Informatics and machine learning to define the phenotype

Anna Okula Basile, Marylyn De Riggi Ritchie

Research output: Contribution to journalReview article

3 Citations (Scopus)

Abstract

Introduction: For the past decade, the focus of complex disease research has been the genotype. From technological advancements to the development of analysis methods, great progress has been made. However, advances in our definition of the phenotype have remained stagnant. Phenotype characterization has recently emerged as an exciting area of informatics and machine learning. The copious amounts of diverse biomedical data that have been collected may be leveraged with data-driven approaches to elucidate trait-related features and patterns. Areas covered: In this review, the authors discuss the phenotype in traditional genetic associations and the challenges this has imposed.Approaches for phenotype refinement that can aid in more accurate characterization of traits are also discussed. Further, the authors highlight promising machine learning approaches for establishing a phenotype and the challenges of electronic health record (EHR)-derived data. Expert commentary: The authors hypothesize that through unsupervised machine learning, data-driven approaches can be used to define phenotypes rather than relying on expert clinician knowledge. Through the use of machine learning and an unbiased set of features extracted from clinical repositories, researchers will have the potential to further understand complex traits and identify patient subgroups. This knowledge may lead to more preventative and precise clinical care.

Original languageEnglish (US)
Pages (from-to)219-226
Number of pages8
JournalExpert Review of Molecular Diagnostics
Volume18
Issue number3
DOIs
StatePublished - Mar 4 2018

Fingerprint

Informatics
Phenotype
Electronic Health Records
Machine Learning
Genotype
Research Personnel
Research

All Science Journal Classification (ASJC) codes

  • Pathology and Forensic Medicine
  • Molecular Medicine
  • Molecular Biology
  • Genetics

Cite this

Basile, Anna Okula ; Ritchie, Marylyn De Riggi. / Informatics and machine learning to define the phenotype. In: Expert Review of Molecular Diagnostics. 2018 ; Vol. 18, No. 3. pp. 219-226.
@article{1043a663f10b4eb18b98a9c74082da1b,
title = "Informatics and machine learning to define the phenotype",
abstract = "Introduction: For the past decade, the focus of complex disease research has been the genotype. From technological advancements to the development of analysis methods, great progress has been made. However, advances in our definition of the phenotype have remained stagnant. Phenotype characterization has recently emerged as an exciting area of informatics and machine learning. The copious amounts of diverse biomedical data that have been collected may be leveraged with data-driven approaches to elucidate trait-related features and patterns. Areas covered: In this review, the authors discuss the phenotype in traditional genetic associations and the challenges this has imposed.Approaches for phenotype refinement that can aid in more accurate characterization of traits are also discussed. Further, the authors highlight promising machine learning approaches for establishing a phenotype and the challenges of electronic health record (EHR)-derived data. Expert commentary: The authors hypothesize that through unsupervised machine learning, data-driven approaches can be used to define phenotypes rather than relying on expert clinician knowledge. Through the use of machine learning and an unbiased set of features extracted from clinical repositories, researchers will have the potential to further understand complex traits and identify patient subgroups. This knowledge may lead to more preventative and precise clinical care.",
author = "Basile, {Anna Okula} and Ritchie, {Marylyn De Riggi}",
year = "2018",
month = "3",
day = "4",
doi = "10.1080/14737159.2018.1439380",
language = "English (US)",
volume = "18",
pages = "219--226",
journal = "Expert Review of Molecular Diagnostics",
issn = "1473-7159",
publisher = "Expert Reviews Ltd.",
number = "3",

}

Informatics and machine learning to define the phenotype. / Basile, Anna Okula; Ritchie, Marylyn De Riggi.

In: Expert Review of Molecular Diagnostics, Vol. 18, No. 3, 04.03.2018, p. 219-226.

Research output: Contribution to journalReview article

TY - JOUR

T1 - Informatics and machine learning to define the phenotype

AU - Basile, Anna Okula

AU - Ritchie, Marylyn De Riggi

PY - 2018/3/4

Y1 - 2018/3/4

N2 - Introduction: For the past decade, the focus of complex disease research has been the genotype. From technological advancements to the development of analysis methods, great progress has been made. However, advances in our definition of the phenotype have remained stagnant. Phenotype characterization has recently emerged as an exciting area of informatics and machine learning. The copious amounts of diverse biomedical data that have been collected may be leveraged with data-driven approaches to elucidate trait-related features and patterns. Areas covered: In this review, the authors discuss the phenotype in traditional genetic associations and the challenges this has imposed.Approaches for phenotype refinement that can aid in more accurate characterization of traits are also discussed. Further, the authors highlight promising machine learning approaches for establishing a phenotype and the challenges of electronic health record (EHR)-derived data. Expert commentary: The authors hypothesize that through unsupervised machine learning, data-driven approaches can be used to define phenotypes rather than relying on expert clinician knowledge. Through the use of machine learning and an unbiased set of features extracted from clinical repositories, researchers will have the potential to further understand complex traits and identify patient subgroups. This knowledge may lead to more preventative and precise clinical care.

AB - Introduction: For the past decade, the focus of complex disease research has been the genotype. From technological advancements to the development of analysis methods, great progress has been made. However, advances in our definition of the phenotype have remained stagnant. Phenotype characterization has recently emerged as an exciting area of informatics and machine learning. The copious amounts of diverse biomedical data that have been collected may be leveraged with data-driven approaches to elucidate trait-related features and patterns. Areas covered: In this review, the authors discuss the phenotype in traditional genetic associations and the challenges this has imposed.Approaches for phenotype refinement that can aid in more accurate characterization of traits are also discussed. Further, the authors highlight promising machine learning approaches for establishing a phenotype and the challenges of electronic health record (EHR)-derived data. Expert commentary: The authors hypothesize that through unsupervised machine learning, data-driven approaches can be used to define phenotypes rather than relying on expert clinician knowledge. Through the use of machine learning and an unbiased set of features extracted from clinical repositories, researchers will have the potential to further understand complex traits and identify patient subgroups. This knowledge may lead to more preventative and precise clinical care.

UR - http://www.scopus.com/inward/record.url?scp=85044093149&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85044093149&partnerID=8YFLogxK

U2 - 10.1080/14737159.2018.1439380

DO - 10.1080/14737159.2018.1439380

M3 - Review article

C2 - 29431517

AN - SCOPUS:85044093149

VL - 18

SP - 219

EP - 226

JO - Expert Review of Molecular Diagnostics

JF - Expert Review of Molecular Diagnostics

SN - 1473-7159

IS - 3

ER -