The emerging role of electronic medical records in pharmacogenomics

CYP2C19 Loss-of-Function Variants Associated With Long-Term Ischemic Stroke Events During Clopidogrel Treatment in the Chinese Population

This study aims to determine whether CYP2C19 loss-of-function (LoF) variants were associated with long-term ischemic stroke risk in Chinese primary care patients treated with clopidogrel. Patients treated with clopidogrel were ascertained from Chinese electronic medical records linked with a biobank for a retrospective cohort study. Their medical information was examined for the period from January 2018 to December 2021. Two CYP2C19 major loss of function variants (*2:rs4244285 and *3: rs4986893) were genotyped. The clinical outcome was ischemic stroke event. Cox regression analysis was used to evaluate the association between the occurrence of ischemic stroke events and CYP2C19 LoF variants. Covariates included age, gender, body mass index, prior ischemic stroke, transient ischemic attack, hypertension, diabetes mellitus, hyperlipoidemia, smoke status, aspirin use, proton-pump inhibitor use, and statin use. Of the 1,141 patients included in the clopidogrel therapy cohort, 61.9% carried at least one CYP2C19 LoF variant. During a median follow-up period of 12 months, 103 patients (9.0%) had an ischemic stroke. After adjusting for other risk factors, carriers of CYP2C19 LoF variants had significantly higher risk of ischemic stroke compared with non-carriers (hazard ratio: 1.64, 95% confidence interval: 1.06-2.53, P = 0.025). This pharmacogenetic study of clopidogrel provides novel insights into the association between the CYP2C19 LoF variant and long-term stroke risk. We established that there is still a need for CYP2C19 genotype-guided personalized antiplatelet therapy in those who have returned to the primary care setting for clopidogrel prescription.

From Paper Files to Web-Based Application for Data-Driven Monitoring of HIV Programs: Nigeria's Journey to a National Data Repository for Decision-Making and Patient Care

BACKGROUND

Timely and reliable data are crucial for clinical, epidemiologic, and program management decision making. Electronic health information systems provide platforms for managing large longitudinal patient records. Nigeria implemented the National Data Repository (NDR) to create a central data warehouse of all people living with human immunodeficiency virus (PLHIV) while providing useful functionalities to aid decision making at different levels of program implementation.

OBJECTIVE

We describe the Nigeria NDR and its development process, including its use for surveillance, research, and national HIV program monitoring toward achieving HIV epidemic control.

METHODS

Stakeholder engagement meetings were held in 2013 to gather information on data elements and vocabulary standards for reporting patient-level information, technical infrastructure, human capacity requirements, and information flow. Findings from these meetings guided the development of the NDR. An implementation guide provided common terminologies and data reporting structures for data exchange between the NDR and the electronic medical record (EMR) systems. Data from the EMR were encoded in extensible markup language and sent to the NDR over secure hypertext transfer protocol after going through a series of validation processes.

RESULTS

By June 30, 2021, the NDR had up-to-date records of 1,477,064 (94.4%) patients receiving HIV treatment across 1,985 health facilities, of which 1,266,512 (85.7%) patient records had fingerprint template data to support unique patient identification and record linkage to prevent registration of the same patient under different identities. Data from the NDR was used to support HIV program monitoring, case-based surveillance and production of products like the monthly lists of patients who have treatment interruptions and dashboards for monitoring HIV test and start.

CONCLUSION

The NDR enabled the availability of reliable and timely data for surveillance, research, and HIV program monitoring to guide program improvements to accelerate progress toward epidemic control.

An Alternative Application of Natural Language Processing to Express a Characteristic Feature of Diseases in Japanese Medical Records

BACKGROUND

Owing to the linguistic situation, Japanese natural language processing (NLP) requires morphological analyses for word segmentation using dictionary techniques.

OBJECTIVE

We aimed to clarify whether it can be substituted with an open-end discovery-based NLP (OD-NLP), which does not use any dictionary techniques.

METHODS

Clinical texts at the first medical visit were collected for comparison of OD-NLP with word dictionary-based-NLP (WD-NLP). Topics were generated in each document using a topic model, which later corresponded to the respective diseases determined in International Statistical Classification of Diseases and Related Health Problems 10 revision. The prediction accuracy and expressivity of each disease were examined in equivalent number of entities/words after filtration with either term frequency and inverse document frequency (TF-IDF) or dominance value (DMV).

RESULTS

In documents from 10,520 observed patients, 169,913 entities and 44,758 words were segmented using OD-NLP and WD-NLP, simultaneously. Without filtering, accuracy and recall levels were low, and there was no difference in the harmonic mean of the F-measure between NLPs. However, physicians reported OD-NLP contained more meaningful words than WD-NLP. When datasets were created in an equivalent number of entities/words with TF-IDF, F-measure in OD-NLP was higher than WD-NLP at lower thresholds. When the threshold increased, the number of datasets created decreased, resulting in increased values of F-measure, although the differences disappeared. Two datasets near the maximum threshold showing differences in F-measure were examined whether their topics were associated with diseases. The results showed that more diseases were found in OD-NLP at lower thresholds, indicating that the topics described characteristics of diseases. The superiority remained as much as that of TF-IDF when filtration was changed to DMV.

CONCLUSION

The current findings prefer the use of OD-NLP to express characteristics of diseases from Japanese clinical texts and may help in the construction of document summaries and retrieval in clinical settings.

Challenges and opportunities for mining adverse drug reactions: perspectives from pharma, regulatory agencies, healthcare providers and consumers

Monitoring drug safety is a central concern throughout the drug life cycle. Information about toxicity and adverse events is generated at every stage of this life cycle, and stakeholders have a strong interest in applying text mining and artificial intelligence (AI) methods to manage the ever-increasing volume of this information. Recognizing the importance of these applications and the role of challenge evaluations to drive progress in text mining, the organizers of BioCreative VII (Critical Assessment of Information Extraction in Biology) convened a panel of experts to explore 'Challenges in Mining Drug Adverse Reactions'. This article is an outgrowth of the panel; each panelist has highlighted specific text mining application(s), based on their research and their experiences in organizing text mining challenge evaluations. While these highlighted applications only sample the complexity of this problem space, they reveal both opportunities and challenges for text mining to aid in the complex process of drug discovery, testing, marketing and post-market surveillance. Stakeholders are eager to embrace natural language processing and AI tools to help in this process, provided that these tools can be demonstrated to add value to stakeholder workflows. This creates an opportunity for the BioCreative community to work in partnership with regulatory agencies, pharma and the text mining community to identify next steps for future challenge evaluations.

