Electronic medical records as a tool in clinical pharmacology: opportunities and challenges

Machine-Learning Parsimonious Prediction Model for Diagnostic Screening of Severe Hematological Adverse Events in Cancer Patients Treated with PD-1/PD-L1 Inhibitors: Retrospective Observational Study by Using the Common Data Model

Background/Objectives: Earlier detection of severe immune-related hematological adverse events (irHAEs) in cancer patients treated with a PD-1 or PD-L1 inhibitor is critical to improving treatment outcomes. The study aimed to develop a simple machine learning (ML) model for predicting irHAEs associated with PD-1/PD-L1 inhibitors. Methods: We utilized the Observational Medical Outcomes Partnership-Common Data Model based on electronic medical records from a tertiary (KHMC) and a secondary (KHNMC) hospital in South Korea. Severe irHAEs were defined as Grades 3-5 by the Common Terminology Criteria for Adverse Events (version 5.0). The predictive model was developed using the KHMC dataset, and then cross-validated against an independent cohort (KHNMC). The full ML models were then simplified by selecting critical features based on the feature importance values (FIVs). Results: Overall, 397 and 255 patients were included in the primary (KHMC) and cross-validation (KHNMC) cohort, respectively. Among the tested ML algorithms, random forest achieved the highest accuracy (area under the receiver operating characteristic curve [AUROC] 0.88 for both cohorts). Parsimonious models reduced to 50% FIVs of the full models showed comparable performance to the full models (AUROC 0.83-0.86, p > 0.05). The KHMC and KHNMC parsimonious models shared common predictive features including furosemide, oxygen gas, piperacillin/tazobactam, and acetylcysteine. Conclusions: Considering the simplicity and adequate predictive performance, our simplified ML models might be easily implemented in clinical practice with broad applicability. Our model might enhance early diagnostic screening of irHAEs induced by PD-1/PD-L1 inhibitors, contributing to minimizing the risk of severe irHAEs and improving the effectiveness of cancer immunotherapy.

Leveraging a pharmacogenomics knowledgebase to formulate a drug response phenotype terminology for genomic medicine

MOTIVATION

Despite the increasing evidence of utility of genomic medicine in clinical practice, systematically integrating genomic medicine information and knowledge into clinical systems with a high-level of consistency, scalability and computability remains challenging. A comprehensive terminology is required for relevant concepts and the associated knowledge model for representing relationships. In this study, we leveraged PharmGKB, a comprehensive pharmacogenomics (PGx) knowledgebase, to formulate a terminology for drug response phenotypes that can represent relationships between genetic variants and treatments. We evaluated coverage of the terminology through manual review of a randomly selected subset of 200 sentences extracted from genetic reports that contained concepts for 'Genes and Gene Products' and 'Treatments'.

RESULTS

Results showed that our proposed drug response phenotype terminology could cover 96% of the drug response phenotypes in genetic reports. Among 18 653 sentences that contained both 'Genes and Gene Products' and 'Treatments', 3011 sentences were able to be mapped to a drug response phenotype in our proposed terminology, among which the most discussed drug response phenotypes were response (994), sensitivity (829) and survival (332). In addition, we were able to re-analyze genetic report context incorporating the proposed terminology and enrich our previously proposed PGx knowledge model to reveal relationships between genetic variants and treatments. In conclusion, we proposed a drug response phenotype terminology that enhanced structured knowledge representation of genomic medicine.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Computational drug repurposing based on electronic health records: a scoping review

Computational drug repurposing methods adapt Artificial intelligence (AI) algorithms for the discovery of new applications of approved or investigational drugs. Among the heterogeneous datasets, electronic health records (EHRs) datasets provide rich longitudinal and pathophysiological data that facilitate the generation and validation of drug repurposing. Here, we present an appraisal of recently published research on computational drug repurposing utilizing the EHR. Thirty-three research articles, retrieved from Embase, Medline, Scopus, and Web of Science between January 2000 and January 2022, were included in the final review. Four themes, (1) publication venue, (2) data types and sources, (3) method for data processing and prediction, and (4) targeted disease, validation, and released tools were presented. The review summarized the contribution of EHR used in drug repurposing as well as revealed that the utilization is hindered by the validation, accessibility, and understanding of EHRs. These findings can support researchers in the utilization of medical data resources and the development of computational methods for drug repurposing.

