Using Phecodes for Research with the Electronic Health Record: From PheWAS to PheRS

Electronic health records (EHRs) are a rich source of data for researchers, but extracting meaningful information out of this highly complex data source is challenging. Phecodes represent one strategy for defining phenotypes for research using EHR data. They are a high-throughput phenotyping tool based on ICD (International Classification of Diseases) codes that can be used to rapidly define the case/control status of thousands of clinically meaningful diseases and conditions. Phecodes were originally developed to conduct phenome-wide association studies to scan for phenotypic associations with common genetic variants. Since then, phecodes have been used to support a wide range of EHR-based phenotyping methods, including the phenotype risk score. This review aims to comprehensively describe the development, validation, and applications of phecodes and suggest some future directions for phecodes and high-throughput phenotyping.

Download Full-text

Genetic validation of bipolar disorder identified by automated phenotyping using electronic health records

10.1101/193011 ◽

2017 ◽

Author(s):

Chia-Yen Chen ◽

Phil H. Lee ◽

Victor M. Castro ◽

Jessica Minnier ◽

Alexander W. Charney ◽

...

Keyword(s):

Bipolar Disorder ◽

Electronic Health Records ◽

Genetic Correlation ◽

High Throughput ◽

Association Studies ◽

European Ancestry ◽

Health Records ◽

Total N ◽

High Throughput Phenotyping ◽

Electronic Health

AbstractBipolar disorder (BD) is a heritable mood disorder characterized by episodes of mania and depression. Although genomewide association studies (GWAS) have successfully identified genetic loci contributing to BD risk, sample size has become a rate-limiting obstacle to genetic discovery. Electronic health records (EHRs) represent a vast but relatively untapped resource for high-throughput phenotyping. As part of the International Cohort Collection for Bipolar Disorder (ICCBD), we previously validated automated EHR-based phenotyping algorithms for BD against in-person diagnostic interviews (Castro et al. 2015). Here, we establish the genetic validity of these phenotypes by determining their genetic correlation with traditionally-ascertained samples. Case and control algorithms were derived from structured and narrative text in the Partners Healthcare system comprising more than 4.6 million patients over 20 years. Genomewide genotype data for 3,330 BD cases and 3,952 controls of European ancestry were used to estimate SNP-based heritability (h2g) and genetic correlation(rg) between EHR-based phenotype definitions and traditionally-ascertained BD cases in GWAS by the ICCBD and Psychiatric Genomics Consortium (PGC) using LD score regression. We evaluated BD cases identified using 4 EHR-based algorithms: an NLP-based algorithm (95-NLP) and 3 rule-based algorithms using codified EHR with decreasing levels of stringency - “coded-strict”, “coded-broad”, and “coded-broad based on a single clinical encounter” (coded-broad-SV). The analytic sample comprised 862 95-NLP, 1,968 coded-strict, 2,581 coded-broad, 408 coded-broad-SV BD cases, and 3,952 controls. The estimated h2g were 0.24 (p=0.015), 0.09 (p=0.064), 0.13 (p=0.003), 0.00 (p=0.591) for 95-NLP, coded-strict, coded-broad and coded-broad-SV BD, respectively. The h2g for all EHR-based cases combined except coded-broad-SV (excluded due to 0 h2g) was 0.12 (p=0.004). These h2g were lower or similar to the h2g observed by the ICCBD+PGCBD (0.23, p=3.17E-80, total N=33,181). However, the rg between ICCBD+PGCBD and the EHR-based cases were high for 95-NLP (0.66, p=3.69x10-5), coded-strict (1.00, p=2.40x10-4), and coded-broad (0.74, p=8.11x10-7). The rg between EHR-based BDs ranged from 0.90 to 0.98. These results provide the first genetic validation of automated EHR-based phenotyping for BD and suggest that this approach identifies cases that are highly genetically correlated with those ascertained through conventional methods. High throughput phenotyping using the large data resources available in EHRs represents a viable method for accelerating psychiatric genetic research.

