessons learned implementing new EHR functionality charting PGx phenotypes in a unique repository, genomic indicators, instead of using the problem or allergy list. The Gen-Ind has additional features including a brief description of the clinical impact, a hyperlink to the original laboratory report, and links to additional educational resources. The automatic generation of genomic indicators from interfaced PGx test results facilitates implementation and long-term maintenance of PGx data in the EHR and can be used as criteria for synchronous and asynchronous CDS., (© The Author(s) 2019. Published by Oxford University Press on behalf of the American Medical Informatics Association. All rights reserved. For permissions, please email: journals.permissions@oup.com.)

Advances in pharmacogenomics (PGx) have the potential to transform healthcare by allowing precision medicine to become a reality. However, PGx knowledge is new, complex, and evolving, and relying on the cognition of clinicians alone is insufficient for clinical implementation. Integrating clinical decision support (CDS) tools in the electronic health record (EHR) is critical for translating PGx into clinical practice. Herein, we review current strategies to implement PGx using EHR-CDS functionalities., (© 2017 American Society for Clinical Pharmacology and Therapeutics.)

Knowledge of variant pathogenicity is key to implementing genomic medicine. We describe variability between expert reviewers in assigning pathogenicity to sequence variants in LDLR, the causal gene in the majority of cases of familial hypercholesterolemia. LDLR was sequenced on the Illumina HiSeq platform (average read depth >200 × ) in 1013 Mayo Biobank participants recruited from 2012 to 2013. Variants with a minor allele frequency (MAF) <5% predicted to be functional or referenced in HGMD (Human Gene Mutation Database) or NCBI-ClinVar databases were reviewed. To assign pathogenicity, variant frequency in population data sets, computational predictions, reported observations and patient-level data including electronic health record-based post hoc phenotyping were leveraged. Of 178 LDLR variants passing quality control, 25 were selected for independent review using either an in-house protocol or a disease/gene-specific semi-quantitative framework based on the American College of Medical Genetics and Genomics-recommended lines of evidence. NCBI-ClinVar included interpretations for all queried variants with 74% (14/19) of variants with >1 submitter showing inconsistency in classification and 26% (5/19) appearing with conflicting clinical actionability. The discordance rate (one-step level of disagreement out of five classes in variant interpretation) between the reviewers was 40% (10/25). Two LDLR variants were independently deemed clinically actionable and returnable. Interpretation of LDLR variants was often discordant among ClinVar submitters and between expert reviewers. A quantitative approach based on strength of each predefined criterion in the context of specific genes and phenotypes may yield greater consistency between different reviewers.

Resistant hypertension is defined as high blood pressure that remains above treatment goals in spite of the concurrent use of three antihypertensive agents from different classes. Despite the important health consequences of resistant hypertension, few studies of resistant hypertension have been conducted. To perform a genome-wide association study for resistant hypertension, we defined and identified cases of resistant hypertension and hypertensives with treated, controlled hypertension among >47,500 adults residing in the US linked to electronic health records (EHRs) and genotyped as part of the electronic MEdical Records & GEnomics (eMERGE) Network. Electronic selection logic using billing codes, laboratory values, text queries, and medication records was used to identify resistant hypertension cases and controls at each site, and a total of 3,006 cases of resistant hypertension and 876 controlled hypertensives were identified among eMERGE Phase I and II sites. After imputation and quality control, a total of 2,530,150 SNPs were tested for an association among 2,830 multi-ethnic cases of resistant hypertension and 876 controlled hypertensives. No test of association was genome-wide significant in the full dataset or in the dataset limited to European American cases (n = 1,719) and controls (n = 708). The most significant finding was CLNK rs13144136 at p = 1.00x10-6 (odds ratio = 0.68; 95% CI = 0.58-0.80) in the full dataset with similar results in the European American only dataset. We also examined whether SNPs known to influence blood pressure or hypertension also influenced resistant hypertension. None was significant after correction for multiple testing. These data highlight both the difficulties and the potential utility of EHR-linked genomic data to study clinically-relevant traits such as resistant hypertension.

Clinical use of pharmacogenomic (PGx) knowledge at the bedside is new and complex. Our program has implemented multiple PGx-CDS interventions in different clinical settings and in multiple commercial EHRs. Herein, we discuss lessons learned and propose general technical guidelines related to PGx implementation.

