Building a vertically integrated genomic learning health system: The biobank at the Colorado Center for Personalized Medicine

Precision medicine initiatives across the globe have led to a revolution of repositories linking large-scale genomic data with electronic health records, enabling genomic analyses across the entire phenome. Many of these initiatives focus solely on research insights, leading to limited direct benefit to patients. We describe the biobank at the Colorado Center for Personalized Medicine (CCPM Biobank) that was jointly developed by the University of Colorado Anschutz Medical Campus and UCHealth to serve as a unique, dual-purpose research and clinical resource accelerating personalized medicine. This living resource currently has more than 200,000 participants with ongoing recruitment. We highlight the clinical, laboratory, regulatory, and HIPAA-compliant informatics infrastructure along with our stakeholder engagement, consent, recontact, and participant engagement strategies. We characterize aspects of genetic and geographic diversity unique to the Rocky Mountain region, the primary catchment area for CCPM Biobank participants. We leverage linked health and demographic information of the CCPM Biobank participant population to demonstrate the utility of the CCPM Biobank to replicate complex trait associations in the first 33,674 genotyped individuals across multiple disease domains. Finally, we describe our current efforts toward return of clinical genetic test results, including high-impact pathogenic variants and pharmacogenetic information, and our broader goals as the CCPM Biobank continues to grow. Bringing clinical and research interests together fosters unique clinical and translational questions that can be addressed from the large EHR-linked CCPM Biobank resource within a HIPAA- and CLIA-certified environment.

Characterizing variability of electronic health record-driven phenotype definitions

OBJECTIVE

The aim of this study was to analyze a publicly available sample of rule-based phenotype definitions to characterize and evaluate the variability of logical constructs used.

MATERIALS AND METHODS

A sample of 33 preexisting phenotype definitions used in research that are represented using Fast Healthcare Interoperability Resources and Clinical Quality Language (CQL) was analyzed using automated analysis of the computable representation of the CQL libraries.

RESULTS

Most of the phenotype definitions include narrative descriptions and flowcharts, while few provide pseudocode or executable artifacts. Most use 4 or fewer medical terminologies. The number of codes used ranges from 5 to 6865, and value sets from 1 to 19. We found that the most common expressions used were literal, data, and logical expressions. Aggregate and arithmetic expressions are the least common. Expression depth ranges from 4 to 27.

DISCUSSION

Despite the range of conditions, we found that all of the phenotype definitions consisted of logical criteria, representing both clinical and operational logic, and tabular data, consisting of codes from standard terminologies and keywords for natural language processing. The total number and variety of expressions are low, which may be to simplify implementation, or authors may limit complexity due to data availability constraints.

CONCLUSIONS

The phenotype definitions analyzed show significant variation in specific logical, arithmetic, and other operators but are all composed of the same high-level components, namely tabular data and logical expressions. A standard representation for phenotype definitions should support these formats and be modular to support localization and shared logic.

ReviewR: a light-weight and extensible tool for manual review of clinical records

Objectives

Manual record review is a crucial step for electronic health record (EHR)-based research, but it has poor workflows and is error prone. We sought to build a tool that provides a unified environment for data review and chart abstraction data entry.

Materials and Methods

ReviewR is an open-source R Shiny application that can be deployed on a single machine or made available to multiple users. It supports multiple data models and database systems, and integrates with the REDCap API for storing abstraction results.

Results

We describe 2 real-world uses and extensions of ReviewR. Since its release in April 2021 as a package on CRAN it has been downloaded 2204 times.

Discussion and Conclusion

ReviewR provides an easily accessible review interface for clinical data warehouses. Its modular, extensible, and open source nature afford future expansion by other researchers.

Assessing the utility and accuracy of ICD10-CM non-traumatic subarachnoid hemorrhage codes for intracranial aneurysm research

BACKGROUND

The 10th revision of International Classification of Disease, Clinical Modification (ICD10-CM) increased the number of codes to identify non-traumatic subarachnoid hemorrhage from 1 to 22. ICD10-CM codes are able to specify the location of aneurysms causing subarachnoid hemorrhage (aSAH); however, it is not clear how frequently or accurately these codes are being used in practice.

OBJECTIVE

To systematically evaluate the usage and accuracy of location-specific ICD10-CM codes for aSAH.

METHODS

We extracted all uses of ICD10-CM codes for non-traumatic subarachnoid hemorrhage (I60.x) during the first 3 years following the implementation of ICD10-CM from the billing module of the electronic health record (EHR) for UCHealth. For those codes that specified aSAH location (I60.0-I60.6), EHR documentation was reviewed to determine whether there was an active aSAH, any patient history of aSAH, or unruptured intracranial aneurysm/s and the locations of those outcomes.

