A survey of clinical phenotyping in selected national networks: demonstrating the need for high-throughput, portable, and computational methods

Rachel L. Richesson, Jimeng Sun, Jyotishman Pathak, Abel N. Kho, Joshua C. Denny

Research output: Contribution to journalArticle

25 Citations (Scopus)

Abstract

Objective The combination of phenomic data from electronic health records (EHR) and clinical data repositories with dense biological data has enabled genomic and pharmacogenomic discovery, a first step toward precision medicine. Computational methods for the identification of clinical phenotypes from EHR data will advance our understanding of disease risk and drug response, and support the practice of precision medicine on a national scale. Methods Based on our experience within three national research networks, we summarize the broad approaches to clinical phenotyping and highlight the important role of these networks in the progression of high-throughput phenotyping and precision medicine. We provide supporting literature in the form of a non-systematic review. Results The practice of clinical phenotyping is evolving to meet the growing demand for scalable, portable, and data driven methods and tools. The resources required for traditional phenotyping algorithms from expert defined rules are significant. In contrast, machine learning approaches that rely on data patterns will require fewer clinical domain experts and resources. Conclusions Machine learning approaches that generate phenotype definitions from patient features and clinical profiles will result in truly computational phenotypes, derived from data rather than experts. Research networks and phenotype developers should cooperate to develop methods, collaboration platforms, and data standards that will enable computational phenotyping and truly modernize biomedical research and precision medicine.

Original languageEnglish (US)
Pages (from-to)57-61
Number of pages5
JournalArtificial Intelligence in Medicine
Volume71
DOIs
StatePublished - Jul 1 2016

Fingerprint

Precision Medicine
Computational methods
Medicine
Throughput
Phenotype
Electronic Health Records
Learning systems
Health
Pharmacogenetics
Research
Biomedical Research
Surveys and Questionnaires
Pharmaceutical Preparations
Machine Learning

Keywords

  • Clinical phenotyping
  • Electronic health records
  • Machine learning
  • Networked research
  • Precision medicine

ASJC Scopus subject areas

  • Artificial Intelligence
  • Medicine (miscellaneous)

Cite this

A survey of clinical phenotyping in selected national networks : demonstrating the need for high-throughput, portable, and computational methods. / Richesson, Rachel L.; Sun, Jimeng; Pathak, Jyotishman; Kho, Abel N.; Denny, Joshua C.

In: Artificial Intelligence in Medicine, Vol. 71, 01.07.2016, p. 57-61.

Research output: Contribution to journalArticle

Richesson, Rachel L. ; Sun, Jimeng ; Pathak, Jyotishman ; Kho, Abel N. ; Denny, Joshua C. / A survey of clinical phenotyping in selected national networks : demonstrating the need for high-throughput, portable, and computational methods. In: Artificial Intelligence in Medicine. 2016 ; Vol. 71. pp. 57-61.
@article{60ae8b914e024fef98a9bddaf5b56949,
title = "A survey of clinical phenotyping in selected national networks: demonstrating the need for high-throughput, portable, and computational methods",
abstract = "Objective The combination of phenomic data from electronic health records (EHR) and clinical data repositories with dense biological data has enabled genomic and pharmacogenomic discovery, a first step toward precision medicine. Computational methods for the identification of clinical phenotypes from EHR data will advance our understanding of disease risk and drug response, and support the practice of precision medicine on a national scale. Methods Based on our experience within three national research networks, we summarize the broad approaches to clinical phenotyping and highlight the important role of these networks in the progression of high-throughput phenotyping and precision medicine. We provide supporting literature in the form of a non-systematic review. Results The practice of clinical phenotyping is evolving to meet the growing demand for scalable, portable, and data driven methods and tools. The resources required for traditional phenotyping algorithms from expert defined rules are significant. In contrast, machine learning approaches that rely on data patterns will require fewer clinical domain experts and resources. Conclusions Machine learning approaches that generate phenotype definitions from patient features and clinical profiles will result in truly computational phenotypes, derived from data rather than experts. Research networks and phenotype developers should cooperate to develop methods, collaboration platforms, and data standards that will enable computational phenotyping and truly modernize biomedical research and precision medicine.",
keywords = "Clinical phenotyping, Electronic health records, Machine learning, Networked research, Precision medicine",
author = "Richesson, {Rachel L.} and Jimeng Sun and Jyotishman Pathak and Kho, {Abel N.} and Denny, {Joshua C.}",
year = "2016",
month = "7",
day = "1",
doi = "10.1016/j.artmed.2016.05.005",
language = "English (US)",
volume = "71",
pages = "57--61",
journal = "Artificial Intelligence in Medicine",
issn = "0933-3657",
publisher = "Elsevier",