Background: Community associated methicillin-resistant Staphylococcus aureus (CA-MRSA) is one of the most common causes of skin and soft tissue infections in the United States, and a variety of genetic host factors are suspected to be risk factors for recurrent infection. Based on the CDC definition, we have developed and validated an electronic health record (EHR) based CA-MRSA phenotype algorithm utilizing both structured and unstructured data., Methods: The algorithm was validated at three eMERGE consortium sites, and positive predictive value, negative predictive value and sensitivity, were calculated. The algorithm was then run and data collected across seven total sites. The resulting data was used in GWAS analysis., Results: Across seven sites, the CA-MRSA phenotype algorithm identified a total of 349 cases and 7761 controls among the genotyped European and African American biobank populations. PPV ranged from 68 to 100% for cases and 96 to 100% for controls; sensitivity ranged from 94 to 100% for cases and 75 to 100% for controls. Frequency of cases in the populations varied widely by site. There were no plausible GWAS-significant (p < 5 E -8) findings., Conclusions: Differences in EHR data representation and screening patterns across sites may have affected identification of cases and controls and accounted for varying frequencies across sites. Future work identifying these patterns is necessary.

Background: Limited information is available regarding primary care clinicians' response to pharmacogenomic clinical decision support (PGx-CDS) alerts integrated in the electronic health record., Methods: In February 2015, 159 clinicians in the Mayo Clinic primary care practice were sent e-mail surveys to understand their perspectives on the implementation and use of pharmacogenomic testing in their clinical practice. Surveys assessed how the clinicians felt about pharmacogenomics and whether they thought electronic PGx-CDS alerts were useful. Information was abstracted on the number of CDS alerts the clinicians received between October 2013 and the date their survey was returned. CDS alerts were grouped into 2 categories: the alert recommended caution using the prescription, or the alert recommended an alternate prescription. Finally, data were abstracted regarding whether the clinician changed their prescription in response to the alert recommendation., Results: The survey response rate was 57% (n = 90). Overall, 52% of the clinicians did not expect to use or did not know whether they would use pharmacogenomic information in their future prescribing practices. Additionally, 53% of the clinicians felt that the alerts were confusing, irritating, frustrating, or that it was difficult to find additional information. Finally, only 30% of the clinicians that received a CDS alert changed their prescription to an alternative medication., Conclusions: Our results suggest a lack of clinician comfort with integration of pharmacogenomic data into primary care. Further efforts to refine PGx-CDS alerts to make them as useful and user-friendly as possible are needed to improve clinician satisfaction with these new tools., (Copyright © 2016 Elsevier Inc. All rights reserved.)

The aim of this study was to compare the QRISKII, an electronic health data-based risk score, to the Framingham Risk Score (FRS) and atherosclerotic cardiovascular disease (ASCVD) score. Risk estimates were calculated for a cohort of 8783 patients, and the patients were followed up from November 29, 2012, through June 1, 2015, for a cardiovascular disease (CVD) event. During follow-up, 246 men and 247 women had a CVD event. Cohen's kappa statistic for the comparison of the QRISKII and FRS was 0.22 for men and 0.23 for women, with the QRISKII classifying more patients in the higher-risk groups. The QRISKII and ASCVD were more similar with kappa statistics of 0.49 for men and 0.51 for women. The QRISKII shows increased discrimination with area under the curve (AUC) statistics of 0.65 and 0.71, respectively, compared to the FRS (0.59 and 0.66) and ASCVD (0.63 and 0.69). These results demonstrate that incorporating additional data from the electronic health record (EHR) may improve CVD risk stratification.