High-throughput framework for genetic analyses of adverse drug reactions using electronic health records

Understanding the contribution of genetic variation to drug response can improve the delivery of precision medicine. However, genome-wide association studies (GWAS) for drug response are uncommon and are often hindered by small sample sizes. We present a high-throughput framework to efficiently identify eligible patients for genetic studies of adverse drug reactions (ADRs) using “drug allergy” labels from electronic health records (EHRs). As a proof-of-concept, we conducted GWAS for ADRs to 14 common drug/drug groups with 81,739 individuals from Vanderbilt University Medical Center’s BioVU DNA Biobank. We identified 7 genetic loci associated with ADRs at P < 5 × 10⁻⁸, including known genetic associations such as CYP2D6 and OPRM1 for CYP2D6-metabolized opioid ADR. Additional expression quantitative trait loci and phenome-wide association analyses added evidence to the observed associations. Our high-throughput framework is both scalable and portable, enabling impactful pharmacogenomic research to improve precision medicine.

Adverse drug reactions are a considerable burden on the healthcare system. Genetic studies can improve our understanding of the pathophysiological mechanisms of adverse drug reactions but have been hindered by small sample sizes. Drug responses are less often recorded than physiological traits and common diseases. Here, we present a high-throughput framework to efficiently identify eligible patients for genetic studies of adverse drug reactions from electronic health records. We validated our approach by conducting genome-wide association studies for adverse reactions to 14 common drug/drug groups with 81,739 individuals from Vanderbilt University Medical Centre’s BioVU DNA Biobank, identifying 7 genetic loci associated with adverse drug reactions. Our high-throughput framework can enable impactful pharmacogenomic research to help develop clinical guidelines for the delivery of the right drug to the right person.

Integrating pharmacogenomics into the electronic health record by implementing genomic indicators

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.

A comparative study of different methods for automatic identification of clopidogrel-induced bleedings in electronic health records

Electronic health records (EHRs) linked with biobanks have been recognized as valuable data sources for pharmacogenomic studies, which require identification of patients with certain adverse drug reactions (ADRs) from a large population. Since manual chart review is costly and time-consuming, automatic methods to accurately identify patients with ADRs have been called for. In this study, we developed and compared different informatics approaches to identify ADRs from EHRs, using clopidogrel-induced bleeding as our case study. Three different types of methods were investigated: 1) rule-based methods; 2) machine learning-based methods; and 3) scoring function-based methods. Our results show that both machine learning and scoring methods are effective and the scoring method can achieve a high precision with a reasonable recall. We also analyzed the contributions of different types of features and found that the temporality information between clopidogrel and bleeding events, as well as textual evidence from physicians' assertion of the adverse events are helpful. We believe that our findings are valuable in advancing EHR-based pharmacogenomic studies.

Evaluating phecodes, clinical classification software, and ICD-9-CM codes for phenome-wide association studies in the electronic health record

OBJECTIVE

To compare three groupings of Electronic Health Record (EHR) billing codes for their ability to represent clinically meaningful phenotypes and to replicate known genetic associations. The three tested coding systems were the International Classification of Diseases, Ninth Revision, Clinical Modification (ICD-9-CM) codes, the Agency for Healthcare Research and Quality Clinical Classification Software for ICD-9-CM (CCS), and manually curated "phecodes" designed to facilitate phenome-wide association studies (PheWAS) in EHRs.

METHODS AND MATERIALS

We selected 100 disease phenotypes and compared the ability of each coding system to accurately represent them without performing additional groupings. The 100 phenotypes included 25 randomly-chosen clinical phenotypes pursued in prior genome-wide association studies (GWAS) and another 75 common disease phenotypes mentioned across free-text problem lists from 189,289 individuals. We then evaluated the performance of each coding system to replicate known associations for 440 SNP-phenotype pairs.

RESULTS

Out of the 100 tested clinical phenotypes, phecodes exactly matched 83, compared to 53 for ICD-9-CM and 32 for CCS. ICD-9-CM codes were typically too detailed (requiring custom groupings) while CCS codes were often not granular enough. Among 440 tested known SNP-phenotype associations, use of phecodes replicated 153 SNP-phenotype pairs compared to 143 for ICD-9-CM and 139 for CCS. Phecodes also generally produced stronger odds ratios and lower p-values for known associations than ICD-9-CM and CCS. Finally, evaluation of several SNPs via PheWAS identified novel potential signals, some seen in only using the phecode approach. Among them, rs7318369 in PEPD was associated with gastrointestinal hemorrhage.