RESULTS

Between 1 October 2015 and 30 September 2018, there were 3119 instances of non-traumatic subarachnoid hemorrhage ICD10-CM codes (I60.00-I60.9), of which 297 (9.5%) code instances identified aSAH location (I60.0-I60.6). The usage of location-specific codes increased from 5.7% in 2015 to 11.2% in 2018. These codes accurately identified current aSAH (64%), any patient history of aSAH (84%), and any patient history of intracranial aneurysm (87%). The accuracy of identified outcome location was 53% in current aSAH, 72% for any history of aSAH, and 76% for any history of an intracranial aneurysm.

CONCLUSIONS

Researchers should use ICD10-CM codes with caution when attempting to detect active aSAH and/or aneurysm location.

Opportunity for Genotype-Guided Prescribing Among Adult Patients in 11 US Health Systems

The value of utilizing a multigene pharmacogenetic panel to tailor pharmacotherapy is contingent on the prevalence of prescribed medications with an actionable pharmacogenetic association. The Clinical Pharmacogenetics Implementation Consortium (CPIC) has categorized over 35 gene-drug pairs as "level A," for which there is sufficiently strong evidence to recommend that genetic information be used to guide drug prescribing. The opportunity to use genetic information to tailor pharmacotherapy among adult patients was determined by elucidating the exposure to CPIC level A drugs among 11 Implementing Genomics In Practice Network (IGNITE)-affiliated health systems across the US. Inpatient and/or outpatient electronic-prescribing data were collected between January 1, 2011 and December 31, 2016 for patients ≥ 18 years of age who had at least one medical encounter that was eligible for drug prescribing in a calendar year. A median of ~ 7.2 million adult patients was available for assessment of drug prescribing per year. From 2011 to 2016, the annual estimated prevalence of exposure to at least one CPIC level A drug prescribed to unique patients ranged between 15,719 (95% confidence interval (CI): 15,658-15,781) in 2011 to 17,335 (CI: 17,283-17,386) in 2016 per 100,000 patients. The estimated annual exposure to at least 2 drugs was above 7,200 per 100,000 patients in most years of the study, reaching an apex of 7,660 (CI: 7,632-7,687) per 100,000 patients in 2014. An estimated 4,748 per 100,000 prescribing events were potentially eligible for a genotype-guided intervention. Results from this study show that a significant portion of adults treated at medical institutions across the United States is exposed to medications for which genetic information, if available, should be used to guide prescribing.

Developing and Deploying a Scalable Computing Platform to Support MOOC Education in Clinical Data Science

One of the challenges of teaching applied data science courses is managing individual students' local computing environment. This is especially challenging when teaching massively open online courses (MOOCs) where students come from across the globe and have a variety of access to and types of computing systems. There are additional challenges with using sensitive health information for clinical data science education. Here we describe the development and performance of a computing platform developed to support a series of MOOCs in clinical data science. This platform was designed to restrict and log all access to health datasets while also being scalable, accessible, secure, privacy preserving, and easy to access. Over the 19 months the platform has been live it has supported the computation of more than 2300 students from 101 countries.

Recommendations for patient similarity classes: results of the AMIA 2019 workshop on defining patient similarity

Defining patient-to-patient similarity is essential for the development of precision medicine in clinical care and research. Conceptually, the identification of similar patient cohorts appears straightforward; however, universally accepted definitions remain elusive. Simultaneously, an explosion of vendors and published algorithms have emerged and all provide varied levels of functionality in identifying patient similarity categories. To provide clarity and a common framework for patient similarity, a workshop at the American Medical Informatics Association 2019 Annual Meeting was convened. This workshop included invited discussants from academics, the biotechnology industry, the FDA, and private practice oncology groups. Drawing from a broad range of backgrounds, workshop participants were able to coalesce around 4 major patient similarity classes: (1) feature, (2) outcome, (3) exposure, and (4) mixed-class. This perspective expands into these 4 subtypes more critically and offers the medical informatics community a means of communicating their work on this important topic.

Predictors of 90-Day Readmission Rate After Unruptured Intracranial Aneurysm Repair

OBJECTIVE

The repair of unruptured intracranial aneurysms has increased since 2000. In this study, we analyzed the Nationwide Readmission Database (NRD) to determine the rate of 90-day readmission. Our objective is to examine readmission trends after unruptured aneurysm repair.

METHODS

This study used the 2013 and 2014 NRD. Patient data included standard demographic, comorbidity, and payer information. We selected patients who had undergone microsurgical or endovascular repair for a nonruptured aneurysm. We excluded patients who were under 18 years of age, had a subarachnoid hemorrhage, or were discharged to home the same day. Readmission was calculated by counting the number of days between the end of the index visit and earliest readmission date.

