TU Darmstadt / ULB / TUbiblio

Predicting Pulmonary Function Testing from Quantified Computed Tomography Using Machine Learning Algorithms in Patients with COPD

Gawlitza, Joshua and Sturm, Timo and Spohrer, Kai and Henzler, Thomas and Akin, Ibrahim and Schönberg, Stefan and Borggrefe, Martin and Haubenreisser, Holger and Trinkmann, Frederik (2019):
Predicting Pulmonary Function Testing from Quantified Computed Tomography Using Machine Learning Algorithms in Patients with COPD.
In: Diagnostics, p. 33, 9, (1), ISSN 2075-4418,
DOI: 10.3390/diagnostics9010033,
[Online-Edition: https://www.mdpi.com/2075-4418/9/1/33],
[Article]

Abstract

Introduction: Quantitative computed tomography (qCT) is an emergent technique for diagnostics and research in patients with chronic obstructive pulmonary disease (COPD). qCT parameters demonstrate a correlation with pulmonary function tests and symptoms. However, qCT only provides anatomical, not functional, information. We evaluated five distinct, partial-machine learning-based mathematical models to predict lung function parameters from qCT values in comparison with pulmonary function tests. Methods: 75 patients with diagnosed COPD underwent body plethysmography and a dose-optimized qCT examination on a third-generation, dual-source CT with inspiration and expiration. Delta values (inspiration—expiration) were calculated afterwards. Four parameters were quantified: mean lung density, lung volume low-attenuated volume, and full width at half maximum. Five models were evaluated for best prediction: average prediction, median prediction, k-nearest neighbours (kNN), gradient boosting, and multilayer perceptron. Results: The lowest mean relative error (MRE) was calculated for the kNN model with 16%. Similar low MREs were found for polynomial regression as well as gradient boosting-based prediction. Other models led to higher MREs and thereby worse predictive performance. Beyond the sole MRE, distinct differences in prediction performance, dependent on the initial dataset (expiration, inspiration, delta), were found. Conclusion: Different, partially machine learning-based models allow the prediction of lung function values from static qCT parameters within a reasonable margin of error. Therefore, qCT parameters may contain more information than we currently utilize and can potentially augment standard functional lung testing.

Item Type: Article
Erschienen: 2019
Creators: Gawlitza, Joshua and Sturm, Timo and Spohrer, Kai and Henzler, Thomas and Akin, Ibrahim and Schönberg, Stefan and Borggrefe, Martin and Haubenreisser, Holger and Trinkmann, Frederik
Title: Predicting Pulmonary Function Testing from Quantified Computed Tomography Using Machine Learning Algorithms in Patients with COPD
Language: English
Abstract:

Introduction: Quantitative computed tomography (qCT) is an emergent technique for diagnostics and research in patients with chronic obstructive pulmonary disease (COPD). qCT parameters demonstrate a correlation with pulmonary function tests and symptoms. However, qCT only provides anatomical, not functional, information. We evaluated five distinct, partial-machine learning-based mathematical models to predict lung function parameters from qCT values in comparison with pulmonary function tests. Methods: 75 patients with diagnosed COPD underwent body plethysmography and a dose-optimized qCT examination on a third-generation, dual-source CT with inspiration and expiration. Delta values (inspiration—expiration) were calculated afterwards. Four parameters were quantified: mean lung density, lung volume low-attenuated volume, and full width at half maximum. Five models were evaluated for best prediction: average prediction, median prediction, k-nearest neighbours (kNN), gradient boosting, and multilayer perceptron. Results: The lowest mean relative error (MRE) was calculated for the kNN model with 16%. Similar low MREs were found for polynomial regression as well as gradient boosting-based prediction. Other models led to higher MREs and thereby worse predictive performance. Beyond the sole MRE, distinct differences in prediction performance, dependent on the initial dataset (expiration, inspiration, delta), were found. Conclusion: Different, partially machine learning-based models allow the prediction of lung function values from static qCT parameters within a reasonable margin of error. Therefore, qCT parameters may contain more information than we currently utilize and can potentially augment standard functional lung testing.

Journal or Publication Title: Diagnostics
Volume: 9
Number: 1
Divisions: 01 Department of Law and Economics
01 Department of Law and Economics > Betriebswirtschaftliche Fachgebiete
01 Department of Law and Economics > Betriebswirtschaftliche Fachgebiete > Fachgebiet Software Business & Information Management
Date Deposited: 15 May 2019 08:38
DOI: 10.3390/diagnostics9010033
Official URL: https://www.mdpi.com/2075-4418/9/1/33
Export:
Suche nach Titel in: TUfind oder in Google

Optionen (nur für Redakteure)

View Item View Item