Efficient Evaluation of Prediction Rules in Semi-Supervised Settings under Stratified Sampling

In many contemporary applications, large amounts of unlabeled data are readily available while labeled examples are limited. There has been substantial interest in semi-supervised learning (SSL) which aims to leverage unlabeled data to improve estimation or prediction. However, current SSL literature focuses primarily on settings where labeled data is selected uniformly at random from the population of interest. Stratified sampling, while posing additional analytical challenges, is highly applicable to many real world problems. Moreover, no SSL methods currently exist for estimating the prediction performance of a fitted model when the labeled data is not selected uniformly at random. In this paper, we propose a two-step SSL procedure for evaluating a prediction rule derived from a working binary regression model based on the Brier score and overall misclassification rate under stratified sampling. In step I, we impute the missing labels via weighted regression with nonlinear basis functions to account for stratified sampling and to improve efficiency. In step II, we augment the initial imputations to ensure the consistency of the resulting estimators regardless of the specification of the prediction model or the imputation model. The final estimator is then obtained with the augmented imputations. We provide asymptotic theory and numerical studies illustrating that our proposals outperform their supervised counterparts in terms of efficiency gain. Our methods are motivated by electronic health record (EHR) research and validated with a real data analysis of an EHR-based study of diabetic neuropathy.

Combining K-72 Hepatic Failure with 15 Individual T-Codes to Identify Patients with Idiosyncratic Drug-Induced Liver Injury in the Electronic Medical Record

BACKGROUND

The aim of this study was to determine the utility of combining three K72 codes (hepatic failure) with 15 individual T-Codes (drug toxicity/poisoning) to identify potential DILI cases.

METHODS

The EMR was searched for encounters that had a K72 code combined with a T-code that also met minimal liver injury laboratory criteria between 10/1/15 and 9/30/18. After manual chart review, a DILIN expert opinion causality score (1-5) was assigned to each case.

RESULTS

Among the 345 patient encounters identified, mean age was 57 years, 53% were male, and 89% Caucasian. Thirty-seven cases (10.7%) were adjudicated as probable DILI with antibiotics being the most frequently identified suspect drugs. Of the 308 non-DILI cases, liver injury was most commonly due to congestive hepatopathy (38%) and hepatic metastases (15%). The probable-DILI cases were significantly more likely to have hepatocellular liver injury (57% vs 32.5%, p = 0.01), higher total bilirubin levels (7.7 vs 4.6 mg/dl, p = 0.03), and more severe liver injury scores (p < 0.01). The K72.0 (acute/ subacute hepatic failure) yielded the most DILI cases (29) compared to K72.9 (13) and K72.1 (0). The positive predictive value of the searching algorithm was 10.7% and improved to 15% when using only the K72.0 codes.

CONCLUSIONS

K72 codes combined with drug poisoning T-codes had a low positive predictive value in identifying patients with idiosyncratic DILI. These data support further refinement of ICD-10-based algorithms to detect DILI cases in the EMR.

An electronic health record (EHR) phenotype algorithm to identify patients with attention deficit hyperactivity disorders (ADHD) and psychiatric comorbidities

Background

In over half of pediatric cases, ADHD presents with comorbidities, and often, it is unclear whether the symptoms causing impairment are due to the comorbidity or the underlying ADHD. Comorbid conditions increase the likelihood for a more severe and persistent course and complicate treatment decisions. Therefore, it is highly important to establish an algorithm that identifies ADHD and comorbidities in order to improve research on ADHD using biorepository and other electronic record data.

Methods

It is feasible to accurately distinguish between ADHD in isolation from ADHD with comorbidities using an electronic algorithm designed to include other psychiatric disorders. We sought to develop an EHR phenotype algorithm to discriminate cases with ADHD in isolation from cases with ADHD with comorbidities more effectively for efficient future searches in large biorepositories. We developed a multi-source algorithm allowing for a more complete view of the patient’s EHR, leveraging the biobank of the Center for Applied Genomics (CAG) at Children’s Hospital of Philadelphia (CHOP). We mined EHRs from 2009 to 2016 using International Statistical Classification of Diseases and Related Health Problems (ICD) codes, medication history and keywords specific to ADHD, and comorbid psychiatric disorders to facilitate genotype-phenotype correlation efforts. Chart abstractions and behavioral surveys added evidence in support of the psychiatric diagnoses. Most notably, the algorithm did not exclude other psychiatric disorders, as is the case in many previous algorithms. Controls lacked psychiatric and other neurological disorders. Participants enrolled in various CAG studies at CHOP and completed a broad informed consent, including consent for prospective analyses of EHRs. We created and validated an EHR-based algorithm to classify ADHD and comorbid psychiatric status in a pediatric healthcare network to be used in future genetic analyses and discovery-based studies.

Results

In this retrospective case-control study that included data from 51,293 subjects, 5840 ADHD cases were discovered of which 46.1% had ADHD alone and 53.9% had ADHD with psychiatric comorbidities. Our primary study outcome was to examine whether the algorithm could identify and distinguish ADHD exclusive cases from ADHD comorbid cases. The results indicate ICD codes coupled with medication searches revealed the most cases. We discovered ADHD-related keywords did not increase yield. However, we found including ADHD-specific medications increased our number of cases by 21%. Positive predictive values (PPVs) were 95% for ADHD cases and 93% for controls.

Conclusion

We established a new algorithm and demonstrated the feasibility of the electronic algorithm approach to accurately diagnose ADHD and comorbid conditions, verifying the efficiency of our large biorepository for further genetic discovery-based analyses.

Trial registration

ClinicalTrials.gov, NCT02286817. First posted on 10 November 2014. ClinicalTrials.gov, NCT02777931. First posted on 19 May 2016. ClinicalTrials.gov, NCT03006367. First posted on 30 December 2016. ClinicalTrials.gov, NCT02895906. First posted on 12 September 2016.

Supplementary Information

The online version contains supplementary material available at 10.1186/s11689-022-09447-9.

CYP2D6 phenotypes and opioid metabolism: the path to personalized analgesia

INTRODUCTION

Opioids play a fundamental role in chronic pain, especially considering when 1 of 5 Europeans adults, even more in older females, suffer from it. However, half of them do not reach an adequate pain relief. Could pharmacogenomics help to choose the most appropriate analgesic drug?

AREAS COVERED

The objective of the present narrative review was to assess the influence of cytochrome P450 2D6 (CYP2D6) phenotypes on pain relief, analgesic tolerability, and potential opioid misuse. Until December 2021, a literature search was conducted through the MEDLINE, PubMed database, including papers from the last 10 years. CYP2D6 plays a major role in metabolism that directly impacts on opioid (tramadol, codeine, or oxycodone) concentration with differences between sexes, with a female trend toward poorer pain control. In fact, CYP2D6 gene variants are the most actionable to be translated into clinical practice according to regulatory drug agencies and international guidelines.

EXPERT OPINION

CYP2D6 genotype can influence opioids' pharmacokinetics, effectiveness, side effects, and average opioid dose. This knowledge needs to be incorporated in pain management. Environmental factors, psychological together with genetic factors, under a sex perspective, must be considered when you are selecting the most personalized pain therapy for your patients.

