Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

A new maximal bicycle test using a prediction algorithm developed from four large COPD studies

Eriksson, Göran LU ; Radner, Finn LU orcid ; Peterson, Stefan LU ; Papapostolou, Georgia LU orcid ; Jarenbäck, Linnea LU ; Jönsson, Saga ; Ankerst, Jaro LU orcid ; Tunsäter, Alf LU ; Tufvesson, Ellen LU and Bjermer, Leif LU (2020) In European clinical respiratory journal 7(1).
Abstract

Background: Maximum exercise workload (WMAX) is today assessed as the first part of Cardiopulmonary Exercise testing. The WMAX test exposes patients with COPD, often having cardiovascular comorbidity, to risks. Our research project was initiated with the final aim to eliminate the WMAX test and replace this test with a predicted value of WMAX, based on a prediction algorithm of WMAX derived from multicentre studies. Methods: Baseline data (WMAX, demography, lung function parameters) from 850 COPD patients from four multicentre studies were collected and standardized. A prediction algorithm was prepared using Random Forest modelling. Predicted values of WMAX... (More)

Background: Maximum exercise workload (WMAX) is today assessed as the first part of Cardiopulmonary Exercise testing. The WMAX test exposes patients with COPD, often having cardiovascular comorbidity, to risks. Our research project was initiated with the final aim to eliminate the WMAX test and replace this test with a predicted value of WMAX, based on a prediction algorithm of WMAX derived from multicentre studies. Methods: Baseline data (WMAX, demography, lung function parameters) from 850 COPD patients from four multicentre studies were collected and standardized. A prediction algorithm was prepared using Random Forest modelling. Predicted values of WMAX were used in a new WMAX test, which used a linear increase in order to reach the predicted WMAX within 8 min. The new WMAX test was compared with the standard stepwise WMAX test in a pilot study including 15 patients with mild/moderate COPD. Results: The best prediction algorithm of WMAX included age, sex, height, weight, and six lung function parameters. FEV1 and DLCO were the most important predictors. The new WMAX test had a better correlation (R2 = 0.84) between predicted and measured WMAX than the standard WMAX test (R2 = 0.66), with slopes of 0.50 and 0.46, respectively. The results from the new WMAX test and the standard WMAX test correlated well. Conclusion: A prediction algorithm based on data from four large multicentre studies was used in a new WMAX test. The prediction algorithm provided reliable values of predicted WMAX. In comparison with the standard WMAX test, the new WMAX test provided similar overall results.

(Less)
Please use this url to cite or link to this publication:
author
; ; ; ; ; ; ; ; and
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
cardiopulmonary exercise testing, COPD, prediction, Random Forest, W
in
European clinical respiratory journal
volume
7
issue
1
article number
1692645
publisher
Taylor & Francis
external identifiers
  • pmid:31839909
  • scopus:85082729809
ISSN
2001-8525
DOI
10.1080/20018525.2019.1692645
language
English
LU publication?
yes
id
5c5acf4c-f92d-4342-9381-298d1d4df12b
date added to LUP
2020-04-24 16:35:15
date last changed
2022-04-18 21:56:18
@article{5c5acf4c-f92d-4342-9381-298d1d4df12b,
  abstract     = {{<p>Background: Maximum exercise workload (W<sub>MAX</sub>) is today assessed as the first part of Cardiopulmonary Exercise testing. The W<sub>MAX</sub> test exposes patients with COPD, often having cardiovascular comorbidity, to risks. Our research project was initiated with the final aim to eliminate the W<sub>MAX</sub> test and replace this test with a predicted value of W<sub>MAX</sub>, based on a prediction algorithm of W<sub>MAX</sub> derived from multicentre studies. Methods: Baseline data (W<sub>MAX</sub>, demography, lung function parameters) from 850 COPD patients from four multicentre studies were collected and standardized. A prediction algorithm was prepared using Random Forest modelling. Predicted values of W<sub>MAX</sub> were used in a new W<sub>MAX</sub> test, which used a linear increase in order to reach the predicted W<sub>MAX</sub> within 8 min. The new W<sub>MAX</sub> test was compared with the standard stepwise W<sub>MAX</sub> test in a pilot study including 15 patients with mild/moderate COPD. Results: The best prediction algorithm of W<sub>MAX</sub> included age, sex, height, weight, and six lung function parameters. FEV<sub>1</sub> and DLCO were the most important predictors. The new W<sub>MAX</sub> test had a better correlation (R<sup>2</sup> = 0.84) between predicted and measured W<sub>MAX</sub> than the standard W<sub>MAX</sub> test (R<sup>2</sup> = 0.66), with slopes of 0.50 and 0.46, respectively. The results from the new W<sub>MAX</sub> test and the standard W<sub>MAX</sub> test correlated well. Conclusion: A prediction algorithm based on data from four large multicentre studies was used in a new W<sub>MAX</sub> test. The prediction algorithm provided reliable values of predicted W<sub>MAX</sub>. In comparison with the standard W<sub>MAX</sub> test, the new W<sub>MAX</sub> test provided similar overall results.</p>}},
  author       = {{Eriksson, Göran and Radner, Finn and Peterson, Stefan and Papapostolou, Georgia and Jarenbäck, Linnea and Jönsson, Saga and Ankerst, Jaro and Tunsäter, Alf and Tufvesson, Ellen and Bjermer, Leif}},
  issn         = {{2001-8525}},
  keywords     = {{cardiopulmonary exercise testing; COPD; prediction; Random Forest; W}},
  language     = {{eng}},
  number       = {{1}},
  publisher    = {{Taylor & Francis}},
  series       = {{European clinical respiratory journal}},
  title        = {{A new maximal bicycle test using a prediction algorithm developed from four large COPD studies}},
  url          = {{http://dx.doi.org/10.1080/20018525.2019.1692645}},
  doi          = {{10.1080/20018525.2019.1692645}},
  volume       = {{7}},
  year         = {{2020}},
}