Integration of Python Modules in a MATLAB-Based Predictive Analytics Toolset for Healthcare

Lukas Haider; Lukas Haider; Martin Baumgartner; Martin Baumgartner; Dieter Hayn; Dieter Hayn; Günter Schreier; Günter Schreier

doi:10.3233/SHTI220369

Integration of Python Modules in a MATLAB-Based Predictive Analytics Toolset for Healthcare

Lukas Haider (Speaker), Lukas Haider, Martin Baumgartner, Martin Baumgartner, Dieter Hayn, Dieter Hayn, Günter Schreier, Günter Schreier

Digital Health Information Systems

Research output: Chapter in Book or Conference Proceedings › Conference Proceedings with Oral Presentation › peer-review

Abstract

Background: Python and MATLAB both are common tools used for predictive modelling applications, not only in healthcare. In our predictive modelling group, both tools are widely used. None of the two tools is optimal for all tasks along the value chain of predictive modelling in healthcare. Objectives: The aim of this study was to explore different ways to extend our MATLAB-based toolset with Python functions. Methods: Pre-existing interfaces between MATLAB and Python have been evaluated and more comprehensive interfaces have been designed to exchange even complex data formats such as MATLAB tables. Results: The interfaces have successfully been implemented and they were validated in a Natural Language Processing scenario based on free-text notes from a telehealth services for heart failure patients. Conclusion: Integration of Python modules in our MATLAB toolset is possible. Further improvements especially in terms of performance, are required if large datasets need to be exchanged. A big advantage of our concept is that tabular data can be exchanged between MATLAB and Python without loss and the Python functions are called dynamically via the interface.

Original language	English
Title of host publication	dHealth 2022 – Proceedings of the 16th Health Informatics Meets Digital Health Conference
Editors	Günter Schreier, Bernhard Erich Pfeifer, Martin Baumgartner, Dieter Hayn
Publisher	IOS Press
Pages	197-204
Number of pages	8
ISBN (Print)	978-1-64368-282-2
DOIs	https://doi.org/10.3233/SHTI220369
Publication status	Published - 2022
Event	dHealth 2022 - 16th Annual Conference on Health Informatics meets Digital Health - Duration: 24 May 2022 → 25 May 2022

Conference

Conference	dHealth 2022 - 16th Annual Conference on Health Informatics meets Digital Health
Period	24/05/22 → 25/05/22

Research Field

Exploration of Digital Health

Keywords

MATLAB
Python
Predictive Analytics
Machine learning
Data exchange
Interfacing

Access to Document

10.3233/SHTI220369Licence: Unspecified

Cite this

Haider, L., Haider, L., Baumgartner, M., Baumgartner, M., Hayn, D., Hayn, D., Schreier, G., & Schreier, G. (2022). Integration of Python Modules in a MATLAB-Based Predictive Analytics Toolset for Healthcare. In G. Schreier, B. E. Pfeifer, M. Baumgartner, & D. Hayn (Eds.), dHealth 2022 – Proceedings of the 16th Health Informatics Meets Digital Health Conference (pp. 197-204). IOS Press. https://doi.org/10.3233/SHTI220369

@inproceedings{02f1a31b470c48b58e81935fbe316cb8,

title = "Integration of Python Modules in a MATLAB-Based Predictive Analytics Toolset for Healthcare",

abstract = "Background: Python and MATLAB both are common tools used for predictive modelling applications, not only in healthcare. In our predictive modelling group, both tools are widely used. None of the two tools is optimal for all tasks along the value chain of predictive modelling in healthcare. Objectives: The aim of this study was to explore different ways to extend our MATLAB-based toolset with Python functions. Methods: Pre-existing interfaces between MATLAB and Python have been evaluated and more comprehensive interfaces have been designed to exchange even complex data formats such as MATLAB tables. Results: The interfaces have successfully been implemented and they were validated in a Natural Language Processing scenario based on free-text notes from a telehealth services for heart failure patients. Conclusion: Integration of Python modules in our MATLAB toolset is possible. Further improvements especially in terms of performance, are required if large datasets need to be exchanged. A big advantage of our concept is that tabular data can be exchanged between MATLAB and Python without loss and the Python functions are called dynamically via the interface.",

keywords = "MATLAB, Python, Predictive Analytics, Machine learning, Data exchange, Interfacing, MATLAB, Python, Predictive Analytics, Machine learning, Data exchange, Interfacing",

author = "Lukas Haider and Lukas Haider and Martin Baumgartner and Martin Baumgartner and Dieter Hayn and Dieter Hayn and G{\"u}nter Schreier and G{\"u}nter Schreier",

year = "2022",

doi = "10.3233/SHTI220369",

language = "English",

isbn = "978-1-64368-282-2",

pages = "197--204",

editor = "G{\"u}nter Schreier and Pfeifer, {Bernhard Erich} and Martin Baumgartner and Dieter Hayn",

booktitle = "dHealth 2022 – Proceedings of the 16th Health Informatics Meets Digital Health Conference",

publisher = "IOS Press",

address = "United States",

note = "dHealth 2022 - 16th Annual Conference on Health Informatics meets Digital Health ; Conference date: 24-05-2022 Through 25-05-2022",

