Workflow Integration of Research AI Tools into a Hospital Radiology Rapid Prototyping Environment.

The field of artificial intelligence (AI) in medical imaging is undergoing explosive growth, and Radiology is a prime target for innovation. The American College of Radiology Data Science Institute has identified more than 240 specific use cases where AI could be used to improve clinical practice. In this context, thousands of potential methods are developed by research labs and industry innovators. Deploying AI tools within a clinical enterprise, even on limited retrospective evaluation, is complicated by security and privacy concerns. Thus, innovation must be weighed against the substantive resources required for local clinical evaluation. To reduce barriers to AI validation while maintaining rigorous security and privacy standards, we developed the AI Imaging Incubator. The AI Imaging Incubator serves as a DICOM storage destination within a clinical enterprise where images can be directed for novel research evaluation under Institutional Review Board approval. AI Imaging Incubator is controlled by a secure HIPAA-compliant front end and provides access to a menu of AI procedures captured within network-isolated containers. Results are served via a secure website that supports research and clinical data formats. Deployment of new AI approaches within this system is streamlined through a standardized application programming interface. This manuscript presents case studies of the AI Imaging Incubator applied to randomizing lung biopsies on chest CT, liver fat assessment on abdomen CT, and brain volumetry on head MRI.

Genetics of glucocorticoid-associated osteonecrosis in children with acute lymphoblastic leukemia.

Glucocorticoids are important therapy for acute lymphoblastic leukemia (ALL) and their major adverse effect is osteonecrosis. Our goal was to identify genetic and nongenetic risk factors for osteonecrosis. We performed a genome-wide association study of single nucleotide polymorphisms (SNPs) in a discovery cohort comprising 2285 children with ALL, treated on the Children's Oncology Group AALL0232 protocol (NCT00075725), adjusting for covariates. The minor allele at SNP rs10989692 (near the glutamate receptor GRIN3A locus) was associated with osteonecrosis (hazard ratio = 2.03; P = 3.59 × 10(-7)). The association was supported by 2 replication cohorts, including 361 children with ALL on St. Jude's Total XV protocol (NCT00137111) and 309 non-ALL patients from Vanderbilt University's BioVU repository treated with glucocorticoids (odds ratio [OR] = 1.87 and 2.26; P = .063 and .0074, respectively). In a meta-analysis, rs10989692 was also highest ranked (P = 2.68 × 10(-8)), and the glutamate pathway was the top ranked pathway (P = 9.8 × 10(-4)). Osteonecrosis-associated glutamate receptor variants were also associated with other vascular phenotypes including cerebral ischemia (OR = 1.64; P = 2.5 × 10(-3)), and arterial embolism and thrombosis (OR = 1.88; P = 4.2 × 10(-3)). In conclusion, osteonecrosis was associated with inherited variations near glutamate receptor genes. Further understanding this association may allow interventions to decrease osteonecrosis. These trials are registered at www.clinicaltrials.gov as #NCT00075725 and #NCT00137111.

Conducting a large, multi-site survey about patients' views on broad consent: challenges and solutions.

BACKGROUND: As biobanks play an increasing role in the genomic research that will lead to precision medicine, input from diverse and large populations of patients in a variety of health care settings will be important in order to successfully carry out such studies. One important topic is participants' views towards consent and data sharing, especially since the 2011 Advanced Notice of Proposed Rulemaking (ANPRM), and subsequently the 2015 Notice of Proposed Rulemaking (NPRM) were issued by the Department of Health and Human Services (HHS) and Office of Science and Technology Policy (OSTP). These notices required that participants consent to research uses of their de-identified tissue samples and most clinical data, and allowing such consent be obtained in a one-time, open-ended or "broad" fashion. Conducting a survey across multiple sites provides clear advantages to either a single site survey or using a large online database, and is a potentially powerful way of understanding the views of diverse populations on this topic. METHODS: A workgroup of the Electronic Medical Records and Genomics (eMERGE) Network, a national consortium of 9 sites (13 separate institutions, 11 clinical centers) supported by the National Human Genome Research Institute (NHGRI) that combines DNA biorepositories with electronic medical record (EMR) systems for large-scale genetic research, conducted a survey to understand patients' views on consent, sample and data sharing for future research, biobank governance, data protection, and return of research results. RESULTS: Working across 9 sites to design and conduct a national survey presented challenges in organization, meeting human subjects guidelines at each institution, and survey development and implementation. The challenges were met through a committee structure to address each aspect of the project with representatives from all sites. Each committee's output was integrated into the overall survey plan. A number of site-specific issues were successfully managed allowing the survey to be developed and implemented uniformly across 11 clinical centers. CONCLUSIONS: Conducting a survey across a number of institutions with different cultures and practices is a methodological and logistical challenge. With a clear infrastructure, collaborative attitudes, excellent lines of communication, and the right expertise, this can be accomplished successfully.

