Study design <p>A retrospective cohort study.</p> Objectives <p>To develop a machine learning (ML) model to predict ambulation prognosis one year post-injury in rehabilitation-phase spinal cord injury (SCI) individuals classified as American Spinal Injury Association Impairment Scale (AIS) grades B and C, and to implement it as a web application.</p> Setting <p>A multicenter database in the United States.</p> Methods <p>Data were collected from the National Spinal Cord Injury Database (NSCID) for the years 2011 to 2021. Traumatic SCI cases with complete neurological data at rehabilitation admission were included, based on the International Standards for Neurological Classification of Spinal Cord Injury (ISNCSCI). Model predictors included age at injury, acute length of stay, neurological level of injury, motor scores, and sensory scores. ML models were developed using nested 5-fold cross-validation and four algorithms: logistic regression, random forest, support vector machine, and extreme gradient boosting (XGB). Performance was assessed and compared using area under the curve (AUC), Brier score, and calibration slope, with a focus on AIS grades B and C. A web application was developed using the R package shiny and deployed via shinyapps.io.</p> Results <p>2034 cases were included in the analysis. XGB demonstrated the best performance in terms of AUC (0.855), Brier score (0.153), and calibration slope (0.900) and was selected as the final model. This model was implemented as a web application.</p> Conclusions <p>The developed model showed good performance for AIS grades B and C and was made practical via web application implementation.</p>