CONCLUSION

Our results suggest that the phecode groupings better align with clinical diseases mentioned in clinical practice or for genomic studies. ICD-9-CM, CCS, and phecode groupings all worked for PheWAS-type studies, though the phecode groupings produced superior results.

Genome-wide study of resistant hypertension identified from electronic health records

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.

PheKB: a catalog and workflow for creating electronic phenotype algorithms for transportability

OBJECTIVE

Health care generated data have become an important source for clinical and genomic research. Often, investigators create and iteratively refine phenotype algorithms to achieve high positive predictive values (PPVs) or sensitivity, thereby identifying valid cases and controls. These algorithms achieve the greatest utility when validated and shared by multiple health care systems.Materials and Methods We report the current status and impact of the Phenotype KnowledgeBase (PheKB, http://phekb.org), an online environment supporting the workflow of building, sharing, and validating electronic phenotype algorithms. We analyze the most frequent components used in algorithms and their performance at authoring institutions and secondary implementation sites.

RESULTS

As of June 2015, PheKB contained 30 finalized phenotype algorithms and 62 algorithms in development spanning a range of traits and diseases. Phenotypes have had over 3500 unique views in a 6-month period and have been reused by other institutions. International Classification of Disease codes were the most frequently used component, followed by medications and natural language processing. Among algorithms with published performance data, the median PPV was nearly identical when evaluated at the authoring institutions (n = 44; case 96.0%, control 100%) compared to implementation sites (n = 40; case 97.5%, control 100%).

DISCUSSION

These results demonstrate that a broad range of algorithms to mine electronic health record data from different health systems can be developed with high PPV, and algorithms developed at one site are generally transportable to others.

CONCLUSION

By providing a central repository, PheKB enables improved development, transportability, and validity of algorithms for research-grade phenotypes using health care generated data.

Mining Retrospective Data for Virtual Prospective Drug Repurposing: L-DOPA and Age-related Macular Degeneration

BACKGROUND

Age-related macular degeneration (AMD) is a leading cause of visual loss among the elderly. A key cell type involved in AMD, the retinal pigment epithelium, expresses a G protein-coupled receptor that, in response to its ligand, L-DOPA, up-regulates pigment epithelia-derived factor, while down-regulating vascular endothelial growth factor. In this study we investigated the potential relationship between L-DOPA and AMD.

METHODS

We used retrospective analysis to compare the incidence of AMD between patients taking vs not taking L-DOPA. We analyzed 2 separate cohorts of patients with extensive medical records from the Marshfield Clinic (approximately 17,000 and approximately 20,000) and the Truven MarketScan outpatient and databases (approximately 87 million) patients. We used International Classification of Diseases, 9th Revision codes to identify AMD diagnoses and L-DOPA prescriptions to determine the relative risk of developing AMD and age of onset with or without an L-DOPA prescription.

RESULTS

In the retrospective analysis of patients without an L-DOPA prescription, AMD age of onset was 71.2, 71.3, and 71.3 in 3 independent retrospective cohorts. Age-related macular degeneration occurred significantly later in patients with an L-DOPA prescription, 79.4 in all cohorts. The odds ratio of developing AMD was also significantly negatively correlated by L-DOPA (odds ratio 0.78; confidence interval, 0.76-0.80; P <.001). Similar results were observed for neovascular AMD (P <.001).

CONCLUSIONS

Exogenous L-DOPA was protective against AMD. L-DOPA is normally produced in pigmented tissues, such as the retinal pigment epithelium, as a byproduct of melanin synthesis by tyrosinase. GPR143 is the only known L-DOPA receptor; it is therefore plausible that GPR143 may be a fruitful target to combat this devastating disease.