Importance: Large-scale DNA sequencing identifies incidental rare variants in established Mendelian disease genes, but the frequency of related clinical phenotypes in unselected patient populations is not well established. Phenotype data from electronic medical records (EMRs) may provide a resource to assess the clinical relevance of rare variants., Objective: To determine the clinical phenotypes from EMRs for individuals with variants designated as pathogenic by expert review in arrhythmia susceptibility genes., Design, Setting, and Participants: This prospective cohort study included 2022 individuals recruited for nonantiarrhythmic drug exposure phenotypes from October 5, 2012, to September 30, 2013, for the Electronic Medical Records and Genomics Network Pharmacogenomics project from 7 US academic medical centers. Variants in SCN5A and KCNH2, disease genes for long QT and Brugada syndromes, were assessed for potential pathogenicity by 3 laboratories with ion channel expertise and by comparison with the ClinVar database. Relevant phenotypes were determined from EMRs, with data available from 2002 (or earlier for some sites) through September 10, 2014., Exposures: One or more variants designated as pathogenic in SCN5A or KCNH2., Main Outcomes and Measures: Arrhythmia or electrocardiographic (ECG) phenotypes defined by International Classification of Diseases, Ninth Revision (ICD-9) codes, ECG data, and manual EMR review., Results: Among 2022 study participants (median age, 61 years [interquartile range, 56-65 years]; 1118 [55%] female; 1491 [74%] white), a total of 122 rare (minor allele frequency <0.5%) nonsynonymous and splice-site variants in 2 arrhythmia susceptibility genes were identified in 223 individuals (11% of the study cohort). Forty-two variants in 63 participants were designated potentially pathogenic by at least 1 laboratory or ClinVar, with low concordance across laboratories (Cohen κ = 0.26). An ICD-9 code for arrhythmia was found in 11 of 63 (17%) variant carriers vs 264 of 1959 (13%) of those without variants (difference, +4%; 95% CI, -5% to +13%; P = .35). In the 1270 (63%) with ECGs, corrected QT intervals were not different in variant carriers vs those without (median, 429 vs 439 milliseconds; difference, -10 milliseconds; 95% CI, -16 to +3 milliseconds; P = .17). After manual review, 22 of 63 participants (35%) with designated variants had any ECG or arrhythmia phenotype, and only 2 had corrected QT interval longer than 500 milliseconds., Conclusions and Relevance: Among laboratories experienced in genetic testing for cardiac arrhythmia disorders, there was low concordance in designating SCN5A and KCNH2 variants as pathogenic. In an unselected population, the putatively pathogenic genetic variants were not associated with an abnormal phenotype. These findings raise questions about the implications of notifying patients of incidental genetic findings.

Identifying populations of heart failure (HF) patients is paramount to research efforts aimed at developing strategies to effectively reduce the burden of this disease. The use of electronic medical record (EMR) data for this purpose is challenging given the syndromic nature of HF and the need to distinguish HF with preserved or reduced ejection fraction. Using a gold standard cohort of manually abstracted cases, an EMR-driven phenotype algorithm based on structured and unstructured data was developed to identify all the cases. The resulting algorithm was executed in two cohorts from the Electronic Medical Records and Genomics (eMERGE) Network with a positive predictive value of >95 %. The algorithm was expanded to include three hierarchical definitions of HF (i.e., definite, probable, possible) based on the degree of confidence of the classification to capture HF cases in a whole population whereby increasing the algorithm utility for use in e-Epidemiologic research.

We describe here the design and initial implementation of the eMERGE-PGx project. eMERGE-PGx, a partnership of the Electronic Medical Records and Genomics Network and the Pharmacogenomics Research Network, has three objectives: (i) to deploy PGRNseq, a next-generation sequencing platform assessing sequence variation in 84 proposed pharmacogenes, in nearly 9,000 patients likely to be prescribed drugs of interest in a 1- to 3-year time frame across several clinical sites; (ii) to integrate well-established clinically validated pharmacogenetic genotypes into the electronic health record with associated clinical decision support and to assess process and clinical outcomes of implementation; and (iii) to develop a repository of pharmacogenetic variants of unknown significance linked to a repository of electronic health record-based clinical phenotype data for ongoing pharmacogenomics discovery. We describe site-specific project implementation and anticipated products, including genetic variant and phenotype data repositories, novel variant association studies, clinical decision support modules, clinical and process outcomes, approaches to managing incidental findings, and patient and clinician education methods.

