Format

Send to

Choose Destination
Diagnostics (Basel). 2019 Mar 21;9(1). pii: E33. doi: 10.3390/diagnostics9010033.

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

Author information

1
Institute of Clinical Radiology and Nuclear Medicine, University Medical Center Mannheim, Medical Faculty Mannheim, Heidelberg University, Theodor-Kutzer-Ufer 1-3, 68167 Mannheim, Germany. Joshua.gawlitza@medma.uni-heidelberg.de.
2
Department of General Management and Information Systems, University of Mannheim, 68131 Mannheim, Germany. timo.sturm@googlemail.com.
3
Department of General Management and Information Systems, University of Mannheim, 68131 Mannheim, Germany. spohrer@uni-mannheim.de.
4
Institute of Clinical Radiology and Nuclear Medicine, University Medical Center Mannheim, Medical Faculty Mannheim, Heidelberg University, Theodor-Kutzer-Ufer 1-3, 68167 Mannheim, Germany. t.henzler@diagnostik-muenchen.de.
5
1st Department of Medicine (Cardiology, Angiology, Pulmonary and Intensive Care), University Medical Center Mannheim, Medical Faculty Mannheim, Heidelberg University, Theodor-Kutzer-Ufer 1-3, 68167 Mannheim, Germany. ibrahim.akin@umm.de.
6
DZHK (German Center for Cardiovascular Research), partner site, 68167 Mannheim, Germany. ibrahim.akin@umm.de.
7
Institute of Clinical Radiology and Nuclear Medicine, University Medical Center Mannheim, Medical Faculty Mannheim, Heidelberg University, Theodor-Kutzer-Ufer 1-3, 68167 Mannheim, Germany. stefan.schoenberg@umm.de.
8
1st Department of Medicine (Cardiology, Angiology, Pulmonary and Intensive Care), University Medical Center Mannheim, Medical Faculty Mannheim, Heidelberg University, Theodor-Kutzer-Ufer 1-3, 68167 Mannheim, Germany. martin.borggrefe@umm.de.
9
DZHK (German Center for Cardiovascular Research), partner site, 68167 Mannheim, Germany. martin.borggrefe@umm.de.
10
Institute of Clinical Radiology and Nuclear Medicine, University Medical Center Mannheim, Medical Faculty Mannheim, Heidelberg University, Theodor-Kutzer-Ufer 1-3, 68167 Mannheim, Germany. holger.haubenreisser@umm.de.
11
1st Department of Medicine (Cardiology, Angiology, Pulmonary and Intensive Care), University Medical Center Mannheim, Medical Faculty Mannheim, Heidelberg University, Theodor-Kutzer-Ufer 1-3, 68167 Mannheim, Germany. frederik.trinkmann@umm.de.
12
Department of Biomedical Informatics of the Heinrich-Lanz-Center, University Medical Center Mannheim, Medical Faculty Mannheim, Heidelberg University, Theodor-Kutzer-Ufer 1-3, 68167 Mannheim, Germany. frederik.trinkmann@umm.de.

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.

KEYWORDS:

chronic obstructive pulmonary disease; machine learning; thorax

Supplemental Content

Full text links

Icon for Multidisciplinary Digital Publishing Institute (MDPI) Icon for PubMed Central
Loading ...
Support Center