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

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