Candidate gene and genome-wide association studies (GWAS) have identified genetic variants that modulate risk for human disease; many of these associations require further study to replicate the results. Here we report the first large-scale application of the phenome-wide association study (PheWAS) paradigm within electronic medical records (EMRs), an unbiased approach to replication and discovery that interrogates relationships between targeted genotypes and multiple phenotypes. We scanned for associations between 3,144 single-nucleotide polymorphisms (previously implicated by GWAS as mediators of human traits) and 1,358 EMR-derived phenotypes in 13,835 individuals of European ancestry. This PheWAS replicated 66% (51/77) of sufficiently powered prior GWAS associations and revealed 63 potentially pleiotropic associations with P < 4.6 × 10⁻⁶ (false discovery rate < 0.1); the strongest of these novel associations were replicated in an independent cohort (n = 7,406). These findings validate PheWAS as a tool to allow unbiased interrogation across multiple phenotypes in EMR-based cohorts and to enhance analysis of the genomic basis of human disease.

Background: Genetic studies require precise phenotype definitions, but electronic medical record (EMR) phenotype data are recorded inconsistently and in a variety of formats., Objective: To present lessons learned about validation of EMR-based phenotypes from the Electronic Medical Records and Genomics (eMERGE) studies., Materials and Methods: The eMERGE network created and validated 13 EMR-derived phenotype algorithms. Network sites are Group Health, Marshfield Clinic, Mayo Clinic, Northwestern University, and Vanderbilt University., Results: By validating EMR-derived phenotypes we learned that: (1) multisite validation improves phenotype algorithm accuracy; (2) targets for validation should be carefully considered and defined; (3) specifying time frames for review of variables eases validation time and improves accuracy; (4) using repeated measures requires defining the relevant time period and specifying the most meaningful value to be studied; (5) patient movement in and out of the health plan (transience) can result in incomplete or fragmented data; (6) the review scope should be defined carefully; (7) particular care is required in combining EMR and research data; (8) medication data can be assessed using claims, medications dispensed, or medications prescribed; (9) algorithm development and validation work best as an iterative process; and (10) validation by content experts or structured chart review can provide accurate results., Conclusions: Despite the diverse structure of the five EMRs of the eMERGE sites, we developed, validated, and successfully deployed 13 electronic phenotype algorithms. Validation is a worthwhile process that not only measures phenotype performance but also strengthens phenotype algorithm definitions and enhances their inter-institutional sharing.

Only one low-density lipoprotein cholesterol (LDL-C) genome-wide association study (GWAS) has been previously reported in -African Americans. We performed a GWAS of LDL-C in African Americans using data extracted from electronic medical records (EMR) in the eMERGE network. African Americans were genotyped on the Illumina 1M chip. All LDL-C measurements, prescriptions, and diagnoses of concomitant disease were extracted from EMR. We created two analytic datasets; one dataset having median LDL-C calculated after the exclusion of some lab values based on comorbidities and medication (n= 618) and another dataset having median LDL-C calculated without any exclusions (n= 1,249). SNP rs7412 in APOE was strongly associated with LDL-C in both datasets (p < 5 × 10(-8) ). In the dataset with exclusions, a decrease of 20.0 mg/dL per minor allele was observed. The effect size was attenuated (12.3 mg/dL) in the dataset without any lab values excluded. Although other signals in APOE have been detected in previous GWAS, this large and important SNP association has not been well detected in large GWAS because rs7412 was not included on many genotyping arrays. Use of median LDL-C extracted from EMR after exclusions for medications and comorbidities increased the percentage of trait variance explained by genetic variation., (© 2012 Wiley Periodicals, Inc.)

Objective: Genome-wide association studies (GWAS) require high specificity and large numbers of subjects to identify genotype-phenotype correlations accurately. The aim of this study was to identify type 2 diabetes (T2D) cases and controls for a GWAS, using data captured through routine clinical care across five institutions using different electronic medical record (EMR) systems., Materials and Methods: An algorithm was developed to identify T2D cases and controls based on a combination of diagnoses, medications, and laboratory results. The performance of the algorithm was validated at three of the five participating institutions compared against clinician review. A GWAS was subsequently performed using cases and controls identified by the algorithm, with samples pooled across all five institutions., Results: The algorithm achieved 98% and 100% positive predictive values for the identification of diabetic cases and controls, respectively, as compared against clinician review. By standardizing and applying the algorithm across institutions, 3353 cases and 3352 controls were identified. Subsequent GWAS using data from five institutions replicated the TCF7L2 gene variant (rs7903146) previously associated with T2D., Discussion: By applying stringent criteria to EMR data collected through routine clinical care, cases and controls for a GWAS were identified that subsequently replicated a known genetic variant. The use of standard terminologies to define data elements enabled pooling of subjects and data across five different institutions to achieve the robust numbers required for GWAS., Conclusions: An algorithm using commonly available data from five different EMR can accurately identify T2D cases and controls for genetic study across multiple institutions.