}

TY - JOUR

T1 - A survey of clinical phenotyping in selected national networks

T2 - demonstrating the need for high-throughput, portable, and computational methods

AU - Richesson, Rachel L.

AU - Sun, Jimeng

AU - Pathak, Jyotishman

AU - Kho, Abel N.

AU - Denny, Joshua C.

PY - 2016/7/1

Y1 - 2016/7/1

N2 - Objective The combination of phenomic data from electronic health records (EHR) and clinical data repositories with dense biological data has enabled genomic and pharmacogenomic discovery, a first step toward precision medicine. Computational methods for the identification of clinical phenotypes from EHR data will advance our understanding of disease risk and drug response, and support the practice of precision medicine on a national scale. Methods Based on our experience within three national research networks, we summarize the broad approaches to clinical phenotyping and highlight the important role of these networks in the progression of high-throughput phenotyping and precision medicine. We provide supporting literature in the form of a non-systematic review. Results The practice of clinical phenotyping is evolving to meet the growing demand for scalable, portable, and data driven methods and tools. The resources required for traditional phenotyping algorithms from expert defined rules are significant. In contrast, machine learning approaches that rely on data patterns will require fewer clinical domain experts and resources. Conclusions Machine learning approaches that generate phenotype definitions from patient features and clinical profiles will result in truly computational phenotypes, derived from data rather than experts. Research networks and phenotype developers should cooperate to develop methods, collaboration platforms, and data standards that will enable computational phenotyping and truly modernize biomedical research and precision medicine.

AB - Objective The combination of phenomic data from electronic health records (EHR) and clinical data repositories with dense biological data has enabled genomic and pharmacogenomic discovery, a first step toward precision medicine. Computational methods for the identification of clinical phenotypes from EHR data will advance our understanding of disease risk and drug response, and support the practice of precision medicine on a national scale. Methods Based on our experience within three national research networks, we summarize the broad approaches to clinical phenotyping and highlight the important role of these networks in the progression of high-throughput phenotyping and precision medicine. We provide supporting literature in the form of a non-systematic review. Results The practice of clinical phenotyping is evolving to meet the growing demand for scalable, portable, and data driven methods and tools. The resources required for traditional phenotyping algorithms from expert defined rules are significant. In contrast, machine learning approaches that rely on data patterns will require fewer clinical domain experts and resources. Conclusions Machine learning approaches that generate phenotype definitions from patient features and clinical profiles will result in truly computational phenotypes, derived from data rather than experts. Research networks and phenotype developers should cooperate to develop methods, collaboration platforms, and data standards that will enable computational phenotyping and truly modernize biomedical research and precision medicine.

KW - Clinical phenotyping

KW - Electronic health records

KW - Machine learning

KW - Networked research

KW - Precision medicine

UR - http://www.scopus.com/inward/record.url?scp=84978069214&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84978069214&partnerID=8YFLogxK

U2 - 10.1016/j.artmed.2016.05.005

DO - 10.1016/j.artmed.2016.05.005

M3 - Article

C2 - 27506131

AN - SCOPUS:84978069214

VL - 71

SP - 57

EP - 61

JO - Artificial Intelligence in Medicine

JF - Artificial Intelligence in Medicine

SN - 0933-3657

ER -