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

Political, economic, and safety concerns have militated for the adoption of Electronic Health Records by physicians in the United States, but current rates of adoption have failed to penetrate the 50% level. A qualitative phenomenological study of practicing physicians reveals stumbling blocks to adoption. Maintaining a physician’s perceived sense of control of the process is key. Electronic Health Records (EHRs) are critical to the support of research, quality control, cost reduction, and implementation of new technologies and methods in healthcare. Progress in the USA towards adoption of standardized EHRs has been halting. The authors discuss the results of a phenomenological study of physicians and draw conclusions that will assist all stakeholders in building a more consistent, comprehensive, and cost-effective healthcare system. When attempting to persuade physicians to migrate to an EMR-based solution, a strong focus on the control that physicians will have should be emphasized. The transition to an EHR system is eased by clearly articulating early in the process the potential benefits and the degree of control physicians can have in the use of the applications.

Download Full-text

Integrating Biomedical Research and Electronic Health Records to Create Knowledge Based Biologically Meaningful Machine Readable Embeddings

10.1101/540963 ◽

2019 ◽

Author(s):

Charlotte A. Nelson ◽

Atul J. Butte ◽

Sergio E. Baranzini

Keyword(s):

Machine Learning ◽

Electronic Health Records ◽

Precision Medicine ◽

Biomedical Research ◽

Current Knowledge ◽

Knowledge Network ◽

Health Records ◽

Major Barrier ◽

Learning Platform ◽

Electronic Health

ABSTRACTIn order to advance precision medicine, detailed clinical features ought to be described in a way that leverages current knowledge. Although data collected from biomedical research is expanding at an almost exponential rate, our ability to transform that information into patient care has not kept at pace. A major barrier preventing this transformation is that multi-dimensional data collection and analysis is usually carried out without much understanding of the underlying knowledge structure. In an effort to bridge this gap, Electronic Health Records (EHRs) of individual patients were connected to a heterogeneous knowledge network called Scalable Precision Medicine Oriented Knowledge Engine (SPOKE). Then an unsupervised machine-learning algorithm was used to create Propagated SPOKE Entry Vectors (PSEVs) that encode the importance of each SPOKE node for any code in the EHRs. We argue that these results, alongside the natural integration of PSEVs into any EHR machine-learning platform, provide a key step toward precision medicine.

Download Full-text

The foundation of precision medicine: integration of electronic health records with genomics through basic, clinical, and translational research

Frontiers in Genetics ◽

10.3389/fgene.2015.00104 ◽

2015 ◽

Vol 6 ◽

Cited By ~ 11

Author(s):

Marylyn D. Ritchie ◽

Mariza de Andrade ◽

Helena Kuivaniemi

Keyword(s):

Electronic Health Records ◽

Translational Research ◽

Precision Medicine ◽

Health Records ◽

Electronic Health ◽

Clinical And Translational Research

Download Full-text

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

PLoS Genetics ◽

10.1371/journal.pgen.1009593 ◽

2021 ◽

Vol 17 (6) ◽

pp. e1009593

Author(s):

Neil S. Zheng ◽

Cosby A. Stone ◽

Lan Jiang ◽

Christian M. Shaffer ◽

V. Eric Kerchberger ◽

...

Keyword(s):

Electronic Health Records ◽

Precision Medicine ◽

Adverse Drug Reactions ◽

High Throughput ◽

Drug Response ◽

Small Sample ◽

Genome Wide Association Studies ◽

Drug Reactions ◽

Health Records ◽

Electronic Health

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

Download Full-text