The ability to conduct genome-wide association studies (GWAS) has enabled new exploration of how genetic variations contribute to health and disease etiology. However, historically GWAS have been limited by inadequate sample size due to associated costs for genotyping and phenotyping of study subjects. This has prompted several academic medical centers to form "biobanks" where biospecimens linked to personal health information, typically in electronic health records (EHRs), are collected and stored on large number of subjects. This provides tremendous opportunities to discover novel genotype-phenotype associations and foster hypothesis generation. In this work, we study how emerging Semantic Web technologies can be applied in conjunction with clinical and genotype data stored at the Mayo Clinic Biobank to mine the phenotype data for genetic associations. In particular, we demonstrate the role of using Resource Description Framework (RDF) for representing EHR diagnoses and procedure data, and enable federated querying via standardized Web protocols to identify subjects genotyped with Type 2 Diabetes for discovering gene-disease associations. Our study highlights the potential of Web-scale data federation techniques to execute complex queries.

Genome-wide association studies (GWAS) are a useful approach in the study of the genetic components of complex phenotypes. Aside from large cohorts, GWAS have generally been limited to the study of one or a few diseases or traits. The emergence of biobanks linked to electronic medical records (EMRs) allows the efficient reuse of genetic data to yield meaningful genotype-phenotype associations for multiple phenotypes or traits. Phase I of the electronic MEdical Records and GEnomics (eMERGE-I) Network is a National Human Genome Research Institute-supported consortium composed of five sites to perform various genetic association studies using DNA repositories and EMR systems. Each eMERGE site has developed EMR-based algorithms to comprise a core set of 14 phenotypes for extraction of study samples from each site's DNA repository. Each eMERGE site selected samples for a specific phenotype, and these samples were genotyped at either the Broad Institute or at the Center for Inherited Disease Research using the Illumina Infinium BeadChip technology. In all, approximately 17,000 samples from across the five sites were genotyped. A unified quality control (QC) pipeline was developed by the eMERGE Genomics Working Group and used to ensure thorough cleaning of the data. This process includes examination of sample and marker quality and various batch effects. Upon completion of the genotyping and QC analyses for each site's primary study, eMERGE Coordinating Center merged the datasets from all five sites. This larger merged dataset reentered the established eMERGE QC pipeline. Based on lessons learned during the process, additional analyses and QC checkpoints were added to the pipeline to ensure proper merging. Here, we explore the challenges associated with combining datasets from different genotyping centers and describe the expansion to eMERGE QC pipeline for merged datasets. These additional steps will be useful as the eMERGE project expands to include additional sites in eMERGE-II, and also serve as a starting point for investigators merging multiple genotype datasets accessible through the National Center for Biotechnology Information in the database of Genotypes and Phenotypes. Our experience demonstrates that merging multiple datasets after additional QC can be an efficient use of genotype data despite new challenges that appear in the process., (© 2011 Wiley Periodicals, Inc.)

Clinical data in electronic medical records (EMRs) are a potential source of longitudinal clinical data for research. The Electronic Medical Records and Genomics Network (eMERGE) investigates whether data captured through routine clinical care using EMRs can identify disease phenotypes with sufficient positive and negative predictive values for use in genome-wide association studies (GWAS). Using data from five different sets of EMRs, we have identified five disease phenotypes with positive predictive values of 73 to 98% and negative predictive values of 98 to 100%. Most EMRs captured key information (diagnoses, medications, laboratory tests) used to define phenotypes in a structured format. We identified natural language processing as an important tool to improve case identification rates. Efforts and incentives to increase the implementation of interoperable EMRs will markedly improve the availability of clinical data for genomics research.