Download Full-text

PheMap: a multi-resource knowledge base for high-throughput phenotyping within electronic health records

Journal of the American Medical Informatics Association ◽

10.1093/jamia/ocaa104 ◽

2020 ◽

Vol 27 (11) ◽

pp. 1675-1687

Author(s):

Neil S Zheng ◽

QiPing Feng ◽

V Eric Kerchberger ◽

Juan Zhao ◽

Todd L Edwards ◽

...

Keyword(s):

Electronic Health Records ◽

Knowledge Base ◽

High Throughput ◽

Association Studies ◽

Research Quality ◽

P Value ◽

Genome Wide Association Studies ◽

Health Records ◽

High Throughput Phenotyping ◽

Electronic Health

Abstract Objective Developing algorithms to extract phenotypes from electronic health records (EHRs) can be challenging and time-consuming. We developed PheMap, a high-throughput phenotyping approach that leverages multiple independent, online resources to streamline the phenotyping process within EHRs. Materials and Methods PheMap is a knowledge base of medical concepts with quantified relationships to phenotypes that have been extracted by natural language processing from publicly available resources. PheMap searches EHRs for each phenotype’s quantified concepts and uses them to calculate an individual’s probability of having this phenotype. We compared PheMap to clinician-validated phenotyping algorithms from the Electronic Medical Records and Genomics (eMERGE) network for type 2 diabetes mellitus (T2DM), dementia, and hypothyroidism using 84 821 individuals from Vanderbilt Univeresity Medical Center's BioVU DNA Biobank. We implemented PheMap-based phenotypes for genome-wide association studies (GWAS) for T2DM, dementia, and hypothyroidism, and phenome-wide association studies (PheWAS) for variants in FTO, HLA-DRB1, and TCF7L2. Results In this initial iteration, the PheMap knowledge base contains quantified concepts for 841 disease phenotypes. For T2DM, dementia, and hypothyroidism, the accuracy of the PheMap phenotypes were >97% using a 50% threshold and eMERGE case-control status as a reference standard. In the GWAS analyses, PheMap-derived phenotype probabilities replicated 43 of 51 previously reported disease-associated variants for the 3 phenotypes. For 9 of the 11 top associations, PheMap provided an equivalent or more significant P value than eMERGE-based phenotypes. The PheMap-based PheWAS showed comparable or better performance to a traditional phecode-based PheWAS. PheMap is publicly available online. Conclusions PheMap significantly streamlines the process of extracting research-quality phenotype information from EHRs, with comparable or better performance to current phenotyping approaches.

Download Full-text

Validation of intellectual disability coding through hospital morbidity records using an intellectual disability population-based database in Western Australia

BMJ Open ◽

10.1136/bmjopen-2017-019113 ◽

2018 ◽

Vol 8 (1) ◽

pp. e019113 ◽

Cited By ~ 6

Author(s):

Jenny Bourke ◽

Kingsley Wong ◽

Helen Leonard

Keyword(s):

Intellectual Disability ◽

International Classification Of Diseases ◽

Population Based ◽

Reliable Source ◽

Morbidity Data ◽

Classification Of Diseases ◽

Data Source ◽

Hospital Morbidity ◽

Western Australian ◽

Hospital Morbidity Data

ObjectivesTo investigate how well intellectual disability (ID) can be ascertained using hospital morbidity data compared with a population-based data source.Design, setting and participantsAll children born in 1983–2010 with a hospital admission in the Western Australian Hospital Morbidity Data System (HMDS) were linked with the Western Australian Intellectual Disability Exploring Answers (IDEA) database. The International Classification of Diseases hospital codes consistent with ID were also identified.Main outcome measuresThe characteristics of those children identified with ID through either or both sources were investigated.ResultsOf the 488 905 individuals in the study, 10 218 (2.1%) were identified with ID in either IDEA or HMDS with 1435 (14.0%) individuals identified in both databases, 8305 (81.3%) unique to the IDEA database and 478 (4.7%) unique to the HMDS dataset only. Of those unique to the HMDS dataset, about a quarter (n=124) had died before 1 year of age and most of these (75%) before 1 month. Children with ID who were also coded as such in the HMDS data were more likely to be aged under 1 year, female, non-Aboriginal and have a severe level of ID, compared with those not coded in the HMDS data. The sensitivity of using HMDS to identify ID was 14.7%, whereas the specificity was much higher at 99.9%.ConclusionHospital morbidity data are not a reliable source for identifying ID within a population, and epidemiological researchers need to take these findings into account in their study design.