RESULTS

A total of 2180 of 29,694 patients (7.34%) were readmitted within 90 days of their initial hospitalization. They were younger (mean, 52.6 years; 95% confidence interval [CI], 51.4-53.8) than patients not readmitted (mean, 57.4 years; 95% CI, 57.1-57.8; P < 0.0001). In total, endovascular repair was more frequent than microsurgery (79.8% vs. 20.2%, respectively). Mean days to readmission was 41.8 (95% CI, 39.7-43.9) and was higher for women (P < 0.0001). The odds ratio for readmission after an endovascular repair was 1.54 (95% CI, 1.27-1.86).

CONCLUSIONS

In this study of over 28,000 patients treated for an unruptured aneurysm, the 90-day readmission rate was 7.34%. Endovascular patients had higher odds of readmission than microsurgical patients. Patients with common medical comorbidities (hypertension, obesity, renal failure, and diabetes) were less likely to be readmitted than patients without those conditions.

Abstract WP353: Assessing the Accuracy of ICD-10 Codes for Ruptured Intracranial Aneurysm Location

The adoption of ICD10 in October 2015 offers important opportunities for administrative database and EHR-based aneurysm research as it includes more than twenty distinct codes for subarachnoid hemorrhage (SAH), for the first time labeling the specific location for common sites of aneurysm rupture. Aneurysm location is a significant risk factor for rupture, but was not specified in any previous ICD classification. This has limited the value of “big-data” research for aneurysm risk modeling. Currently, it is not clear how frequently - or accurately - the codes are being used in practice. This study reviewed three years of records (10/2015-9/2018) from the UCHealth system in Colorado to assess the accuracy and utility of these codes for stroke research. Over this time, ICD10 codes for SAH (I60.x) were used a total of 5,090 times in 1,842 patients. After removing non-aneurysmal SAH (I60.8), the majority (92.7%) of the codes had no location specified (I60.7, I60.9). Of the codes with a location (I60.00-I60.6), upon review of the clinical record 9 (2.5%) did not have any evidence of subarachnoid hemorrhage, 3 (0.8%) did not have an aneurysm, and 5 (1.4%) had a pseudoaneurysm. Of the 338 verified instances of aneurysmal subarachnoid hemorrhage, 82 (24%) had multiple aneurysms and were excluded from further analysis. Within those records that had only a single aneurysm 197/256 (77%) had the location coded correctly. Of the 23% that were incorrectly coded, 1 was coded as the correct artery on the wrong side, all remaining (n=58) were the wrong artery. Although ICD10 codes offers the possibility of more advanced analysis due to the inclusion of aneurysm location, based on these data, we found that codes specifying location are frequently incorrect. Future studies are needed to validate these findings in other settings. However, researchers should be cautious about their ability to detect aneurysm location from administrative billing data using ICD10 location mapping.

Opportunities and obstacles for deep learning in biology and medicine

Deep learning describes a class of machine learning algorithms that are capable of combining raw inputs into layers of intermediate features. These algorithms have recently shown impressive results across a variety of domains. Biology and medicine are data-rich disciplines, but the data are complex and often ill-understood. Hence, deep learning techniques may be particularly well suited to solve problems of these fields. We examine applications of deep learning to a variety of biomedical problems-patient classification, fundamental biological processes and treatment of patients-and discuss whether deep learning will be able to transform these tasks or if the biomedical sphere poses unique challenges. Following from an extensive literature review, we find that deep learning has yet to revolutionize biomedicine or definitively resolve any of the most pressing challenges in the field, but promising advances have been made on the prior state of the art. Even though improvements over previous baselines have been modest in general, the recent progress indicates that deep learning methods will provide valuable means for speeding up or aiding human investigation. Though progress has been made linking a specific neural network's prediction to input features, understanding how users should interpret these models to make testable hypotheses about the system under study remains an open challenge. Furthermore, the limited amount of labelled data for training presents problems in some domains, as do legal and privacy constraints on work with sensitive health records. Nonetheless, we foresee deep learning enabling changes at both bench and bedside with the potential to transform several areas of biology and medicine.

