Objective To analyze clinical data of hospitalized patients with extensive burns， identify independent risk

factors， establish a risk prediction model， and validate its performance. Methods A retrospective analysis was conducted on the clinical data of 450 patients with extensive burns admitted to the burn departments of two tertiary hospitals from January 2015 to December 2024， according to inclusion criteria. Patients were divided into surgical and non-surgical groups based on whether they received reconstructive surgery. Relevant clinical characteristics were compared between the two groups using one way ANOVA，χ² tests， LASSO regression analysis， multivariate logistic regression analysis， and nomogram construction. The model’s performance was evaluated using receiver operating characteristic （ROC） curve analysis. Results There were statistically significant differences （P<0.05） between the surgical group and the non-surgical group in terms of burn index， duration of mechanical ventilation， use of floating bed therapy， time to initiate rehabilitation exercises （post injury）， type of rehabilitation during the stabilization phase， type of rehabilitation during the recovery phase， and VSS score. LASSO regression identified six independent risk factors： burn index， use of floating bed therapy， time to initiate rehabilitation exercises （post-injury）， type of rehabilitation during stabilization phase， type of rehabilitation during recovery phase， and VSS score. Multivariate logistic regression confirmed that burn index， use of floating bed therapy， time to initiate rehabilitation exercises （post-injury）， type of rehabilitation during stabilization phase， type of rehabilitation during recovery phase， and VSS score were independent predictors of treatment efficacy in rehabilitation. A nomogram prediction model was constructed based on these six independent factors. The area under the ROC curve （AUC） for this model was 0.90（95% confidence interval：0.81-0.89）， with a sensitivity of 0.87 and specificity of 0.81. Conclusion The independent risk factors for rehabilitation treatment outcomes in patients with extensive burns are burn index， use of floating bed therapy， time to initiate rehabilitation exercises （post-injury）， type of rehabilitation during stabilization phase， type of rehabilitation during recovery phase， and VSS score. The nomogram prediction model developed based on these factors demonstrates strong predictive value for assessing rehabilitation outcomes in patients with extensive burns

Burns, Rehabilitation therapy, Efficacy, Risk factors, Nomogram, Prediction model