A MATLAB Toolbox for Classification and Visualization of Heterogenous Multi-Scale Human Data Using the Disease State Fingerprint Method

Luc Cluitmans, Jussi Mattila, Hilkka Runtti, Mark van Gils, Jyrki Lötjönen

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

2 Citations (Scopus)

Abstract

As the amount of data acquired from humans is constantly increasing, efficient tools are needed for extracting relevant information from this data. This paper presents a Matlab implementation of a method to classify and visually explore (highly) multi-variate patient data. The method uses the so-called Disease State Index (DSI) which measures the fit of a test subject's data to two classes present in the data (e.g. 'controls' and 'positives'). DSI values of the different variables measured from a patient can be combined and visualized in a tree-like form using the Disease State Fingerprint (DSF) method. This allows a researcher to explore and understand the relevance of the different variables in classification problems. Moreover, the method is robust with respect to missing data. After giving an introduction to the DSF and DSI methods, the paper describes the steps required to use the methods and presents a MATLAB toolbox to perform these steps. To demonstrate the methods' versatility, the paper illustrates the usage of the toolbox in a few different contexts in which personal health data is to be classified. With this implementation, a powerful and flexible tool is made available to the biomedical research community.
Original languageEnglish
Title of host publicationpHealth 2013
Subtitle of host publicationProceedings of the 10th International Conference on Wearable Micro and Nano Technologies for Personalized Health
Place of PublicationAmsterdam
PublisherIOS Press
Pages77-82
ISBN (Print)978-1-61499-267-7 , 978-1-61499-268-4
DOIs
Publication statusPublished - 2013
MoE publication typeNot Eligible
Event10th International Conference on Wearable Micro and Nano Technologies for Personalized Health, pHealth 2013 - Tallinn, Estonia
Duration: 26 Jun 201328 Jun 2013

Publication series

SeriesStudies in Health Technology and Informatics
Volume189
ISSN0926-9630

Conference

Conference10th International Conference on Wearable Micro and Nano Technologies for Personalized Health, pHealth 2013
Abbreviated titlepHealth 2013
CountryEstonia
CityTallinn
Period26/06/1328/06/13

Fingerprint

MATLAB
Visualization
Health

Keywords

  • decision support
  • multi-variate classification
  • data visualization
  • MATLAB

Cite this

Cluitmans, L., Mattila, J., Runtti, H., van Gils, M., & Lötjönen, J. (2013). A MATLAB Toolbox for Classification and Visualization of Heterogenous Multi-Scale Human Data Using the Disease State Fingerprint Method. In pHealth 2013: Proceedings of the 10th International Conference on Wearable Micro and Nano Technologies for Personalized Health (pp. 77-82). Amsterdam: IOS Press. Studies in Health Technology and Informatics, Vol.. 189 https://doi.org/10.3233/978-1-61499-268-4-77
Cluitmans, Luc ; Mattila, Jussi ; Runtti, Hilkka ; van Gils, Mark ; Lötjönen, Jyrki. / A MATLAB Toolbox for Classification and Visualization of Heterogenous Multi-Scale Human Data Using the Disease State Fingerprint Method. pHealth 2013: Proceedings of the 10th International Conference on Wearable Micro and Nano Technologies for Personalized Health. Amsterdam : IOS Press, 2013. pp. 77-82 (Studies in Health Technology and Informatics, Vol. 189).
@inproceedings{44a57b54da12417cabe6961520d524bc,
title = "A MATLAB Toolbox for Classification and Visualization of Heterogenous Multi-Scale Human Data Using the Disease State Fingerprint Method",
abstract = "As the amount of data acquired from humans is constantly increasing, efficient tools are needed for extracting relevant information from this data. This paper presents a Matlab implementation of a method to classify and visually explore (highly) multi-variate patient data. The method uses the so-called Disease State Index (DSI) which measures the fit of a test subject's data to two classes present in the data (e.g. 'controls' and 'positives'). DSI values of the different variables measured from a patient can be combined and visualized in a tree-like form using the Disease State Fingerprint (DSF) method. This allows a researcher to explore and understand the relevance of the different variables in classification problems. Moreover, the method is robust with respect to missing data. After giving an introduction to the DSF and DSI methods, the paper describes the steps required to use the methods and presents a MATLAB toolbox to perform these steps. To demonstrate the methods' versatility, the paper illustrates the usage of the toolbox in a few different contexts in which personal health data is to be classified. With this implementation, a powerful and flexible tool is made available to the biomedical research community.",
keywords = "decision support, multi-variate classification, data visualization, MATLAB",
author = "Luc Cluitmans and Jussi Mattila and Hilkka Runtti and {van Gils}, Mark and Jyrki L{\"o}tj{\"o}nen",
note = "Project code: 72578",
year = "2013",
doi = "10.3233/978-1-61499-268-4-77",
language = "English",
isbn = "978-1-61499-267-7",
series = "Studies in Health Technology and Informatics",
publisher = "IOS Press",
pages = "77--82",
booktitle = "pHealth 2013",
address = "Netherlands",