Prior Adaptive Semi-supervised Learning with Application to EHR Phenotyping

Electronic Health Record (EHR) data, a rich source for biomedical research, have been successfully used to gain novel insight into a wide range of diseases. Despite its potential, EHR is currently underutilized for discovery research due to its major limitation in the lack of precise phenotype information. To overcome such difficulties, recent efforts have been devoted to developing supervised algorithms to accurately predict phenotypes based on relatively small training datasets with gold standard labels extracted via chart review. However, supervised methods typically require a sizable training set to yield generalizable algorithms, especially when the number of candidate features, p , is large. In this paper, we propose a semi-supervised (SS) EHR phenotyping method that borrows information from both a small, labeled dataset (where both the label Y and the feature set X are observed) and a much larger, weakly-labeled dataset in which the feature set X is accompanied only by a surrogate label S that is available to all patients. Under a working prior assumption that S is related to X only through Y and allowing it to hold approximately, we propose a prior adaptive semi-supervised (PASS) estimator that incorporates the prior knowledge by shrinking the estimator towards a direction derived under the prior. We derive asymptotic theory for the proposed estimator and justify its efficiency and robustness to prior information of poor quality. We also demonstrate its superiority over existing estimators under various scenarios via simulation studies and on three real-world EHR phenotyping studies at a large tertiary hospital.

Pharmacogenomics in the era of next generation sequencing - from byte to bedside

Pharmacogenetic research has resulted in the identification of a multitude of genetic variants that impact drug response or toxicity. These polymorphisms are mostly common and have been included as actionable information in the labels of numerous drugs. In addition to common variants, recent advances in Next Generation Sequencing (NGS) technologies have resulted in the identification of a plethora of rare and population-specific pharmacogenetic variations with unclear functional consequences that are not accessible by conventional forward genetics strategies. In this review, we discuss how comprehensive sequencing information can be translated into personalized pharmacogenomic advice in the age of NGS. Specifically, we provide an update of the functional impacts of rare pharmacogenetic variability and how this information can be leveraged to improve pharmacogenetic guidance. Furthermore, we critically discuss the current status of implementation of pharmacogenetic testing across drug development and layers of care. We identify major gaps and provide perspectives on how these can be minimized to optimize the utilization of NGS data for personalized clinical decision-support.

Electronic Health Record (EHR) Abstraction

The purpose of electronic health record (EHR) abstraction includes collection of data related to administrative coding functions, quality improvement, clinical registry functions and clinical research. This article examines the different abstraction methods, such as manual abstraction, simple query, and natural language processing (NLP). It also discusses the advantages and disadvantages of each of those methods. The process used for successful EHR abstraction is also discussed and includes the scope and resources needed (time, budget, type of healthcare professionals RHIA, RHIT, etc.). The relationship between EHRs and the clinical registry is also examined with a focus on validity of the data extracted. Future research in this area to examine abstraction methods across hospitals who do data abstraction are being finalized for a future publication.

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.

Pharmacogenomics Implementation and Hurdles to Overcome; In the Context of a Developing Country

Having multiple dimensions, uncertainties and several stakeholders, the costly pharmacogenomics (PGx) is associated with dynamic implementation complexities. Identification of these challenges is critical to harness its full potential, especially in developing countries with fragile healthcare systems and scarce resources. This is the first study aimed to identify most salient challenges related to PGx implementation, with respect to the experiences of early-adopters and local experts' prospects, in the context of a developing country in the Middle East. To perform a comprehensive reconnaissance on PGx adoption challenges a scoping literature review was conducted based on national drug policy components: efficacy/safety, access, affordability and rational use of medicine (RUM). Strategic option development and analysis workshop method with cognitive mapping as the technique was used to evaluate challenges in the context of Iran. The cognitive maps were face-validated and analyzed via Decision Explorer XML. The findings indicated a complex network of issues relative to PGx adoption, categorized in national drug policy indicators. In the rational use of medicine category, ethics, education, bench -to- bedside strategies, guidelines, compliance, and health system issues were found. Clinical trial issues, test's utility, and biomarker validation were identified in the efficacy group. Affordability included pricing, reimbursement, and value assessment issues. Finally, access category included regulation, availability, and stakeholder management challenges. The current study identified the most significant challenges ahead of clinical implementation of PGx in a developing country. This could be the basis of a policy-note development in future work, which may consolidate vital communication among stakeholders and accelerate the efficient implementation in developing new-comer countries.

Drug Response Pharmacogenetics for 200,000 UK Biobank Participants

Pharmacogenetics studies how genetic variation leads to variability in drug response. Guidelines for selecting the right drug and right dose for patients based on their genetics are clinically effective, but are widely unused. For some drugs, the normal clinical decision making process may lead to the optimal dose of a drug that minimizes side effects and maximizes effectiveness. Without measurements of genotype, physicians and patients may adjust dosage in a manner that reflects the underlying genetics. The emergence of genetic data linked to longitudinal clinical data in large biobanks offers an opportunity to confirm known pharmacogenetic interactions as well as discover novel associations by investigating outcomes from normal clinical practice. Here we use the UK Biobank to search for pharmacogenetic interactions among 200 drugs and 9 genes among 200,000 participants. We identify associations between pharmacogene phenotypes and drug maintenance dose as well as differential drug response phenotypes. We find support for several known drug-gene associations as well as novel pharmacogenetic interactions.

An artificial intelligence approach to COVID-19 infection risk assessment in virtual visits: A case report

Objective

In an effort to improve the efficiency of computer algorithms applied to screening for coronavirus disease 2019 (COVID-19) testing, we used natural language processing and artificial intelligence–based methods with unstructured patient data collected through telehealth visits.

Materials and Methods

After segmenting and parsing documents, we conducted analysis of overrepresented words in patient symptoms. We then developed a word embedding–based convolutional neural network for predicting COVID-19 test results based on patients’ self-reported symptoms.

Results

Text analytics revealed that concepts such as smell and taste were more prevalent than expected in patients testing positive. As a result, screening algorithms were adapted to include these symptoms. The deep learning model yielded an area under the receiver-operating characteristic curve of 0.729 for predicting positive results and was subsequently applied to prioritize testing appointment scheduling.

Conclusions

Informatics tools such as natural language processing and artificial intelligence methods can have significant clinical impacts when applied to data streams early in the development of clinical systems for outbreak response.