Genome- and phenome-wide analyses of cardiac conduction identifies markers of arrhythmia risk.

BACKGROUND: ECG QRS duration, a measure of cardiac intraventricular conduction, varies ≈2-fold in individuals without cardiac disease. Slow conduction may promote re-entrant arrhythmias. METHODS AND RESULTS: We performed a genome-wide association study to identify genomic markers of QRS duration in 5272 individuals without cardiac disease selected from electronic medical record algorithms at 5 sites in the Electronic Medical Records and Genomics (eMERGE) network. The most significant loci were evaluated within the Cohorts for Heart and Aging Research in Genomic Epidemiology (CHARGE) consortium QRS genome-wide association study meta-analysis. Twenty-three single-nucleotide polymorphisms in 5 loci, previously described by CHARGE, were replicated in the eMERGE samples; 18 single-nucleotide polymorphisms were in the chromosome 3 SCN5A and SCN10A loci, where the most significant single-nucleotide polymorphisms were rs1805126 in SCN5A with P=1.2×10(-8) (eMERGE) and P=2.5×10(-20) (CHARGE) and rs6795970 in SCN10A with P=6×10(-6) (eMERGE) and P=5×10(-27) (CHARGE). The other loci were in NFIA, near CDKN1A, and near C6orf204. We then performed phenome-wide association studies on variants in these 5 loci in 13859 European Americans to search for diagnoses associated with these markers. Phenome-wide association study identified atrial fibrillation and cardiac arrhythmias as the most common associated diagnoses with SCN10A and SCN5A variants. SCN10A variants were also associated with subsequent development of atrial fibrillation and arrhythmia in the original 5272 "heart-healthy" study population. CONCLUSIONS: We conclude that DNA biobanks coupled to electronic medical records not only provide a platform for genome-wide association study but also may allow broad interrogation of the longitudinal incidence of disease associated with genetic variants. The phenome-wide association study approach implicated sodium channel variants modulating QRS duration in subjects without cardiac disease as predictors of subsequent arrhythmias.

Variants near FOXE1 are associated with hypothyroidism and other thyroid conditions: using electronic medical records for genome- and phenome-wide studies.

We repurposed existing genotypes in DNA biobanks across the Electronic Medical Records and Genomics network to perform a genome-wide association study for primary hypothyroidism, the most common thyroid disease. Electronic selection algorithms incorporating billing codes, laboratory values, text queries, and medication records identified 1317 cases and 5053 controls of European ancestry within five electronic medical records (EMRs); the algorithms' positive predictive values were 92.4% and 98.5% for cases and controls, respectively. Four single-nucleotide polymorphisms (SNPs) in linkage disequilibrium at 9q22 near FOXE1 were associated with hypothyroidism at genome-wide significance, the strongest being rs7850258 (odds ratio [OR] 0.74, p = 3.96 × 10(-9)). This association was replicated in a set of 263 cases and 1616 controls (OR = 0.60, p = 5.7 × 10(-6)). A phenome-wide association study (PheWAS) that was performed on this locus with 13,617 individuals and more than 200,000 patient-years of billing data identified associations with additional phenotypes: thyroiditis (OR = 0.58, p = 1.4 × 10(-5)), nodular (OR = 0.76, p = 3.1 × 10(-5)) and multinodular (OR = 0.69, p = 3.9 × 10(-5)) goiters, and thyrotoxicosis (OR = 0.76, p = 1.5 × 10(-3)), but not Graves disease (OR = 1.03, p = 0.82). Thyroid cancer, previously associated with this locus, was not significantly associated in the PheWAS (OR = 1.29, p = 0.09). The strongest association in the PheWAS was hypothyroidism (OR = 0.76, p = 2.7 × 10(-13)), which had an odds ratio that was nearly identical to that of the curated case-control population in the primary analysis, providing further validation of the PheWAS method. Our findings indicate that EMR-linked genomic data could allow discovery of genes associated with many diseases without additional genotyping cost.