CYP450 genotype and pharmacogenetic association studies: a critical appraisal

Despite strong pharmacological support, association studies using genotype-predicted phenotype as a variable have yielded conflicting or inconclusive evidence to promote personalized pharmacotherapy. Unless the patient is a genotypic poor metabolizer, imputation of patient's metabolic capacity (or metabolic phenotype), a major factor in drug exposure-related clinical response, is a complex and highly challenging task because of limited number of alleles interrogated, population-specific differences in allele frequencies, allele-specific substrate-selectivity and importantly, phenoconversion mediated by co-medications and inflammatory co-morbidities that modulate the functional activity of drug metabolizing enzymes. Furthermore, metabolic phenotype and clinical outcomes are not binary functions; there is large intragenotypic and intraindividual variability. Therefore, the ability of association studies to identify relationships between genotype and clinical outcomes can be greatly enhanced by determining phenotype measures of study participants and/or by therapeutic drug monitoring to correlate drug concentrations with genotype and actual metabolic phenotype. To facilitate improved analysis and reporting of association studies, we propose acronyms with the prefixes ‘g’ (genotype-predicted phenotype) and ‘m’ (measured metabolic phenotype) to better describe this important variable of the study subjects. Inclusion of actually measured metabolic phenotype, and when appropriate therapeutic drug monitoring, promises to reveal relationships that may not be detected by using genotype alone as the variable.

Population-Level Prediction of Type 2 Diabetes From Claims Data and Analysis of Risk Factors

We present a new approach to population health, in which data-driven predictive models are learned for outcomes such as type 2 diabetes. Our approach enables risk assessment from readily available electronic claims data on large populations, without additional screening cost. Proposed model uncovers early and late-stage risk factors. Using administrative claims, pharmacy records, healthcare utilization, and laboratory results of 4.1 million individuals between 2005 and 2009, an initial set of 42,000 variables were derived that together describe the full health status and history of every individual. Machine learning was then used to methodically enhance predictive variable set and fit models predicting onset of type 2 diabetes in 2009-2011, 2010-2012, and 2011-2013. We compared the enhanced model with a parsimonious model consisting of known diabetes risk factors in a real-world environment, where missing values are common and prevalent. Furthermore, we analyzed novel and known risk factors emerging from the model at different age groups at different stages before the onset. Parsimonious model using 21 classic diabetes risk factors resulted in area under ROC curve (AUC) of 0.75 for diabetes prediction within a 2-year window following the baseline. The enhanced model increased the AUC to 0.80, with about 900 variables selected as predictive (p < 0.0001 for differences between AUCs). Similar improvements were observed for models predicting diabetes onset 1-3 years and 2-4 years after baseline. The enhanced model improved positive predictive value by at least 50% and identified novel surrogate risk factors for type 2 diabetes, such as chronic liver disease (odds ratio [OR] 3.71), high alanine aminotransferase (OR 2.26), esophageal reflux (OR 1.85), and history of acute bronchitis (OR 1.45). Liver risk factors emerge later in the process of diabetes development compared with obesity-related factors such as hypertension and high hemoglobin A1c. In conclusion, population-level risk prediction for type 2 diabetes using readily available administrative data is feasible and has better prediction performance than classical diabetes risk prediction algorithms on very large populations with missing data. The new model enables intervention allocation at national scale quickly and accurately and recovers potentially novel risk factors at different stages before the disease onset.

Ease of adoption of clinical natural language processing software: An evaluation of five systems

OBJECTIVE

In recognition of potential barriers that may inhibit the widespread adoption of biomedical software, the 2014 i2b2 Challenge introduced a special track, Track 3 - Software Usability Assessment, in order to develop a better understanding of the adoption issues that might be associated with the state-of-the-art clinical NLP systems. This paper reports the ease of adoption assessment methods we developed for this track, and the results of evaluating five clinical NLP system submissions.

MATERIALS AND METHODS

A team of human evaluators performed a series of scripted adoptability test tasks with each of the participating systems. The evaluation team consisted of four "expert evaluators" with training in computer science, and eight "end user evaluators" with mixed backgrounds in medicine, nursing, pharmacy, and health informatics. We assessed how easy it is to adopt the submitted systems along the following three dimensions: communication effectiveness (i.e., how effective a system is in communicating its designed objectives to intended audience), effort required to install, and effort required to use. We used a formal software usability testing tool, TURF, to record the evaluators' interactions with the systems and 'think-aloud' data revealing their thought processes when installing and using the systems and when resolving unexpected issues.