STRATEGIES FOR EQUITABLE PHARMACOGENOMIC-GUIDED WARFARIN DOSING AMONG EUROPEAN AND AFRICAN AMERICAN INDIVIDUALS IN A CLINICAL POPULATION

The blood thinner warfarin has a narrow therapeutic range and high inter- and intra-patient variability in therapeutic doses. Several studies have shown that pharmacogenomic variants help predict stable warfarin dosing. However, retrospective and randomized controlled trials that employ dosing algorithms incorporating pharmacogenomic variants under perform in African Americans. This study sought to determine if: 1) including additional variants associated with warfarin dose in African Americans, 2) predicting within single ancestry groups rather than a combined population, or 3) using percentage African ancestry rather than observed race, would improve warfarin dosing algorithms in African Americans. Using BioVU, the Vanderbilt University Medical Center biobank linked to electronic medical records, we compared 25 modeling strategies to existing algorithms using a cohort of 2,181 warfarin users (1,928 whites, 253 blacks). We found that approaches incorporating additional variants increased model accuracy, but not in clinically significant ways. Race stratification increased model fidelity for African Americans, but the improvement was small and not likely to be clinically significant. Use of percent African ancestry improved model fit in the context of race misclassification.

Harnessing next-generation informatics for personalizing medicine: a report from AMIA's 2014 Health Policy Invitational Meeting

The American Medical Informatics Association convened the 2014 Health Policy Invitational Meeting to develop recommendations for updates to current policies and to establish an informatics research agenda for personalizing medicine. In particular, the meeting focused on discussing informatics challenges related to personalizing care through the integration of genomic or other high-volume biomolecular data with data from clinical systems to make health care more efficient and effective. This report summarizes the findings (n = 6) and recommendations (n = 15) from the policy meeting, which were clustered into 3 broad areas: (1) policies governing data access for research and personalization of care; (2) policy and research needs for evolving data interpretation and knowledge representation; and (3) policy and research needs to ensure data integrity and preservation. The meeting outcome underscored the need to address a number of important policy and technical considerations in order to realize the potential of personalized or precision medicine in actual clinical contexts.

Phenotyping Adverse Drug Reactions: Statin-Related Myotoxicity

It is unclear the extent to which best practices for phenotyping disease states from electronic medical records (EMRs) translate to phenotyping adverse drug events. Here we use statin-induced myotoxicity as a case study to identify best practices in this area. We compared multiple phenotyping algorithms using administrative codes, laboratory measurements, and full-text keyword matching to identify statin-related myopathy from EMRs. Manual review of 300 deidentified EMRs with exposure to at least one statin, created a gold standard set of 124 cases and 176 controls. We tested algorithms using ICD-9 billing codes, laboratory measurements of creatine kinase (CK) and keyword searches of clinical notes and allergy lists. The combined keyword algorithms produced were the most accurate (PPV=86%, NPV=91%). Unlike in most disease phenotyping algorithms, addition of ICD9 codes or laboratory data did not appreciably increase algorithm accuracy. We conclude that phenotype algorithms for adverse drug events should consider text based approaches.

Rapid storage and retrieval of genomic intervals from a relational database system using nested containment lists

Efficient storage and retrieval of genomic annotations based on range intervals is necessary, given the amount of data produced by next-generation sequencing studies. The indexing strategies of relational database systems (such as MySQL) greatly inhibit their use in genomic annotation tasks. This has led to the development of stand-alone applications that are dependent on flat-file libraries. In this work, we introduce MyNCList, an implementation of the NCList data structure within a MySQL database. MyNCList enables the storage, update and rapid retrieval of genomic annotations from the convenience of a relational database system. Range-based annotations of 1 million variants are retrieved in under a minute, making this approach feasible for whole-genome annotation tasks.

Database URL:https://github.com/bushlab/mynclist

ICD-9 tobacco use codes are effective identifiers of smoking status

OBJECTIVE

To evaluate the validity of, characterize the usage of, and propose potential research applications for International Classification of Diseases, Ninth Revision (ICD-9) tobacco codes in clinical populations.

MATERIALS AND METHODS

Using data on cancer cases and cancer-free controls from Vanderbilt's biorepository, BioVU, we evaluated the utility of ICD-9 tobacco use codes to identify ever-smokers in general and high smoking prevalence (lung cancer) clinic populations. We assessed potential biases in documentation, and performed temporal analysis relating transitions between smoking codes to smoking cessation attempts. We also examined the suitability of these codes for use in genetic association analyses.

RESULTS

ICD-9 tobacco use codes can identify smokers in a general clinic population (specificity of 1, sensitivity of 0.32), and there is little evidence of documentation bias. Frequency of code transitions between 'current' and 'former' tobacco use was significantly correlated with initial success at smoking cessation (p<0.0001). Finally, code-based smoking status assignment is a comparable covariate to text-based smoking status for genetic association studies.

DISCUSSION

Our results support the use of ICD-9 tobacco use codes for identifying smokers in a clinical population. Furthermore, with some limitations, these codes are suitable for adjustment of smoking status in genetic studies utilizing electronic health records.

CONCLUSIONS

Researchers should not be deterred by the unavailability of full-text records to determine smoking status if they have ICD-9 code histories.