Engineering Requirements of a Herpes Simplex Virus Patient Registry: Discovery Phase of a Real-World Evidence Platform to Advance Pharmacogenomics and Personalized Medicine

Comprehensive pharmacogenomic understanding requires both robust genomic and demographic data. Patient registries present an opportunity to collect large amounts of robust, patient-level data. Pharmacogenomic advancement in the treatment of infectious diseases is yet to be fully realised. Herpes simplex virus (HSV) is one disease for which pharmacogenomic understanding is wanting. This paper aims to understand the key factors that impact data collection quality for medical registries and suggest potential design features of an HSV medical registry to overcome current constraints and allow for this data to be used as a complement to genomic and clinical data to further the treatment of HSV. This paper outlines the discovery phase for the development of an HSV registry with the aim of learning about the users and their contexts, the technological constraints and the potential improvements that can be made. The design requirements and user stories for the HSV registry have been identified for further alpha phase development. The current landscape of HSV research and patient registry development were discussed. Through the analysis of the current state of the art and thematic user analysis, potential design features were elucidated to facilitate the collection of high-quality, robust patient-level data which could contribute to advances in pharmacogenomic understanding and personalised medicine in HSV. The user requirements specification for the development of an HSV registry has been summarised and implementation strategies for the alpha phase discussed.

Factors associated with clinical inertia in type 2 diabetes mellitus patients treated with metformin monotherapy

Aims: To assess demographic and clinical characteristics associated with clinical inertia in a real-world cohort of type 2 diabetes mellitus patients not at hemoglobin A1c goal (<7%) on metformin monotherapy.Methods: Adult (≥18 years) type 2 diabetes mellitus patients who received care at Massachusetts General Hospital/Brigham and Women's Hospital and received a new metformin prescription between 1992 and 2010 were included in the analysis. Clinical inertia was defined as two consecutive hemoglobin A1c measures ≥7% ≥3 months apart while remaining on metformin monotherapy (i.e. without add-on therapy). The association between clinical inertia and demographic and clinical characteristics was examined via logistic regression.Results: Of 2848 eligible patients, 43% did not achieve a hemoglobin A1c goal of <7% 3 months after metformin monotherapy initiation. A sub-group of 1533 patients was included in the clinical inertia analysis, of which 36% experienced clinical inertia. Asian race was associated with an increased likelihood of clinical inertia (OR = 2.43; 95% CI = 1.48-3.96), while congestive heart failure had a decreased likelihood (OR = 0.58; 95% CI = 0.32-0.98). Chronic kidney disease and cardiovascular/cerebrovascular disease had weaker associations but were directionally similar to congestive heart failure.Conclusions: Asian patients were at an increased risk of clinical inertia, whereas patients with comorbidities appeared to have their treatment more appropriately intensified. A better understanding of these factors may inform efforts to decrease the likelihood for clinical inertia.

Automated detection of altered mental status in emergency department clinical notes: a deep learning approach

BACKGROUND

Machine learning has been used extensively in clinical text classification tasks. Deep learning approaches using word embeddings have been recently gaining momentum in biomedical applications. In an effort to automate the identification of altered mental status (AMS) in emergency department provider notes for the purpose of decision support, we compare the performance of classic bag-of-words-based machine learning classifiers and novel deep learning approaches.

METHODS

We used a case-control study design to extract an adequate number of clinical notes with AMS and non-AMS based on ICD codes. The notes were parsed to extract the history of present illness, which was used as the clinical text for the classifiers. The notes were manually labeled by clinicians. As a baseline for comparison, we tested several traditional bag-of-words based classifiers. We then tested several deep learning models using a convolutional neural network architecture with three different types of word embeddings, a pre-trained word2vec model and two models without pre-training but with different word embedding dimensions.

RESULTS

We evaluated the models on 1130 labeled notes from the emergency department. The deep learning models had the best overall performance with an area under the ROC curve of 98.5% and an accuracy of 94.5%. Pre-training word embeddings on the unlabeled corpus reduced training iterations and had performance that was statistically no different than the other deep learning models.

CONCLUSION

This supervised deep learning approach performs exceedingly well for the detection of AMS symptoms in clinical text in our environment. Further work is needed for the generalizability of these findings, including evaluation of these models in other types of clinical notes and other environments. The results seem promising for the ultimate use of these types of classifiers in combination with other information derived from the electronic health records as input for clinical decision support.

The next generation of precision medicine: observational studies, electronic health records, biobanks and continuous monitoring

Precision medicine can utilize new techniques in order to more effectively translate research findings into clinical practice. In this article, we first explore the limitations of traditional study designs, which stem from (to name a few): massive cost for the assembly of large patient cohorts; non-representative patient data; and the astounding complexity of human biology. Second, we propose that harnessing electronic health records and mobile device biometrics coupled to longitudinal data may prove to be a solution to many of these problems by capturing a 'real world' phenotype. We envision that future biomedical research utilizing more precise approaches to patient care will utilize continuous and longitudinal data sources.

Evidence of heterogeneity in statin-associated type 2 diabetes mellitus risk: A meta-analysis of randomized controlled trials and observational studies

AIMS

To conduct a meta-analysis of statin-associated type 2 diabetes mellitus (T2D) risk among randomized controlled trials (RCTs) and observational studies (OBSs), excluding studies conducted among secondary prevention populations.

METHODS

Studies were identified by searching PubMed (1994-present) and EMBASE (1994-present). Articles had to meet the following criteria: (1) follow-up >one year; (2) >50% of participants free of clinically diagnosed ASCVD; (3) adult participants ≥30 years old; (4) reported statin-associated T2D effect estimates; and (5) quantified precision using 95% confidence interval. Data were pooled using random-effects model.

RESULTS

We identified 23 studies (35% RCTs) of n = 4,012,555 participants. OBS participants were on average younger (mean difference = 6.2 years) and had lower mean low-density lipoprotein cholesterol (LDL-C, mean difference = 20.6 mg/dL) and mean fasting plasma glucose (mean difference = 5.2 mg/dL) compared to RCT participants. There was little evidence for publication bias (P > 0.1). However, evidence of heterogeneity was observed overall and among OBSs and RCTs (PCochran = <0.05). OBS designs, younger baseline mean ages, lower LDL-C concentrations, and high proportions of never or former smokers were significantly associated with increased statin-associated T2D risk.

CONCLUSIONS

Potentially elevated statin-associated T2D risk in younger populations with lower LDL-C merits further investigation in light of evolving statin guidelines targeting primary prevention populations.

Informatics and Computational Methods in Natural Product Drug Discovery: A Review and Perspectives

The discovery of new pharmaceutical drugs is one of the preeminent tasks-scientifically, economically, and socially-in biomedical research. Advances in informatics and computational biology have increased productivity at many stages of the drug discovery pipeline. Nevertheless, drug discovery has slowed, largely due to the reliance on small molecules as the primary source of novel hypotheses. Natural products (such as plant metabolites, animal toxins, and immunological components) comprise a vast and diverse source of bioactive compounds, some of which are supported by thousands of years of traditional medicine, and are largely disjoint from the set of small molecules used commonly for discovery. However, natural products possess unique characteristics that distinguish them from traditional small molecule drug candidates, requiring new methods and approaches for assessing their therapeutic potential. In this review, we investigate a number of state-of-the-art techniques in bioinformatics, cheminformatics, and knowledge engineering for data-driven drug discovery from natural products. We focus on methods that aim to bridge the gap between traditional small-molecule drug candidates and different classes of natural products. We also explore the current informatics knowledge gaps and other barriers that need to be overcome to fully leverage these compounds for drug discovery. Finally, we conclude with a "road map" of research priorities that seeks to realize this goal.

