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

Background: Maximum exercise workload (W(MAX)) is today assessed as the first part of Cardiopulmonary Exercise testing. The W(MAX) test exposes patients with COPD, often having cardiovascular comorbidity, to risks. Our research project was initiated with the final aim to eliminate the W(MAX) test and replace this test with a predicted value of W(MAX), based on a prediction algorithm of W(MAX) derived from multicentre studies. Methods: Baseline data (W(MAX), 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(MAX) were used in a new W(MAX) test, which used a linear increase in order to reach the predicted W(MAX) within 8 min. The new W(MAX) test was compared with the standard stepwise W(MAX) test in a pilot study including 15 patients with mild/moderate COPD. Results: The best prediction algorithm of W(MAX) included age, sex, height, weight, and six lung function parameters. FEV(1) and DLCO were the most important predictors. The new W(MAX) test had a better correlation (R(2) = 0.84) between predicted and measured W(MAX) than the standard W(MAX) test (R(2) = 0.66), with slopes of 0.50 and 0.46, respectively. The results from the new W(MAX) test and the standard W(MAX) test correlated well. Conclusion: A prediction algorithm based on data from four large multicentre studies was used in a new W(MAX) test. The prediction algorithm provided reliable values of predicted W(MAX). In comparison with the standard W(MAX) test, the new W(MAX) test provided similar overall results.