Ethical and practical challenges of sharing data from genome-wide association studies: the eMERGE Consortium experience.

In 2007, the National Human Genome Research Institute (NHGRI) established the Electronic MEdical Records and GEnomics (eMERGE) Consortium (www.gwas.net) to develop, disseminate, and apply approaches to research that combine DNA biorepositories with electronic medical record (EMR) systems for large-scale, high-throughput genetic research. One of the major ethical and administrative challenges for the eMERGE Consortium has been complying with existing data-sharing policies. This paper discusses the challenges of sharing genomic data linked to health information in the electronic medical record (EMR) and explores the issues as they relate to sharing both within a large consortium and in compliance with the National Institutes of Health (NIH) data-sharing policy. We use the eMERGE Consortium experience to explore data-sharing challenges from the perspective of multiple stakeholders (i.e., research participants, investigators, and research institutions), provide recommendations for researchers and institutions, and call for clearer guidance from the NIH regarding ethical implementation of its data-sharing policy.

Secondary use of clinical data: the Vanderbilt approach.

The last decade has seen an exponential growth in the quantity of clinical data collected nationwide, triggering an increase in opportunities to reuse the data for biomedical research. The Vanderbilt research data warehouse framework consists of identified and de-identified clinical data repositories, fee-for-service custom services, and tools built atop the data layer to assist researchers across the enterprise. Providing resources dedicated to research initiatives benefits not only the research community, but also clinicians, patients and institutional leadership. This work provides a summary of our approach in the secondary use of clinical data for research domain, including a description of key components and a list of lessons learned, designed to assist others assembling similar services and infrastructure.

Generalization of variants identified by genome-wide association studies for electrocardiographic traits in African Americans.

Electrocardiographic (ECG) measurements vary by ancestry. Genome-wide association studies (GWAS) have identified loci that contribute to ECG measurements; however, most are performed in Europeans collected from population-based cohorts or surveys. The strongest associations reported are in NOS1AP with QT interval and SCN10A with PR and QRS durations. The extent to which these associations can be generalized to African Americans has yet to be determined. Using electronic medical records, PR and QT intervals, QRS duration, and heart rate were determined in 455 African Americans as part of the Vanderbilt Genome-Electronic Records Project and Northwestern University NUgene Project. We tested for an association between these ECG traits and >930K SNPs. We identified a total 36 novel associations with PR interval, QRS duration, QT interval, and heart rate at p < 1.0 × 10(-6). Using published GWAS data, we compared our results with those previously identified in other populations. Five associations originally identified in other populations generalized with respect to statistical significance and direction of effect. A total of 43 associations have a consistent direction of effect with European and/or Asian populations. This work provides a catalogue of generalized versus nongeneralized associations, a necessary step in prioritizing GWAS-identified regions for further fine-mapping in diverse populations.

Robust replication of genotype-phenotype associations across multiple diseases in an electronic medical record.

Large-scale DNA databanks linked to electronic medical record (EMR) systems have been proposed as an approach for rapidly generating large, diverse cohorts for discovery and replication of genotype-phenotype associations. However, the extent to which such resources are capable of delivering on this promise is unknown. We studied whether an EMR-linked DNA biorepository can be used to detect known genotype-phenotype associations for five diseases. Twenty-one SNPs previously implicated as common variants predisposing to atrial fibrillation, Crohn disease, multiple sclerosis, rheumatoid arthritis, or type 2 diabetes were successfully genotyped in 9483 samples accrued over 4 mo into BioVU, the Vanderbilt University Medical Center DNA biobank. Previously reported odds ratios (OR(PR)) ranged from 1.14 to 2.36. For each phenotype, natural language processing techniques and billing-code queries were used to identify cases (n = 70-698) and controls (n = 808-3818) from deidentified health records. Each of the 21 tests of association yielded point estimates in the expected direction. Previous genotype-phenotype associations were replicated (p < 0.05) in 8/14 cases when the OR(PR) was > 1.25, and in 0/7 with lower OR(PR). Statistically significant associations were detected in all analyses that were adequately powered. In each of the five diseases studied, at least one previously reported association was replicated. These data demonstrate that phenotypes representing clinical diagnoses can be extracted from EMR systems, and they support the use of DNA resources coupled to EMR systems as tools for rapid generation of large data sets required for replication of associations found in research cohorts and for discovery in genome science.