Download Full-text

Are International Classification of Diseases Codes in Electronic Health Records Useful in Identifying Obesity as a Risk Factor When Evaluating Surgical Outcomes?

The Health Care Manager ◽

10.1097/hcm.0000000000000112 ◽

2016 ◽

Vol 35 (4) ◽

pp. 361-367 ◽

Cited By ~ 1

Author(s):

Victoria Goode ◽

Virginia Rovnyak ◽

Ivora Hinton ◽

Elayne Phillips ◽

Elizabeth Merwin

Keyword(s):

Risk Factor ◽

Electronic Health Records ◽

Surgical Outcomes ◽

International Classification Of Diseases ◽

International Classification ◽

Health Records ◽

Classification Of Diseases ◽

Electronic Health

Download Full-text

Applying active learning to high-throughput phenotyping algorithms for electronic health records data

Journal of the American Medical Informatics Association ◽

10.1136/amiajnl-2013-001945 ◽

2013 ◽

Vol 20 (e2) ◽

pp. e253-e259 ◽

Cited By ~ 53

Author(s):

Yukun Chen ◽

Robert J Carroll ◽

Eugenia R McPeek Hinz ◽

Anushi Shah ◽

Anne E Eyler ◽

...

Keyword(s):

Active Learning ◽

Electronic Health Records ◽

High Throughput ◽

Health Records ◽

High Throughput Phenotyping ◽

Electronic Health

Download Full-text

Surrogate-assisted feature extraction for high-throughput phenotyping

Journal of the American Medical Informatics Association ◽

10.1093/jamia/ocw135 ◽

2016 ◽

Vol 24 (e1) ◽

pp. e143-e149 ◽

Cited By ~ 19

Author(s):

Sheng Yu ◽

Abhishek Chakrabortty ◽

Katherine P Liao ◽

Tianrun Cai ◽

Ashwin N Ananthakrishnan ◽

...

Keyword(s):

Feature Extraction ◽

Language Processing ◽

High Throughput ◽

Gold Standard ◽

Characteristic Curve ◽

Feature Selection Method ◽

International Classification Of Diseases ◽

Silver Standard ◽

Automated Feature Extraction ◽

High Throughput Phenotyping

Objective: Phenotyping algorithms are capable of accurately identifying patients with specific phenotypes from within electronic medical records systems. However, developing phenotyping algorithms in a scalable way remains a challenge due to the extensive human resources required. This paper introduces a high-throughput unsupervised feature selection method, which improves the robustness and scalability of electronic medical record phenotyping without compromising its accuracy. Methods: The proposed Surrogate-Assisted Feature Extraction (SAFE) method selects candidate features from a pool of comprehensive medical concepts found in publicly available knowledge sources. The target phenotype’s International Classification of Diseases, Ninth Revision and natural language processing counts, acting as noisy surrogates to the gold-standard labels, are used to create silver-standard labels. Candidate features highly predictive of the silver-standard labels are selected as the final features. Results: Algorithms were trained to identify patients with coronary artery disease, rheumatoid arthritis, Crohn’s disease, and ulcerative colitis using various numbers of labels to compare the performance of features selected by SAFE, a previously published automated feature extraction for phenotyping procedure, and domain experts. The out-of-sample area under the receiver operating characteristic curve and F-score from SAFE algorithms were remarkably higher than those from the other two, especially at small label sizes. Conclusion: SAFE advances high-throughput phenotyping methods by automatically selecting a succinct set of informative features for algorithm training, which in turn reduces overfitting and the needed number of gold-standard labels. SAFE also potentially identifies important features missed by automated feature extraction for phenotyping or experts.

Download Full-text

Developing and Evaluating Mappings of ICD-10 and ICD-10-CM Codes to PheCodes

10.1101/462077 ◽

2018 ◽

Cited By ~ 13

Author(s):

Patrick Wu ◽

Aliya Gifford ◽

Xiangrui Meng ◽

Xue Li ◽

Harry Campbell ◽

...