RESULTS

Overall, the ease of adoption ratings that the five systems received are unsatisfactory. Installation of some of the systems proved to be rather difficult, and some systems failed to adequately communicate their designed objectives to intended adopters. Further, the average ratings provided by the end user evaluators on ease of use and ease of interpreting output are -0.35 and -0.53, respectively, indicating that this group of users generally deemed the systems extremely difficult to work with. While the ratings provided by the expert evaluators are higher, 0.6 and 0.45, respectively, these ratings are still low indicating that they also experienced considerable struggles.

DISCUSSION

The results of the Track 3 evaluation show that the adoptability of the five participating clinical NLP systems has a great margin for improvement. Remedy strategies suggested by the evaluators included (1) more detailed and operation system specific use instructions; (2) provision of more pertinent onscreen feedback for easier diagnosis of problems; (3) including screen walk-throughs in use instructions so users know what to expect and what might have gone wrong; (4) avoiding jargon and acronyms in materials intended for end users; and (5) packaging prerequisites required within software distributions so that prospective adopters of the software do not have to obtain each of the third-party components on their own.

Combining billing codes, clinical notes, and medications from electronic health records provides superior phenotyping performance

OBJECTIVE

To evaluate the phenotyping performance of three major electronic health record (EHR) components: International Classification of Disease (ICD) diagnosis codes, primary notes, and specific medications.

MATERIALS AND METHODS

We conducted the evaluation using de-identified Vanderbilt EHR data. We preselected ten diseases: atrial fibrillation, Alzheimer's disease, breast cancer, gout, human immunodeficiency virus infection, multiple sclerosis, Parkinson's disease, rheumatoid arthritis, and types 1 and 2 diabetes mellitus. For each disease, patients were classified into seven categories based on the presence of evidence in diagnosis codes, primary notes, and specific medications. Twenty-five patients per disease category (a total number of 175 patients for each disease, 1750 patients for all ten diseases) were randomly selected for manual chart review. Review results were used to estimate the positive predictive value (PPV), sensitivity, andF-score for each EHR component alone and in combination.

RESULTS

The PPVs of single components were inconsistent and inadequate for accurately phenotyping (0.06-0.71). Using two or more ICD codes improved the average PPV to 0.84. We observed a more stable and higher accuracy when using at least two components (mean ± standard deviation: 0.91 ± 0.08). Primary notes offered the best sensitivity (0.77). The sensitivity of ICD codes was 0.67. Again, two or more components provided a reasonably high and stable sensitivity (0.59 ± 0.16). Overall, the best performance (Fscore: 0.70 ± 0.12) was achieved by using two or more components. Although the overall performance of using ICD codes (0.67 ± 0.14) was only slightly lower than using two or more components, its PPV (0.71 ± 0.13) is substantially worse (0.91 ± 0.08).

CONCLUSION

Multiple EHR components provide a more consistent and higher performance than a single one for the selected phenotypes. We suggest considering multiple EHR components for future phenotyping design in order to obtain an ideal result.

Extracting research-quality phenotypes from electronic health records to support precision medicine

The convergence of two rapidly developing technologies - high-throughput genotyping and electronic health records (EHRs) - gives scientists an unprecedented opportunity to utilize routine healthcare data to accelerate genomic discovery. Institutions and healthcare systems have been building EHR-linked DNA biobanks to enable such a vision. However, the precise extraction of detailed disease and drug-response phenotype information hidden in EHRs is not an easy task. EHR-based studies have successfully replicated known associations, made new discoveries for diseases and drug response traits, rapidly contributed cases and controls to large meta-analyses, and demonstrated the potential of EHRs for broad-based phenome-wide association studies. In this review, we summarize the advantages and challenges of repurposing EHR data for genetic research. We also highlight recent notable studies and novel approaches to provide an overview of advanced EHR-based phenotyping.

Systems medicine: evolution of systems biology from bench to bedside

High-throughput experimental techniques for generating genomes, transcriptomes, proteomes, metabolomes, and interactomes have provided unprecedented opportunities to interrogate biological systems and human diseases on a global level. Systems biology integrates the mass of heterogeneous high-throughput data and predictive computational modeling to understand biological functions as system-level properties. Most human diseases are biological states caused by multiple components of perturbed pathways and regulatory networks rather than individual failing components. Systems biology not only facilitates basic biological research but also provides new avenues through which to understand human diseases, identify diagnostic biomarkers, and develop disease treatments. At the same time, systems biology seeks to assist in drug discovery, drug optimization, drug combinations, and drug repositioning by investigating the molecular mechanisms of action of drugs at a system's level. Indeed, systems biology is evolving to systems medicine as a new discipline that aims to offer new approaches for addressing the diagnosis and treatment of major human diseases uniquely, effectively, and with personalized precision.