The Electronic Medical Records and Genomics (eMERGE) Network: past, present, and future.

The Electronic Medical Records and Genomics Network is a National Human Genome Research Institute-funded consortium engaged in the development of methods and best practices for using the electronic medical record as a tool for genomic research. Now in its sixth year and second funding cycle, and comprising nine research groups and a coordinating center, the network has played a major role in validating the concept that clinical data derived from electronic medical records can be used successfully for genomic research. Current work is advancing knowledge in multiple disciplines at the intersection of genomics and health-care informatics, particularly for electronic phenotyping, genome-wide association studies, genomic medicine implementation, and the ethical and regulatory issues associated with genomics research and returning results to study participants. Here, we describe the evolution, accomplishments, opportunities, and challenges of the network from its inception as a five-group consortium focused on genotype-phenotype associations for genomic discovery to its current form as a nine-group consortium pivoting toward the implementation of genomic medicine.

How Fitbit data are being made available to registered researchers in All of Us Research Program.

The National Institutes of Health's (NIH) All of Us Research Program aims to enroll at least one million US participants from diverse backgrounds; collect electronic health record (EHR) data, survey data, physical measurements, biospecimens for genomics and other assays, and digital health data; and create a researcher database and tools to enable precision medicine research [1]. Since inception, digital health technologies (DHT) have been envisioned as essential to achieving the goals of the program [2]. A "bring your own device" (BYOD) study for collecting Fitbit data from participants' devices was developed with integration of additional DHTs planned in the future [3]. Here we describe how participants can consent to share their digital health technology data, how the data are collected, how the data set is parsed, and how researchers can access the data.

Managing re-identification risks while providing access to the All of Us research program.

OBJECTIVE: The All of Us Research Program makes individual-level data available to researchers while protecting the participants' privacy. This article describes the protections embedded in the multistep access process, with a particular focus on how the data was transformed to meet generally accepted re-identification risk levels. METHODS: At the time of the study, the resource consisted of 329 084 participants. Systematic amendments were applied to the data to mitigate re-identification risk (eg, generalization of geographic regions, suppression of public events, and randomization of dates). We computed the re-identification risk for each participant using a state-of-the-art adversarial model specifically assuming that it is known that someone is a participant in the program. We confirmed the expected risk is no greater than 0.09, a threshold that is consistent with guidelines from various US state and federal agencies. We further investigated how risk varied as a function of participant demographics. RESULTS: The results indicated that 95th percentile of the re-identification risk of all the participants is below current thresholds. At the same time, we observed that risk levels were higher for certain race, ethnic, and genders. CONCLUSIONS: While the re-identification risk was sufficiently low, this does not imply that the system is devoid of risk. Rather, All of Us uses a multipronged data protection strategy that includes strong authentication practices, active monitoring of data misuse, and penalization mechanisms for users who violate terms of service.

De-black-boxing health AI: demonstrating reproducible machine learning computable phenotypes using the N3C-RECOVER Long COVID model in the All of Us data repository.

Machine learning (ML)-driven computable phenotypes are among the most challenging to share and reproduce. Despite this difficulty, the urgent public health considerations around Long COVID make it especially important to ensure the rigor and reproducibility of Long COVID phenotyping algorithms such that they can be made available to a broad audience of researchers. As part of the NIH Researching COVID to Enhance Recovery (RECOVER) Initiative, researchers with the National COVID Cohort Collaborative (N3C) devised and trained an ML-based phenotype to identify patients highly probable to have Long COVID. Supported by RECOVER, N3C and NIH's All of Us study partnered to reproduce the output of N3C's trained model in the All of Us data enclave, demonstrating model extensibility in multiple environments. This case study in ML-based phenotype reuse illustrates how open-source software best practices and cross-site collaboration can de-black-box phenotyping algorithms, prevent unnecessary rework, and promote open science in informatics.