}

Haider, L, Haider, L, Baumgartner, M, Baumgartner, M, Hayn, D, Hayn, D, Schreier, G & Schreier, G 2022, Integration of Python Modules in a MATLAB-Based Predictive Analytics Toolset for Healthcare. in G Schreier, BE Pfeifer, M Baumgartner & D Hayn (eds), dHealth 2022 – Proceedings of the 16th Health Informatics Meets Digital Health Conference. IOS Press, pp. 197-204, dHealth 2022 - 16th Annual Conference on Health Informatics meets Digital Health, 24/05/22. https://doi.org/10.3233/SHTI220369

Integration of Python Modules in a MATLAB-Based Predictive Analytics Toolset for Healthcare. / Haider, Lukas (Speaker); Haider, Lukas; Baumgartner, Martin et al.
dHealth 2022 – Proceedings of the 16th Health Informatics Meets Digital Health Conference. ed. / Günter Schreier; Bernhard Erich Pfeifer; Martin Baumgartner; Dieter Hayn. IOS Press, 2022. p. 197-204.

Research output: Chapter in Book or Conference Proceedings › Conference Proceedings with Oral Presentation › peer-review

TY - GEN

T1 - Integration of Python Modules in a MATLAB-Based Predictive Analytics Toolset for Healthcare

AU - Haider, Lukas

AU - Baumgartner, Martin

AU - Hayn, Dieter

AU - Schreier, Günter

A2 - Haider, Lukas

A2 - Schreier, Günter

A2 - Pfeifer, Bernhard Erich

A2 - Baumgartner, Martin

A2 - Hayn, Dieter

PY - 2022

Y1 - 2022

N2 - Background: Python and MATLAB both are common tools used for predictive modelling applications, not only in healthcare. In our predictive modelling group, both tools are widely used. None of the two tools is optimal for all tasks along the value chain of predictive modelling in healthcare. Objectives: The aim of this study was to explore different ways to extend our MATLAB-based toolset with Python functions. Methods: Pre-existing interfaces between MATLAB and Python have been evaluated and more comprehensive interfaces have been designed to exchange even complex data formats such as MATLAB tables. Results: The interfaces have successfully been implemented and they were validated in a Natural Language Processing scenario based on free-text notes from a telehealth services for heart failure patients. Conclusion: Integration of Python modules in our MATLAB toolset is possible. Further improvements especially in terms of performance, are required if large datasets need to be exchanged. A big advantage of our concept is that tabular data can be exchanged between MATLAB and Python without loss and the Python functions are called dynamically via the interface.

AB - Background: Python and MATLAB both are common tools used for predictive modelling applications, not only in healthcare. In our predictive modelling group, both tools are widely used. None of the two tools is optimal for all tasks along the value chain of predictive modelling in healthcare. Objectives: The aim of this study was to explore different ways to extend our MATLAB-based toolset with Python functions. Methods: Pre-existing interfaces between MATLAB and Python have been evaluated and more comprehensive interfaces have been designed to exchange even complex data formats such as MATLAB tables. Results: The interfaces have successfully been implemented and they were validated in a Natural Language Processing scenario based on free-text notes from a telehealth services for heart failure patients. Conclusion: Integration of Python modules in our MATLAB toolset is possible. Further improvements especially in terms of performance, are required if large datasets need to be exchanged. A big advantage of our concept is that tabular data can be exchanged between MATLAB and Python without loss and the Python functions are called dynamically via the interface.

KW - MATLAB

KW - Python

KW - Predictive Analytics

KW - Machine learning

KW - Data exchange

KW - Interfacing

KW - MATLAB

KW - Python

KW - Predictive Analytics

KW - Machine learning

KW - Data exchange

KW - Interfacing

U2 - 10.3233/SHTI220369

DO - 10.3233/SHTI220369

M3 - Conference Proceedings with Oral Presentation

SN - 978-1-64368-282-2

SP - 197

EP - 204

BT - dHealth 2022 – Proceedings of the 16th Health Informatics Meets Digital Health Conference

PB - IOS Press

T2 - dHealth 2022 - 16th Annual Conference on Health Informatics meets Digital Health

Y2 - 24 May 2022 through 25 May 2022

ER -

Integration of Python Modules in a MATLAB-Based Predictive Analytics Toolset for Healthcare

Abstract

Conference

Research Field

Keywords

Access to Document

Fingerprint

Cite this