Intelligent use and clinical benefits of electronic health records in rheumatoid arthritis

In the past 10 years, electronic health records (EHRs) have had growing impact in clinical care. EHRs efficiently capture and reuse clinical information, which can directly benefit patient care by guiding treatments and providing effective reminders for best practices. The increased adoption has also lead to more complex implementations, including robust, disease-specific tools, such as for rheumatoid arthritis (RA). In addition, the data collected through normal clinical care is also used in secondary research, helping to refine patient treatment for the future. Although few studies have directly demonstrated benefits for direct clinical care of RA, the opposite is true for EHR-based research - RA has been a particularly fertile ground for clinical and genomic research that have leveraged typically advanced informatics methods to accurately define RA populations. We discuss the clinical impact of EHRs in RA treatment and their impact on secondary research, and provide recommendations for improved utility in future EHR installations.

The promise of psychiatric pharmacogenomics

Clinicians already face "personalized" medicine every day while experiencing the great variation in toxicities and drug efficacy among individual patients. Pharmacogenetics studies are the platform for discovering the DNA determinants of variability in drug response and tolerability. Research now focuses on the genome after its beginning with analyses of single genes. Therapeutic outcomes from several psychotropic drugs have been weakly linked to specific genetic variants without independent replication. Drug side effects show stronger associations to genetic variants, including human leukocyte antigen loci with carbamazepine-induced dermatologic outcome and MC4R with atypical antipsychotic weight gain. Clinical implementation has proven challenging, with barriers including a lack of replicable prospective evidence for clinical utility required for altering medical care. More recent studies show promising approaches for reducing these barriers to routine incorporation of pharmacogenetics data into clinical care.

Electronic health records, adoption, quality of care, legal and privacy issues and their implementation in emergency departments

Recently, the healthcare sector has shown a growing interest in information technologies. Two popular health IT (HIT) products are the electronic health record (EHR) and health information exchange (HIE) networks. The introduction of these tools is believed to improve care, but has also raised some important questions and legal and privacy issues. The implementation of these systems has not gone smoothly, and still faces some considerable barriers. This article reviews EHR and HIE to address these obstacles, and analyzes the current state of development and adoption in various countries around the world. Moreover, legal and ethical concerns that may be encountered by EHR users and purchasers are reviewed. Finally, links and interrelations between EHR and HIE and several quality of care issues in today's healthcare domain are examined with a focus on EHR and HIE in the emergency department (ED), whose unique characteristics makes it an environment in which the implementation of such technology may be a major contributor to health, but also faces substantial challenges. The paper ends with a discussion of specific policy implications and recommendations based on an examination of the current limitations of these systems.

Design patterns for the development of electronic health record-driven phenotype extraction algorithms

BACKGROUND

Design patterns, in the context of software development and ontologies, provide generalized approaches and guidance to solving commonly occurring problems, or addressing common situations typically informed by intuition, heuristics and experience. While the biomedical literature contains broad coverage of specific phenotype algorithm implementations, no work to date has attempted to generalize common approaches into design patterns, which may then be distributed to the informatics community to efficiently develop more accurate phenotype algorithms.

METHODS

Using phenotyping algorithms stored in the Phenotype KnowledgeBase (PheKB), we conducted an independent iterative review to identify recurrent elements within the algorithm definitions. We extracted and generalized recurrent elements in these algorithms into candidate patterns. The authors then assessed the candidate patterns for validity by group consensus, and annotated them with attributes.

RESULTS

A total of 24 electronic Medical Records and Genomics (eMERGE) phenotypes available in PheKB as of 1/25/2013 were downloaded and reviewed. From these, a total of 21 phenotyping patterns were identified, which are available as an online data supplement.

CONCLUSIONS

Repeatable patterns within phenotyping algorithms exist, and when codified and cataloged may help to educate both experienced and novice algorithm developers. The dissemination and application of these patterns has the potential to decrease the time to develop algorithms, while improving portability and accuracy.

