Since critical respiratory muscle workload is a significant determinant of weaning failure, applied mechanical power (MP) during artificial ventilation may serve for readiness testing before proceeding on a spontaneous breathing trial (SBT). Secondary analysis of a prospective, observational study in 130 prolonged ventilated, tracheotomized patients. Calculated MP’s predictive SBT outcome performance was determined using the area under receiver operating characteristic curve (AUROC), measures derived from k-fold cross-validation (likelihood ratios, Matthew's correlation coefficient [MCC]), and a multivariable binary logistic regression model. Thirty (23.1%) patients failed the SBT, with absolute MP presenting poor discriminatory ability (MCC 0.26; AUROC 0.68, 95%CI [0.59‒0.75], p = 0.002), considerably improved when normalized to lung-thorax compliance (LTCdyn-MP, MCC 0.37; AUROC 0.76, 95%CI [0.68‒0.83], p < 0.001) and mechanical ventilation PaCO2 (so-called power index of the respiratory system [PIrs]: MCC 0.42; AUROC 0.81 [0.73‒0.87], p < 0.001). In the logistic regression analysis, PIrs (OR 1.48 per 1000 cmH2O2/min, 95%CI [1.24‒1.76], p < 0.001) and its components LTCdyn-MP (1.25 per 1000 cmH2O2/min, [1.06‒1.46], p < 0.001) and mechanical ventilation PaCO2 (1.17 [1.06‒1.28], p < 0.001) were independently related to SBT failure. MP normalized to respiratory system compliance may help identify prolonged mechanically ventilated patients ready for spontaneous breathing.