Demonstrating paths for unlocking the value of cloud genomics through cross cohort analysis.

Recently, large scale genomic projects such as All of Us and the UK Biobank have introduced a new research paradigm where data are stored centrally in cloud-based Trusted Research Environments (TREs). To characterize the advantages and drawbacks of different TRE attributes in facilitating cross-cohort analysis, we conduct a Genome-Wide Association Study of standard lipid measures using two approaches: meta-analysis and pooled analysis. Comparison of full summary data from both approaches with an external study shows strong correlation of known loci with lipid levels (R2 ~ 83-97%). Importantly, 90 variants meet the significance threshold only in the meta-analysis and 64 variants are significant only in pooled analysis, with approximately 20% of variants in each of those groups being most prevalent in non-European, non-Asian ancestry individuals. These findings have important implications, as technical and policy choices lead to cross-cohort analyses generating similar, but not identical results, particularly for non-European ancestral populations.

Genetic and Survey Data Improves Performance of Machine Learning Model for Long COVID.

Over 200 million SARS-CoV-2 patients have or will develop persistent symptoms (long COVID). Given this pressing research priority, the National COVID Cohort Collaborative (N3C) developed a machine learning model using only electronic health record data to identify potential patients with long COVID. We hypothesized that additional data from health surveys, mobile devices, and genotypes could improve prediction ability. In a cohort of SARS-CoV-2 infected individuals (n=17,755) in the All of Us program, we applied and expanded upon the N3C long COVID prediction model, testing machine learning infrastructures, assessing model performance, and identifying factors that contributed most to the prediction models. For the survey/mobile device information and genetic data, extreme gradient boosting and a convolutional neural network delivered the best performance for predicting long COVID, respectively. Combined survey, genetic, and mobile data increased specificity and the Area Under Curve the Receiver Operating Characteristic score versus the original N3C model.

The All of Us Data and Research Center: Creating a Secure, Scalable, and Sustainable Ecosystem for Biomedical Research.

The All of Us Research Program's Data and Research Center (DRC) was established to help acquire, curate, and provide access to one of the world's largest and most diverse datasets for precision medicine research. Already, over 500,000 participants are enrolled in All of Us, 80% of whom are underrepresented in biomedical research, and data are being analyzed by a community of over 2,300 researchers. The DRC created this thriving data ecosystem by collaborating with engaged participants, innovative program partners, and empowered researchers. In this review, we first describe how the DRC is organized to meet the needs of this broad group of stakeholders. We then outline guiding principles, common challenges, and innovative approaches used to build the All of Us data ecosystem. Finally, we share lessons learned to help others navigate important decisions and trade-offs in building a modern biomedical data platform.

The use of a DNA biobank linked to electronic medical records to characterize pharmacogenomic predictors of tacrolimus dose requirement in kidney transplant recipients.

OBJECTIVE: Tacrolimus, an immunosuppressive drug widely prescribed in kidney transplantation, requires therapeutic drug monitoring due to its marked interindividual pharmacokinetic variability and narrow therapeutic index. Previous studies have established that CYP3A5 rs776746 is associated with tacrolimus clearance, blood concentration, and dose requirement. The importance of other drug absorption, distribution, metabolism, and elimination (ADME) gene variants has not been well characterized. METHODS: We used novel DNA biobank and electronic medical record resources to identify ADME variants associated with tacrolimus dose requirement. Broad ADME genotyping was performed on 446 kidney transplant recipients, who had been dosed to a steady state with tacrolimus. The cohort was obtained from Vanderbilt's DNA biobank, BioVU, which contains linked deidentified electronic medical record data. Genotyping included Affymetrix drug-metabolizing enzymes and transporters Plus (1936 polymorphisms), custom Sequenom Massarray iPLEX Gold assay (95 polymorphisms), and ancestry-informative markers. The primary outcome was tacrolimus dose requirement defined as blood concentration to dose ratio. RESULTS: In analyses, which adjusted for race and other clinical factors, we replicated the association of tacrolimus blood concentration to dose ratio with CYP3A5 rs776746 (P=7.15×10), and identified associations with nine variants in linkage disequilibrium with rs776746, including eight CYP3A4 variants. No NR1I2 variants were significantly associated. Age, weight, and hemoglobin were also significantly associated with the outcome. In final models, rs776746 explained 39% of variability in dose requirement and 46% was explained by the model containing clinical covariates. CONCLUSION: This study highlights the utility of DNA biobanks and electronic medical records for tacrolimus pharmacogenomic research.