Accuracy of administratively-assigned ancestry for diverse populations in an electronic medical record-linked biobank

Recently, the development of biobanks linked to electronic medical records has presented new opportunities for genetic and epidemiological research. Studies based on these resources, however, present unique challenges, including the accurate assignment of individual-level population ancestry. In this work we examine the accuracy of administratively-assigned race in diverse populations by comparing assigned races to genetically-defined ancestry estimates. Using 220 ancestry informative markers, we generated principal components for patients in our dataset, which were used to cluster patients into groups based on genetic ancestry. Consistent with other studies, we find a strong overall agreement (Kappa  = 0.872) between genetic ancestry and assigned race, with higher rates of agreement for African-descent and European-descent assignments, and reduced agreement for Hispanic, East Asian-descent, and South Asian-descent assignments. These results suggest caution when selecting study samples of non-African and non-European backgrounds when administratively-assigned race from biobanks is used.

Creation and Validation of an EMR-based Algorithm for Identifying Major Adverse Cardiac Events while on Statins

Statin medications are often prescribed to ameliorate a patient's risk of cardiovascular events due in part to cholesterol reduction. We developed and evaluated an algorithm that can accurately identify subjects with major adverse cardiac events (MACE) while on statins using electronic medical record (EMR) data. The algorithm also identifies subjects experiencing their first MACE while on statins for primary prevention. The algorithm achieved 90% to 97% PPVs in identification of MACE cases as compared against physician review. By applying the algorithm to EMR data in BioVU, cases and controls were identified and used subsequently to replicate known associations with eight genetic variants. We replicated 6/8 previously reported genetic associations with cardiovascular diseases or lipid metabolism disorders. Our results demonstrated that the algorithm can be used to accurately identify subjects with MACE and MACE while on statins. Consequently, future e studies can be conducted to investigate and validate the relationship between statins and MACE using real-world clinical data.

A review of approaches to identifying patient phenotype cohorts using electronic health records

Objective

To summarize literature describing approaches aimed at automatically identifying patients with a common phenotype.

Materials and methods

We performed a review of studies describing systems or reporting techniques developed for identifying cohorts of patients with specific phenotypes. Every full text article published in (1) Journal of American Medical Informatics Association, (2) Journal of Biomedical Informatics, (3) Proceedings of the Annual American Medical Informatics Association Symposium, and (4) Proceedings of Clinical Research Informatics Conference within the past 3 years was assessed for inclusion in the review. Only articles using automated techniques were included.

Results

Ninety-seven articles met our inclusion criteria. Forty-six used natural language processing (NLP)-based techniques, 24 described rule-based systems, 41 used statistical analyses, data mining, or machine learning techniques, while 22 described hybrid systems. Nine articles described the architecture of large-scale systems developed for determining cohort eligibility of patients.

Discussion

We observe that there is a rise in the number of studies associated with cohort identification using electronic medical records. Statistical analyses or machine learning, followed by NLP techniques, are gaining popularity over the years in comparison with rule-based systems.

Conclusions

There are a variety of approaches for classifying patients into a particular phenotype. Different techniques and data sources are used, and good performance is reported on datasets at respective institutions. However, no system makes comprehensive use of electronic medical records addressing all of their known weaknesses.

Integration of genomics into the electronic health record: mapping terra incognita

Successfully realizing the vision of genomic medicine will require management of large amounts of complex data. The electronic health record (EHR) is destined to play a critical role in the translation of genomic information into clinical care. The papers in this special issue explore the challenges associated with the implementation of genomics in the EHR. The proposed solutions are meant to provide guidance for those responsible for moving genomics into the clinic.

Systems medicine: helping us understand the complexity of disease

Advances in genomics and other -omic fields in the last decade have resulted in unprecedented volumes of complex data now being available. These data can enable physicians to provide their patients with care that is more personalized, predictive, preventive and participatory. The expertise required to manage and understand this data is to be found in fields outside of medical science, thus multidisciplinary collaboration coupled to a systems approach is key to unlocking its potential, with concomitant new ways of working. Systems medicine can build on the successes in the field of systems biology, recognizing the human body as the multidimensional network of networks that it is. While systems medicine can provide a conceptual and theoretical framework, its practical goal is to provide physicians the tools necessary for harnessing the rapid advances in basic biomedical science into their routine clinical arsenal.