Feasibility of Integrating Panel-Based Pharmacogenomics Testing for Chemotherapy and Supportive Care in Patients With Colorectal Cancer

INTRODUCTION

Pharmacogenomics is about selecting the "right drug in the right amount for the right patient." In metastatic colorectal cancer, germline pharmacogenomics testing presents a unique opportunity to improve outcomes, since the genes dihydropyrimidine dehydrogenase and UDP-glucuronosyltransferase metabolizing the chemotherapy drugs, 5-fluorouracil, and irinotecan are already well known. In a retrospective analysis of the landmark TRIBE clinical trial [(TRIBE - TRIplet plus BEvacizumab multicenter, phase III trial by the Italian Cooperative GONO (Gruppo Oncologico Nord Ovest) group (NCT00719797)], the proportion of patients with serious adverse events was higher in those with dihydropyrimidine dehydrogenase/UDP-glucuronosyltransferase aberrations and was dose dependent. We aimed to report on the feasibility and the results of incorporating pharmacogenomics testing into clinical practice.

METHODS

As a quality improvement initiative and a center of individualized medicine grant, we integrated the use of OneOme RightMed comprehensive test, which reports on 27 genes related to pharmacogenomics and over 300 medications of interest. We limited initial testing to patients with colorectal cancer. Pharmacists provided dosage recommendations based on test results in real-time.

RESULTS

At our cancer center, 155 patients underwent pharmacogenomics testing from November 2017 to January 2019. Results were available within 3 to 5 days of testing for most patients and were integrated into treatment decision-making. Of 155 sampled participants, a total of 89 (57.4%) participants had an UGT1A1 variant genotype, NM_000463.2: c.-53_-52[8] *1/*28, n = 74 (47.7%); *28/*28, n = 15 (9.7%). Additionally, 4 (2.6%) participants were heterozygous for dihydropyrimidine dehydrogenase. Two (1.3%) individuals were heterozygous for both UDP-glucuronosyltransferase and dihydropyrimidine dehydrogenase genes. All (100%) the patients had at least 1 actionable aberration related to supportive care medications (CYP-family) of all the possible medications listed on their pharmacogenomics report.

CONCLUSION

Preemptive comprehensive pharmacogenomics testing can be integrated into clinical practice in real-time for patients with cancer given faster turnaround and low cost. Pharmacist-driven, patient-specific medication management consults add further value given the number of genes/drugs. This sets the stage for a prospective randomized clinical trial to demonstrate the amount of benefit this can result in these patients.

Framework to Enhance Nurses' Use of EMR

The ability of nurses to adopt and successfully use EMR is expected to have a significant impact on achieving benefits such as reduction in healthcare costs and improvement in healthcare quality. A review of the current research literature reveals issues and concerns relating to the adoption and use of EMR by nurses in hospital environments. This article presents a literature review of such issues and concerns, and suggests a framework for enhancing the adoption and use of EMR by nurses and hospitals.

Large-Scale Analysis of Genetic and Clinical Patient Data

Biomedical data science has experienced an explosion of new data over the past decade. Abundant genetic and genomic data are increasingly available in large, diverse data sets due to the maturation of modern molecular technologies. Along with these molecular data, dense, rich phenotypic data are also available on comprehensive clinical data sets from health care provider organizations, clinical trials, population health registries, and epidemiologic studies. The methods and approaches for interrogating these large genetic/genomic and clinical data sets continue to evolve rapidly, as our understanding of the questions and challenges continue to emerge. In this review, the state-of-the-art methodologies for genetic/genomic analysis along with complex phenomics will be discussed. This field is changing and adapting to the novel data types made available, as well as technological advances in computation and machine learning. Thus, I will also discuss the future challenges in this exciting and innovative space. The promises of precision medicine rely heavily on the ability to marry complex genetic/genomic data with clinical phenotypes in meaningful ways.

Development of an Algorithm to Identify Patients with Physician-Documented Insomnia

We developed an insomnia classification algorithm by interrogating an electronic medical records (EMR) database of 314,292 patients. The patients received care at Massachusetts General Hospital (MGH), Brigham and Women’s Hospital (BWH), or both, between 1992 and 2010. Our algorithm combined structured variables (such as International Classification of Diseases 9th Revision [ICD-9] codes, prescriptions, laboratory observations) and unstructured variables (such as text mentions of sleep and psychiatric disorders in clinical narrative notes). The highest classification performance of our algorithm was achieved when it included a combination of structured variables (billing codes for insomnia, common psychiatric conditions, and joint disorders) and unstructured variables (sleep disorders and psychiatric disorders). Our algorithm had superior performance in identifying insomnia patients compared to billing codes alone (area under the receiver operating characteristic curve [AUROC] = 0.83 vs. 0.55 with 95% confidence intervals [CI] of 0.76–0.90 and 0.51–0.58, respectively). When applied to the 314,292-patient population, our algorithm classified 36,810 of the patients with insomnia, of which less than 17% had a billing code for insomnia. In conclusion, an insomnia classification algorithm that incorporates clinical notes is superior to one based solely on billing codes. Compared to traditional methods, our study demonstrates that a classification algorithm that incorporates physician notes can more accurately, comprehensively, and quickly identify large cohorts of insomnia patients.

Clinical Natural Language Processing in languages other than English: opportunities and challenges

Background

Natural language processing applied to clinical text or aimed at a clinical outcome has been thriving in recent years. This paper offers the first broad overview of clinical Natural Language Processing (NLP) for languages other than English. Recent studies are summarized to offer insights and outline opportunities in this area.

Main Body

We envision three groups of intended readers: (1) NLP researchers leveraging experience gained in other languages, (2) NLP researchers faced with establishing clinical text processing in a language other than English, and (3) clinical informatics researchers and practitioners looking for resources in their languages in order to apply NLP techniques and tools to clinical practice and/or investigation. We review work in clinical NLP in languages other than English. We classify these studies into three groups: (i) studies describing the development of new NLP systems or components de novo, (ii) studies describing the adaptation of NLP architectures developed for English to another language, and (iii) studies focusing on a particular clinical application.

Conclusion

We show the advantages and drawbacks of each method, and highlight the appropriate application context. Finally, we identify major challenges and opportunities that will affect the impact of NLP on clinical practice and public health studies in a context that encompasses English as well as other languages.

