A prehabilitation-enhanced nomogram for predicting early pulmonary recovery failure after lung tumor surgery:...

To develop and validate a practical prehabilitation-enhanced nomogram for predicting early postoperative pulmonary recovery failure within 7 days after lung tumor surgery.

In this multicenter retrospective study, patients were enrolled from the first center as the development cohort and the second center as the external test cohort. Routine perioperative variables and quantified 14-day prehabilitation process indicators were collected. A routine-variable model and a prehabilitation-enhanced model were compared under the same framework. Independent predictors were identified by multivariable logistic regression and integrated into a nomogram. Model performance was evaluated in terms of discrimination, calibration, and clinical utility.

Adding prehabilitation indicators improved discrimination in the training, internal validation, and external test cohorts, with the area under the curve increasing from 0.946 to 0.972, from 0.825 to 0.863, and from 0.861 to 0.883, respectively. The final nomogram included five predictors: intraoperative blood loss, DLCO% predicted, preoperative resting SpO₂, incentive spirometry target-achieved days (0-14), and breathing training target-achieved days (0-14). The nomogram showed good discrimination with AUCs of 0.921 (95% CI 0.891-0.952), 0.885 (95% CI 0.826-0.943), and 0.845 (95% CI 0.778-0.912) in the training, internal validation, and external test cohorts, respectively, and outperformed any single predictor. Calibration was acceptable across cohorts, with Brier scores of 0.097, 0.122, and 0.143, and decision curve analysis supported clinical usefulness across relevant threshold probabilities.

A prehabilitation-enhanced nomogram enables individualized early risk stratification for early postoperative pulmonary recovery failure within 7 days and may support targeted prevention and nursing resource allocation.