Characterization of schizophrenia adverse drug interactions through a network approach and drug classification

Antipsychotic drugs are medications commonly for schizophrenia (SCZ) treatment, which include two groups: typical and atypical. SCZ patients have multiple comorbidities, and the coadministration of drugs is quite common. This may result in adverse drug-drug interactions, which are events that occur when the effect of a drug is altered by the coadministration of another drug. Therefore, it is important to provide a comprehensive view of these interactions for further coadministration improvement. Here, we extracted SCZ drugs and their adverse drug interactions from the DrugBank and compiled a SCZ-specific adverse drug interaction network. This network included 28 SCZ drugs, 241 non-SCZs, and 991 interactions. By integrating the Anatomical Therapeutic Chemical (ATC) classification with the network analysis, we characterized those interactions. Our results indicated that SCZ drugs tended to have more adverse drug interactions than other drugs. Furthermore, SCZ typical drugs had significant interactions with drugs of the "alimentary tract and metabolism" category while SCZ atypical drugs had significant interactions with drugs of the categories "nervous system" and "antiinfectives for systemic uses." This study is the first to characterize the adverse drug interactions in the course of SCZ treatment and might provide useful information for the future SCZ treatment.

Stem cell therapy for chronic heart failure: an updated appraisal

INTRODUCTION

Significant advances have been made to understand the mechanisms involved in cardiac cell-based therapies. The early translational application of basic science knowledge has led to several animal and human clinical trials. The initial promising beneficial effect of stem cells on cardiac function restoration has been eclipsed by the inability of animal studies to translate into sustained clinical improvements in human clinical trials.

AREAS COVERED

In this review, the authors cover an updated overview of various stem cell populations used in chronic heart failure. A critical review of clinical trials conducted in advanced heart failure patients is proposed, and finally promising avenues for developments in the field of cardiac cell-based therapies are presented.

EXPERT OPINION

Several questions remain unanswered, and this limits our ability to understand basic mechanisms involved in stem cell therapeutics. Human studies have revealed critical unresolved issues. Further elucidation of the proper timing, mode delivery and prosurvival factors is imperative, if the field is to advance. The limited benefits seen to date are simply not enough if the potential for substantial recovery of nonfunctioning myocardium is to be realized.

Cardiovascular pharmacogenomics: the future of cardiovascular therapeutics?

Responses to drug therapy vary from benefit to no effect to adverse effects which can be serious or occasionally fatal. Increasing evidence supports the idea that genetic variants can play a major role in this spectrum of responses. Well-studied examples in cardiovascular therapeutics include predictors of steady-state warfarin dosage, predictors of reduced efficacy among patients receiving clopidogrel for drug eluting stents, and predictors of some serious adverse drug effects. This review summarizes contemporary approaches to identifying and validating genetic predictors of variability in response to drug treatment. Approaches to incorporating this new knowledge into clinical care, and the barriers to this concept, are addressed.

Inclusion of pediatric samples in an opt-out biorepository linking DNA to de-identified medical records: pediatric BioVU

The Vanderbilt DNA repository, BioVU, links DNA from leftover clinical blood samples to de-identified electronic medical records (EMRs). After initiating adult sample collection, pediatric extension required consideration of ethical concerns specific to pediatrics and implementation of specialized DNA extraction methods. In the first year of pediatric sample collection, more than 11,000 samples from individuals younger than 18 years were included. We compared data from the pediatric BioVU cohort with those from the overall Vanderbilt University Medical Center pediatric population and found similar demographic characteristics; however, the BioVU cohort had higher rates of select diseases, medication exposures, and laboratory testing, demonstrating enriched representation of severe or chronic disease. The fact that the sample accumulation is not balanced may accelerate research in some cohorts while limiting the study of relatively benign conditions and the accrual of unaffected and unbiased control samples. BioVU represents a feasible model for pediatric DNA biobanking but involves both ethical and practical considerations specific to the pediatric population.

Omics and drug response

A new generation of technologies commonly named omics permits assessment of the entirety of the components of biological systems and produces an explosion of data and a major shift in our concepts of disease. These technologies will likely shape the future of health care. One aspect of these advances is that the data generated document the uniqueness of each human being in regard to disease risk and treatment response. These developments have reemphasized the concept of personalized medicine. Here we review the impact of omics technologies on one key aspect of personalized medicine: the individual drug response. We describe how knowledge of different omics may affect treatment decisions, namely drug choice and drug dose, and how it can be used to improve clinical outcomes.