Big Data in Drug Discovery

Interpretation of Big Data in the drug discovery community should enhance project timelines and reduce clinical attrition through improved early decision making. The issues we encounter start with the sheer volume of data and how we first ingest it before building an infrastructure to house it to make use of the data in an efficient and productive way. There are many problems associated with the data itself including general reproducibility, but often, it is the context surrounding an experiment that is critical to success. Help, in the form of artificial intelligence (AI), is required to understand and translate the context. On the back of natural language processing pipelines, AI is also used to prospectively generate new hypotheses by linking data together. We explain Big Data from the context of biology, chemistry and clinical trials, showcasing some of the impressive public domain sources and initiatives now available for interrogation.

Integrating pharmacogenomics into electronic health records with clinical decision support

PURPOSE

Existing pharmacogenomic informatics models, key implementation steps, and emerging resources to facilitate the development of pharmacogenomic clinical decision support (CDS) are described.

SUMMARY

Pharmacogenomics is an important component of precision medicine. Informatics, especially CDS in the electronic health record (EHR), is a critical tool for the integration of pharmacogenomics into routine patient care. Effective integration of pharmacogenomic CDS into the EHR can address implementation challenges, including the increasing volume of pharmacogenomic clinical knowledge, the enduring nature of pharmacogenomic test results, and the complexity of interpreting results. Both passive and active CDS provide point-of-care information to clinicians that can guide the systematic use of pharmacogenomics to proactively optimize pharmacotherapy. Key considerations for a successful implementation have been identified; these include clinical workflows, identification of alert triggers, and tools to guide interpretation of results. These considerations, along with emerging resources from the Clinical Pharmacogenetics Implementation Consortium and the National Academy of Medicine, are described.

CONCLUSION

The EHR with CDS is essential to curate pharmacogenomic data and disseminate patient-specific information at the point of care. As part of the successful implementation of pharmacogenomics into clinical settings, all relevant clinical recommendations pertaining to gene-drug pairs must be summarized and presented to clinicians in a manner that is seamlessly integrated into the clinical workflow of the EHR. In some situations, ancillary systems and applications outside the EHR may be integrated to augment the capabilities of the EHR.

iCHRCloud: Web & Mobile based Child Health Imprints for Smart Healthcare

Reducing child mortality with quality care is the prime-most concern of all nations. Thus in current IT era, our healthcare industry needs to focus on adapting information technology in healthcare services. Barring few preliminary attempts to digitalize basic hospital administrative and clinical functions, even today in India, child health and vaccination records are still maintained as paper-based records. Also, error in manually plotting the parameters in growth charts results in missed opportunities for early detection of growth disorders in children. To address these concerns, we present India's first hospital linked, affordable automated vaccination and real-time child's growth monitoring cloud based application- Integrated Child Health Record cloud (iCHRcloud). This application is based on HL7 protocol enabling integration with hospital's HIS/EMR system. It provides Java (Enterprise Service Bus and Hibernate) based web portal for doctors and mobile application for parents, enhancing doctor-parent engagement. It leverages highchart to automate chart preparation and provides access of data via Push Notification (GCM and APNS) to parents on iOS and Android mobile platforms. iCHRcloud has also been recognized as one of the best innovative solution in three nationwide challenges, 2016 in India. iCHRcloud offers a seamless, secure (256 bit HTTPS) and sustainable solution to reduce child mortality. Detail analysis on preliminary data of 16,490 child health records highlight the diversified need of various demographic regions. Thus, primary lesson would be to implement better validation strategies to fulfill the customize requisites of entire population. This paper presents first glimpse of data and power of the analytics in policy framework.

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.

Development and validation of algorithms for the detection of statin myopathy signals from electronic medical records

The purpose of this study was to develop and validate sensitive algorithms to detect hospitalized statin-induced myopathy (SIM) cases from electronic medical records (EMRs). We developed four algorithms on a training set of 31,211 patient records from a large tertiary hospital. We determined the performance of these algorithms against manually curated records. The best algorithm used a combination of elevated creatine kinase (>4× the upper limit of normal (ULN)), discharge summary, diagnosis, and absence of statin in discharge medications. This algorithm achieved a positive predictive value of 52-71% and a sensitivity of 72-78% on two validation sets of >30,000 records each. Using this algorithm, the incidence of SIM was estimated at 0.18%. This algorithm captured three times more rhabdomyolysis cases than spontaneous reports (95% vs. 30% of manually curated gold standard cases). Our results show the potential power of utilizing data and text mining of EMRs to enhance pharmacovigilance activities.

Impact of New Genomic Technologies on Understanding Adverse Drug Reactions

It is well established that variations in genes can alter the pharmacokinetic and pharmacodynamic profile of a drug and immunological responses to it. Early advances in pharmacogenetics were made with traditional genetic techniques such as functional cloning of genes using knowledge gained from purified proteins, and candidate gene analysis. Over the past decade, techniques for analysing the human genome have accelerated greatly as knowledge and technological capabilities have grown. These techniques were initially focussed on understanding genetic factors of disease, but increasingly they are helping to clarify the genetic basis of variable drug responses and adverse drug reactions (ADRs). We examine genetic methods that have been applied to the understanding of ADRs, review the current state of knowledge of genetic factors that influence ADR development, and discuss how the application of genome-wide association studies and next-generation sequencing approaches is supporting and extending existing knowledge of pharmacogenetic processes leading to ADRs. Such approaches have identified single genes that are major contributing genetic risk factors for an ADR, (such as flucloxacillin and drug-induced liver disease), making pre-treatment testing a possibility. They have contributed to the identification of multiple genetic determinants of a single ADR, some involving both pharmacologic and immunological processes (such as phenytoin and severe cutaneous adverse reactions). They have indicated that rare genetic variants, often not previously reported, are likely to have more influence on the phenotype than common variants that have been traditionally tested for. The problem of genotype/phenotype discordance affecting the interpretation of pharmacogenetic screening and the future of genome-based testing applied to ADRs are also discussed.

Educational strategies to enable expansion of pharmacogenomics-based care

PURPOSE

The current state of pharmacogenomics education for pharmacy students and practitioners is discussed, and resources and strategies to address persistent challenges in this area are reviewed.

SUMMARY

Consensus-based pharmacist competencies and guidelines have been published to guide pharmacogenomics knowledge attainment and application in clinical practice. Pharmacogenomics education is integrated into various pharmacy school courses and, increasingly, into Pharm.D. curricula in the form of required standalone courses. Continuing-education programs and a limited number of postgraduate training opportunities are available to practicing pharmacists. For colleges and schools of pharmacy, identifying the optimal structure and content of pharmacogenomics education remains a challenge; insufficient numbers of faculty members with pharmacogenomics expertise and the inadequate availability of practice settings for experiential education are other limiting factors. Strategies for overcoming those challenges include providing early exposure to pharmacogenomics through foundational courses and incorporating pharmacogenomics into practice-based therapeutics courses and introductory and advanced pharmacy practice experiences. For practitioner education, online resources, clinical decision support-based tools, and certificate programs can be used to supplement structured postgraduate training in pharmacogenomics. Recently published data indicate successful use of "shared curricula" and participatory education models involving opportunities for learners to undergo personal genomic testing.