}

Cluitmans, L, Mattila, J, Runtti, H, van Gils, M & Lötjönen, J 2013, A MATLAB Toolbox for Classification and Visualization of Heterogenous Multi-Scale Human Data Using the Disease State Fingerprint Method. in pHealth 2013: Proceedings of the 10th International Conference on Wearable Micro and Nano Technologies for Personalized Health. IOS Press, Amsterdam, Studies in Health Technology and Informatics, vol. 189, pp. 77-82, 10th International Conference on Wearable Micro and Nano Technologies for Personalized Health, pHealth 2013, Tallinn, Estonia, 26/06/13. https://doi.org/10.3233/978-1-61499-268-4-77

A MATLAB Toolbox for Classification and Visualization of Heterogenous Multi-Scale Human Data Using the Disease State Fingerprint Method. / Cluitmans, Luc; Mattila, Jussi; Runtti, Hilkka; van Gils, Mark; Lötjönen, Jyrki.

pHealth 2013: Proceedings of the 10th International Conference on Wearable Micro and Nano Technologies for Personalized Health. Amsterdam : IOS Press, 2013. p. 77-82 (Studies in Health Technology and Informatics, Vol. 189).

Research output: Chapter in Book/Report/Conference proceedingConference article in proceedingsScientificpeer-review

TY - GEN

T1 - A MATLAB Toolbox for Classification and Visualization of Heterogenous Multi-Scale Human Data Using the Disease State Fingerprint Method

AU - Cluitmans, Luc

AU - Mattila, Jussi

AU - Runtti, Hilkka

AU - van Gils, Mark

AU - Lötjönen, Jyrki

N1 - Project code: 72578

PY - 2013

Y1 - 2013

N2 - As the amount of data acquired from humans is constantly increasing, efficient tools are needed for extracting relevant information from this data. This paper presents a Matlab implementation of a method to classify and visually explore (highly) multi-variate patient data. The method uses the so-called Disease State Index (DSI) which measures the fit of a test subject's data to two classes present in the data (e.g. 'controls' and 'positives'). DSI values of the different variables measured from a patient can be combined and visualized in a tree-like form using the Disease State Fingerprint (DSF) method. This allows a researcher to explore and understand the relevance of the different variables in classification problems. Moreover, the method is robust with respect to missing data. After giving an introduction to the DSF and DSI methods, the paper describes the steps required to use the methods and presents a MATLAB toolbox to perform these steps. To demonstrate the methods' versatility, the paper illustrates the usage of the toolbox in a few different contexts in which personal health data is to be classified. With this implementation, a powerful and flexible tool is made available to the biomedical research community.

AB - As the amount of data acquired from humans is constantly increasing, efficient tools are needed for extracting relevant information from this data. This paper presents a Matlab implementation of a method to classify and visually explore (highly) multi-variate patient data. The method uses the so-called Disease State Index (DSI) which measures the fit of a test subject's data to two classes present in the data (e.g. 'controls' and 'positives'). DSI values of the different variables measured from a patient can be combined and visualized in a tree-like form using the Disease State Fingerprint (DSF) method. This allows a researcher to explore and understand the relevance of the different variables in classification problems. Moreover, the method is robust with respect to missing data. After giving an introduction to the DSF and DSI methods, the paper describes the steps required to use the methods and presents a MATLAB toolbox to perform these steps. To demonstrate the methods' versatility, the paper illustrates the usage of the toolbox in a few different contexts in which personal health data is to be classified. With this implementation, a powerful and flexible tool is made available to the biomedical research community.

KW - decision support

KW - multi-variate classification

KW - data visualization

KW - MATLAB

U2 - 10.3233/978-1-61499-268-4-77

DO - 10.3233/978-1-61499-268-4-77

M3 - Conference article in proceedings

SN - 978-1-61499-267-7

SN - 978-1-61499-268-4

T3 - Studies in Health Technology and Informatics

SP - 77

EP - 82

BT - pHealth 2013

PB - IOS Press

CY - Amsterdam

ER -

Cluitmans L, Mattila J, Runtti H, van Gils M, Lötjönen J. A MATLAB Toolbox for Classification and Visualization of Heterogenous Multi-Scale Human Data Using the Disease State Fingerprint Method. In pHealth 2013: Proceedings of the 10th International Conference on Wearable Micro and Nano Technologies for Personalized Health. Amsterdam: IOS Press. 2013. p. 77-82. (Studies in Health Technology and Informatics, Vol. 189). https://doi.org/10.3233/978-1-61499-268-4-77