Ontology-Guided Principal Component Analysis: Reaching the limits of the doctor-in-the-loop

Sandra Wartner, Dominic Girardi, Johannes Trenkler, Manuela Wiesinger-Widi, Raimund Kleiser, Andreas Holzinger

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

Biomedical research requires deep domain expertise to perform analyses of complex data sets, assisted by mathematical expertise
provided by data scientists who design and develop sophisticated methods and tools. Such methods and tools not only require preprocessing
of the data, but most of all a meaningful input selection. Usually, data
scientists do not have sufficient background knowledge about the origin
of the data and the biomedical problems to be solved, consequently a
doctor-in-the-loop can be of great help here. In this paper we revise the
viability of integrating an analysis guided visualization component in an
ontology-guided data infrastructure, exemplified by the principal component analysis. We evaluated this approach by examining the potential for
intelligent support of medical experts on the case of cerebral aneurysms
research.
LanguageEnglish
Title of host publicationSpringer Lecture Notes in Computer Science LNCS 9832
Subtitle of host publicationInformation Technology in Bio- and Medical Informatics
Place of PublicationHeidelberg, Berlin, New York
PublisherSpringer
Pages22-33
DOIs
StatusPublished - 19 Aug 2016

Fingerprint

Principal component analysis
Ontology
Visualization

Keywords

  • health informatics
  • Machine Learning
  • Doctor-in-the-loop

ASJC Scopus subject areas

  • Artificial Intelligence

Fields of Expertise

  • Information, Communication & Computing

Treatment code (Nähere Zuordnung)

  • Basic - Fundamental (Grundlagenforschung)

Cite this

Wartner, S., Girardi, D., Trenkler, J., Wiesinger-Widi, M., Kleiser, R., & Holzinger, A. (2016). Ontology-Guided Principal Component Analysis: Reaching the limits of the doctor-in-the-loop. In Springer Lecture Notes in Computer Science LNCS 9832: Information Technology in Bio- and Medical Informatics (pp. 22-33). Heidelberg, Berlin, New York: Springer. DOI: 10.1007/978-3-319-43949-5_2

Ontology-Guided Principal Component Analysis: Reaching the limits of the doctor-in-the-loop. / Wartner, Sandra; Girardi, Dominic; Trenkler, Johannes; Wiesinger-Widi, Manuela; Kleiser, Raimund; Holzinger, Andreas.

Springer Lecture Notes in Computer Science LNCS 9832: Information Technology in Bio- and Medical Informatics. Heidelberg, Berlin, New York : Springer, 2016. p. 22-33.

Research output: Chapter in Book/Report/Conference proceedingChapter

Wartner, S, Girardi, D, Trenkler, J, Wiesinger-Widi, M, Kleiser, R & Holzinger, A 2016, Ontology-Guided Principal Component Analysis: Reaching the limits of the doctor-in-the-loop. in Springer Lecture Notes in Computer Science LNCS 9832: Information Technology in Bio- and Medical Informatics. Springer, Heidelberg, Berlin, New York, pp. 22-33. DOI: 10.1007/978-3-319-43949-5_2
Wartner S, Girardi D, Trenkler J, Wiesinger-Widi M, Kleiser R, Holzinger A. Ontology-Guided Principal Component Analysis: Reaching the limits of the doctor-in-the-loop. In Springer Lecture Notes in Computer Science LNCS 9832: Information Technology in Bio- and Medical Informatics. Heidelberg, Berlin, New York: Springer. 2016. p. 22-33. Available from, DOI: 10.1007/978-3-319-43949-5_2
Wartner, Sandra ; Girardi, Dominic ; Trenkler, Johannes ; Wiesinger-Widi, Manuela ; Kleiser, Raimund ; Holzinger, Andreas. / Ontology-Guided Principal Component Analysis: Reaching the limits of the doctor-in-the-loop. Springer Lecture Notes in Computer Science LNCS 9832: Information Technology in Bio- and Medical Informatics. Heidelberg, Berlin, New York : Springer, 2016. pp. 22-33
@inbook{71e3c365d14948d8a2cb1f3e0a0e753a,
title = "Ontology-Guided Principal Component Analysis: Reaching the limits of the doctor-in-the-loop",
abstract = "Biomedical research requires deep domain expertise to perform analyses of complex data sets, assisted by mathematical expertiseprovided by data scientists who design and develop sophisticated methods and tools. Such methods and tools not only require preprocessingof the data, but most of all a meaningful input selection. Usually, datascientists do not have sufficient background knowledge about the originof the data and the biomedical problems to be solved, consequently adoctor-in-the-loop can be of great help here. In this paper we revise theviability of integrating an analysis guided visualization component in anontology-guided data infrastructure, exemplified by the principal component analysis. We evaluated this approach by examining the potential forintelligent support of medical experts on the case of cerebral aneurysmsresearch.",
keywords = "health informatics, Machine Learning, Doctor-in-the-loop",
author = "Sandra Wartner and Dominic Girardi and Johannes Trenkler and Manuela Wiesinger-Widi and Raimund Kleiser and Andreas Holzinger",
year = "2016",
month = "8",
day = "19",
doi = "10.1007/978-3-319-43949-5_2",
language = "English",
pages = "22--33",
booktitle = "Springer Lecture Notes in Computer Science LNCS 9832",
publisher = "Springer",

}

TY - CHAP

T1 - Ontology-Guided Principal Component Analysis: Reaching the limits of the doctor-in-the-loop

AU - Wartner,Sandra

AU - Girardi,Dominic

AU - Trenkler,Johannes

AU - Wiesinger-Widi,Manuela

AU - Kleiser,Raimund

AU - Holzinger,Andreas

PY - 2016/8/19

Y1 - 2016/8/19

N2 - Biomedical research requires deep domain expertise to perform analyses of complex data sets, assisted by mathematical expertiseprovided by data scientists who design and develop sophisticated methods and tools. Such methods and tools not only require preprocessingof the data, but most of all a meaningful input selection. Usually, datascientists do not have sufficient background knowledge about the originof the data and the biomedical problems to be solved, consequently adoctor-in-the-loop can be of great help here. In this paper we revise theviability of integrating an analysis guided visualization component in anontology-guided data infrastructure, exemplified by the principal component analysis. We evaluated this approach by examining the potential forintelligent support of medical experts on the case of cerebral aneurysmsresearch.

AB - Biomedical research requires deep domain expertise to perform analyses of complex data sets, assisted by mathematical expertiseprovided by data scientists who design and develop sophisticated methods and tools. Such methods and tools not only require preprocessingof the data, but most of all a meaningful input selection. Usually, datascientists do not have sufficient background knowledge about the originof the data and the biomedical problems to be solved, consequently adoctor-in-the-loop can be of great help here. In this paper we revise theviability of integrating an analysis guided visualization component in anontology-guided data infrastructure, exemplified by the principal component analysis. We evaluated this approach by examining the potential forintelligent support of medical experts on the case of cerebral aneurysmsresearch.

KW - health informatics

KW - Machine Learning

KW - Doctor-in-the-loop

U2 - 10.1007/978-3-319-43949-5_2

DO - 10.1007/978-3-319-43949-5_2

M3 - Chapter

SP - 22

EP - 33

BT - Springer Lecture Notes in Computer Science LNCS 9832

PB - Springer

CY - Heidelberg, Berlin, New York

ER -