CONCLUSION

The pharmacy profession has taken a leadership role in expanding student and practitioner education to meet the demand for increased pharmacist involvement in precision medicine initiatives. Effective approaches to teaching pharmacogenomics knowledge and driving its appropriate application in clinical practice are increasingly available.

Biomechanisms of Comorbidity: Reviewing Integrative Analyses of Multi-omics Datasets and Electronic Health Records

OBJECTIVES

Disease comorbidity is a pervasive phenomenon impacting patients' health outcomes, disease management, and clinical decisions. This review presents past, current and future research directions leveraging both phenotypic and molecular information to uncover disease similarity underpinning the biology and etiology of disease comorbidity.

METHODS

We retrieved ~130 publications and retained 59, ranging from 2006 to 2015, that comprise a minimum number of five diseases and at least one type of biomolecule. We surveyed their methods, disease similarity metrics, and calculation of comorbidities in the electronic health records, if present.

RESULTS

Among the surveyed studies, 44% generated or validated disease similarity metrics in context of comorbidity, with 60% being published in the last two years. As inputs, 87% of studies utilized intragenic loci and proteins while 13% employed RNA (mRNA, LncRNA or miRNA). Network modeling was predominantly used (35%) followed by statistics (28%) to impute similarity between these biomolecules and diseases. Studies with large numbers of biomolecules and diseases used network models or naïve overlap of disease-molecule associations, while machine learning, statistics, and information retrieval were utilized in smaller and moderate sized studies. Multiscale computations comprising shared function, network topology, and phenotypes were performed exclusively on proteins.

CONCLUSION

This review highlighted the growing methods for identifying the molecular mechanisms underpinning comorbidities that leverage multiscale molecular information and patterns from electronic health records. The survey unveiled that intergenic polymorphisms have been overlooked for similarity imputation compared to their intragenic counterparts, offering new opportunities to bridge the mechanistic and similarity gaps of comorbidity.

Electronic medical record phenotyping using the anchor and learn framework

Background Electronic medical records (EMRs) hold a tremendous amount of information about patients that is relevant to determining the optimal approach to patient care. As medicine becomes increasingly precise, a patient’s electronic medical record phenotype will play an important role in triggering clinical decision support systems that can deliver personalized recommendations in real time. Learning with anchors presents a method of efficiently learning statistically driven phenotypes with minimal manual intervention.

Materials and Methods We developed a phenotype library that uses both structured and unstructured data from the EMR to represent patients for real-time clinical decision support. Eight of the phenotypes were evaluated using retrospective EMR data on emergency department patients using a set of prospectively gathered gold standard labels.

Results We built a phenotype library with 42 publicly available phenotype definitions. Using information from triage time, the phenotype classifiers have an area under the ROC curve (AUC) of infection 0.89, cancer 0.88, immunosuppressed 0.85, septic shock 0.93, nursing home 0.87, anticoagulated 0.83, cardiac etiology 0.89, and pneumonia 0.90. Using information available at the time of disposition from the emergency department, the AUC values are infection 0.91, cancer 0.95, immunosuppressed 0.90, septic shock 0.97, nursing home 0.91, anticoagulated 0.94, cardiac etiology 0.92, and pneumonia 0.97.

Discussion The resulting phenotypes are interpretable and fast to build, and perform comparably to statistically learned phenotypes developed with 5000 manually labeled patients.

Conclusion Learning with anchors is an attractive option for building a large public repository of phenotype definitions that can be used for a range of health IT applications, including real-time decision support.

The genetics of drug efficacy: opportunities and challenges

Lack of sufficient efficacy is the most common cause of attrition in late-phase drug development. It has long been envisioned that genetics could drive stratified drug development by identifying those patient subgroups that are most likely to respond. However, this vision has not been realized as only a small proportion of drugs have been found to have germline genetic predictors of efficacy with clinically meaningful effects, and so far all but one were found after drug approval. With the exception of oncology, systematic application of efficacy pharmacogenetics has not been integrated into drug discovery and development across the industry. Here, we argue for routine, early and cumulative screening for genetic predictors of efficacy, as an integrated component of clinical trial analysis. Such a strategy would identify clinically relevant predictors that may exist at the earliest possible opportunity, allow these predictors to be integrated into subsequent clinical development and provide mechanistic insights into drug disposition and patient-specific factors that influence response, therefore paving the way towards more personalized medicine.

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.

The 3-I framework: a framework for developing public policies regarding pharmacogenomics (PGx) testing in Canada

The 3-I framework of analyzing the ideas, interests, and institutions around a topic has been used by political scientists to guide public policy development. In Canada, there is a lack of policy governing pharmacogenomics (PGx) testing compared to other developed nations. The goal of this study was to use the 3-I framework, a policy development tool, and apply it to PGx testing to identify and analyze areas where current policy is limited and challenges exist in bringing PGx testing into wide-spread clinical practice in Canada. A scoping review of the literature was conducted to determine the extent and challenges of PGx policy implementation at federal and provincial levels. Based on the 3-I analysis, contentious ideas related to PGx are (i) genetic discrimination, (ii) informed consent, (iii) the lack of knowledge about PGx in health care, (iv) the value of PGx testing, (v) the roles of health care workers in the coordination of PGx services, and (vi) confidentiality and privacy. The 3-I framework is a useful tool for policy makers, and applying it to PGx policy development is a new approach in Canadian genomics. Policy makers at every organizational level can use this analysis to help develop targeted PGx policies.

Common Genetic Variants Influence Circulating Vitamin D Levels in Inflammatory Bowel Diseases

BACKGROUND

The accuracy and utility of electronic health record (EHR)-derived phenotypes in replicating genotype-phenotype relationships have been infrequently examined. Low circulating vitamin D levels are associated with severe outcomes in inflammatory bowel disease (IBD); however, the genetic basis for vitamin D insufficiency in this population has not been examined previously.

METHODS

We compared the accuracy of physician-assigned phenotypes in a large prospective IBD registry to that identified by an EHR algorithm incorporating codified and structured data. Genotyping for IBD risk alleles was performed on the Immunochip and a genetic risk score calculated and compared between EHR-defined patients and those in the registry. Additionally, 4 vitamin D risk alleles were genotyped and serum 25-hydroxy vitamin D [25(OH)D] levels compared across genotypes.