Keyword(s):

Medical Center ◽

Association Studies ◽

International Classification Of Diseases ◽

Snomed Ct ◽

Unified Medical Language System ◽

Classification Of Diseases ◽

Icd 10 ◽

The Uk ◽

Systematized Nomenclature Of Medicine

AbstractBackgroundThe PheCode system was built upon the International Classification of Diseases, Ninth Revision, Clinical Modification (ICD-9-CM) for phenome-wide association studies (PheWAS) in the electronic health record (EHR).ObjectiveHere, we present our work on the development and evaluation of maps from ICD-10 and ICD-10-CM codes to PheCodes.MethodsWe mapped ICD-10 and ICD-10-CM codes to PheCodes using a number of methods and resources, such as concept relationships and explicit mappings from the Unified Medical Language System (UMLS), Observational Health Data Sciences and Informatics (OHDSI), Systematized Nomenclature of Medicine - Clinical Terms (SNOMED CT), and National Library of Medicine (NLM). We assessed the coverage of the maps in two databases: Vanderbilt University Medical Center (VUMC) using ICD-10-CM and the UK Biobank (UKBB) using ICD-10. We assessed the fidelity of the ICD-10-CM map in comparison to the gold-standard ICD-9-CM→PheCode map by investigating phenotype reproducibility and conducting a PheWAS.ResultsWe mapped >75% of ICD-10-CM and ICD-10 codes to PheCodes. Of the unique codes observed in the VUMC (ICD-10-CM) and UKBB (ICD-10) cohorts, >90% were mapped to PheCodes. We observed 70-75% reproducibility for chronic diseases and <10% for an acute disease. A PheWAS with a lipoprotein(a) (LPA) genetic variant, rs10455872, using the ICD-9-CM and ICD-10-CM maps replicated two genotype-phenotype associations with similar effect sizes: coronary atherosclerosis (ICD-9-CM: P < .001, OR = 1.60 vs. ICD-10-CM: P < .001, OR = 1.60) and with chronic ischemic heart disease (ICD-9-CM: P < .001, OR = 1.5 vs. ICD-10-CM: P < .001, OR = 1.47).ConclusionsThis study introduces the initial “beta” versions of ICD-10 and ICD-10-CM to PheCode maps that will enable researchers to leverage accumulated ICD-10 and ICD-10-CM data for high-throughput PheWAS in the EHR.

Download Full-text

Conventional and hyperspectral time-series imaging of maize lines widely used in field trials

10.1101/169045 ◽

2017 ◽

Author(s):

Zhikai Liang ◽

Piyush Pandey ◽

Vincent Stoerger ◽

Yuhang Xu ◽

Yumou Qiu ◽

...

Keyword(s):

High Throughput ◽

Measurement Errors ◽

Hyperspectral Image ◽

Image Data ◽

Field Trials ◽

Plant Phenotyping ◽

Wide Range ◽

High Throughput Phenotyping ◽

University Of Nebraska Lincoln ◽

The Cost

ABSTRACTMaize (Zea mays ssp. mays) is one of three crops, along with rice and wheat, responsible for more than 1/2 of all calories consumed around the world. Increasing the yield and stress tolerance of these crops is essential to meet the growing need for food. The cost and speed of plant phenotyping is currently the largest constraint on plant breeding efforts. Datasets linking new types of high throughput phenotyping data collected from plants to the performance of the same genotypes under agronomic conditions across a wide range of environments are essential for developing new statistical approaches and computer vision based tools. A set of maize inbreds – primarily recently off patent lines – were phenotyped using a high throughput platform at University of Nebraska-Lincoln. These lines have been previously subjected to high density genotyping, and scored for a core set of 13 phenotypes in field trials across 13 North American states in two years by the Genomes to Fields consortium. A total of 485 GB of image data including RGB, hyperspectral, fluorescence and thermal infrared photos has been released. Correlations between image-based measurements and manual measurements demonstrated the feasibility of quantifying variation in plant architecture using image data. However, naive approaches to measuring traits such as biomass can introduce nonrandom measurement errors confounded with genotype variation. Analysis of hyperspectral image data demonstrated unique signatures from stem tissue. Integrating heritable phenotypes from high-throughput phenotyping data with field data from different environments can reveal previously unknown factors influencing yield plasticity.

Download Full-text