The All of Us Research Program: Data quality, utility, and diversity.

The All of Us Research Program seeks to engage at least one million diverse participants to advance precision medicine and improve human health. We describe here the cloud-based Researcher Workbench that uses a data passport model to democratize access to analytical tools and participant information including survey, physical measurement, and electronic health record (EHR) data. We also present validation study findings for several common complex diseases to demonstrate use of this novel platform in 315,000 participants, 78% of whom are from groups historically underrepresented in biomedical research, including 49% self-reporting non-White races. Replication findings include medication usage pattern differences by race in depression and type 2 diabetes, validation of known cancer associations with smoking, and calculation of cardiovascular risk scores by reported race effects. The cloud-based Researcher Workbench represents an important advance in enabling secure access for a broad range of researchers to this large resource and analytical tools.

Identification of genomic predictors of atrioventricular conduction: using electronic medical records as a tool for genome science.

BACKGROUND: Recent genome-wide association studies in which selected community populations are used have identified genomic signals in SCN10A influencing PR duration. The extent to which this can be demonstrated in cohorts derived from electronic medical records is unknown. METHODS AND RESULTS: We performed a genome-wide association study on 2334 European American patients with normal ECGs without evidence of prior heart disease from the Vanderbilt DNA databank, BioVU, which accrues subjects from routine patient care. Subjects were identified by combinations of natural language processing, laboratory queries, and billing code queries of deidentified medical record data. Subjects were 58% female, of mean (± SD) age 54 ± 15 years, and had mean PR intervals of 158 ± 18 ms. Genotyping was performed with the use of the Illumina Human660W-Quad platform. Our results identify 4 single nucleotide polymorphisms (rs6800541, rs6795970, rs6798015, rs7430477) linked to SCN10A associated with PR interval (P=5.73 × 10(-7) to 1.78 × 10(-6)). CONCLUSIONS: This genome-wide association study confirms a gene heretofore not implicated in cardiac pathophysiology as a modulator of PR interval in humans. This study is one of the first replication genome-wide association studies performed with the use of an electronic medical records-derived cohort, supporting their further use for genotype-phenotype analyses.

PheWAS: demonstrating the feasibility of a phenome-wide scan to discover gene-disease associations.

MOTIVATION: Emergence of genetic data coupled to longitudinal electronic medical records (EMRs) offers the possibility of phenome-wide association scans (PheWAS) for disease-gene associations. We propose a novel method to scan phenomic data for genetic associations using International Classification of Disease (ICD9) billing codes, which are available in most EMR systems. We have developed a code translation table to automatically define 776 different disease populations and their controls using prevalent ICD9 codes derived from EMR data. As a proof of concept of this algorithm, we genotyped the first 6005 European-Americans accrued into BioVU, Vanderbilt's DNA biobank, at five single nucleotide polymorphisms (SNPs) with previously reported disease associations: atrial fibrillation, Crohn's disease, carotid artery stenosis, coronary artery disease, multiple sclerosis, systemic lupus erythematosus and rheumatoid arthritis. The PheWAS software generated cases and control populations across all ICD9 code groups for each of these five SNPs, and disease-SNP associations were analyzed. The primary outcome of this study was replication of seven previously known SNP-disease associations for these SNPs. RESULTS: Four of seven known SNP-disease associations using the PheWAS algorithm were replicated with P-values between 2.8 x 10(-6) and 0.011. The PheWAS algorithm also identified 19 previously unknown statistical associations between these SNPs and diseases at P < 0.01. This study indicates that PheWAS analysis is a feasible method to investigate SNP-disease associations. Further evaluation is needed to determine the validity of these associations and the appropriate statistical thresholds for clinical significance. AVAILABILITY: The PheWAS software and code translation table are freely available at http://knowledgemap.mc.vanderbilt.edu/research.