RESULTS

A total of 1131 patients captured by our EHR algorithm were also included in our prospective registry (656 Crohn's disease, 475 ulcerative colitis). The overall genetic risk score for Crohn's disease (P = 0.13) and ulcerative colitis (P = 0.32) was similar between EHR-defined patients and a prospective registry. Three of the 4 vitamin D risk alleles were associated with low vitamin D levels in patients with IBD and contributed an additional 3% of the variance explained. Vitamin D genetic risk score did not predict normalization of vitamin D levels.

CONCLUSIONS

EHR cohorts form valuable data sources for examining genotype-phenotype relationships. Vitamin D risk alleles explain 3% of the variance in vitamin D levels in patients with IBD.

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.

A Validated Phenotyping Algorithm for Genetic Association Studies in Age-related Macular Degeneration

Age-related macular degeneration (AMD), a multifactorial, neurodegenerative disease, is a leading cause of vision loss. With the rapid advancement of DNA sequencing technologies, many AMD-associated genetic polymorphisms have been identified. Currently, the most time consuming steps of these studies are patient recruitment and phenotyping. In this study, we describe the development of an automated algorithm to identify neovascular (wet) AMD, non-neovascular (dry) AMD and control subjects using electronic medical record (EMR)-based criteria. Positive predictive value (91.7%) and negative predictive value (97.5%) were calculated using expert chart review as the gold standard to assess algorithm performance. We applied the algorithm to an EMR-linked DNA bio-repository to study previously identified AMD-associated single nucleotide polymorphisms (SNPs), using case/control status determined by the algorithm. Risk alleles of three SNPs, rs1061170 (CFH), rs1410996 (CFH), and rs10490924 (ARMS2) were found to be significantly associated with the AMD case/control status as defined by the algorithm. With the rapid growth of EMR-linked DNA biorepositories, patient selection algorithms can greatly increase the efficiency of genetic association study. We have found that stepwise validation of such an algorithm can result in reliable cohort selection and, when coupled within an EMR-linked DNA biorepository, replicates previously published AMD-associated SNPs.

Clinical Pharmacogenetics Implementation Consortium (CPIC) guidelines for human leukocyte antigen B (HLA-B) genotype and allopurinol dosing: 2015 update

The Clinical Pharmacogenetics Implementation Consortium (CPIC) Guidelines for HLA-B*58:01 Genotype and Allopurinol Dosing was originally published in February 2013. We reviewed the recent literature and concluded that none of the evidence would change the therapeutic recommendations in the original guideline; therefore, the original publication remains clinically current. However, we have updated the Supplemental Material and included additional resources for applying CPIC guidelines into the electronic health record. Up-to-date information can be found at PharmGKB (http://www.pharmgkb.org).

An Introduction to Natural Language Processing: How You Can Get More From Those Electronic Notes You Are Generating

Electronically stored clinical documents may contain both structured data and unstructured data. The use of structured clinical data varies by facility, but clinicians are familiar with coded data such as International Classification of Diseases, Ninth Revision, Systematized Nomenclature of Medicine-Clinical Terms codes, and commonly other data including patient chief complaints or laboratory results. Most electronic health records have much more clinical information stored as unstructured data, for example, clinical narrative such as history of present illness, procedure notes, and clinical decision making are stored as unstructured data. Despite the importance of this information, electronic capture or retrieval of unstructured clinical data has been challenging. The field of natural language processing (NLP) is undergoing rapid development, and existing tools can be successfully used for quality improvement, research, healthcare coding, and even billing compliance. In this brief review, we provide examples of successful uses of NLP using emergency medicine physician visit notes for various projects and the challenges of retrieving specific data and finally present practical methods that can run on a standard personal computer as well as high-end state-of-the-art funded processes run by leading NLP informatics researchers.

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.

Implementation of personalized medicine services in community pharmacies: perceptions of independent community pharmacists

OBJECTIVES

To evaluate the perceptions of independent community pharmacists within a regional independent community pharmacy cooperative on implementing personalized medicine services at their pharmacies and to gauge the pharmacists' self-reported knowledge of pharmacogenomic principles.

DESIGN

Descriptive, exploratory, nonexperimental study.

SETTING

American Pharmacy Services Corporation (APSC), 2011-12.

PARTICIPANTS

Pharmacists (n = 101) affiliated with the independent pharmacies of APSC.

INTERVENTION

Single-mode survey.

MAIN OUTCOME MEASURES

Independent community pharmacists' interest in implementing personalized medicine services, perceived readiness to provide such services, and perceived barriers to implementation.

RESULTS

101 completed surveys were returned for data analysis. The majority of pharmacists surveyed (75%) expressed interest in offering personalized medicine services. When asked to describe their knowledge of pharmacogenomics and readiness to implement such services, more than 50% said they were not knowledgeable on the subject and would not currently be comfortable making drug therapy recommendations to physicians or confident counseling patients based on results of genetic screenings without further training and education. Respondents identified cost of providing the service, reimbursement issues, current knowledge of pharmacogenomics, and time to devote to the program as the greatest barriers to implementing personalized medicine services.

CONCLUSION

The majority of independent community pharmacists are interested in incorporating personalized medicine services into their practices, but they require further education before this is possible. Future initiatives should focus on the development of comprehensive education programs to further train pharmacists for provision of these services.

Automatic identification of methotrexate-induced liver toxicity in patients with rheumatoid arthritis from the electronic medical record

OBJECTIVES

To improve the accuracy of mining structured and unstructured components of the electronic medical record (EMR) by adding temporal features to automatically identify patients with rheumatoid arthritis (RA) with methotrexate-induced liver transaminase abnormalities.

MATERIALS AND METHODS

Codified information and a string-matching algorithm were applied to a RA cohort of 5903 patients from Partners HealthCare to select 1130 patients with potential liver toxicity. Supervised machine learning was applied as our key method. For features, Apache clinical Text Analysis and Knowledge Extraction System (cTAKES) was used to extract standard vocabulary from relevant sections of the unstructured clinical narrative. Temporal features were further extracted to assess the temporal relevance of event mentions with regard to the date of transaminase abnormality. All features were encapsulated in a 3-month-long episode for classification. Results were summarized at patient level in a training set (N=480 patients) and evaluated against a test set (N=120 patients).

RESULTS

The system achieved positive predictive value (PPV) 0.756, sensitivity 0.919, F1 score 0.829 on the test set, which was significantly better than the best baseline system (PPV 0.590, sensitivity 0.703, F1 score 0.642). Our innovations, which included framing the phenotype problem as an episode-level classification task, and adding temporal information, all proved highly effective.

CONCLUSIONS

Automated methotrexate-induced liver toxicity phenotype discovery for patients with RA based on structured and unstructured information in the EMR shows accurate results. Our work demonstrates that adding temporal features significantly improved classification results.