Development and validation of a nomogram for predicting ADL outcomes in patients undergoing subacute stroke...

The subacute phase is a key period for stroke recovery, yet there is a lack of simple and effective indicators to predict rehabilitation outcomes. This study aims to develop and validate a predictive model for assessing patients' activities of daily living (ADL) recovery at 3 months, providing valuable insights to guide clinical rehabilitation decisions.

This retrospective cohort study included patients admitted to rehabilitation within 7 to 30 days after their first stroke. Data were obtained from the electronic medical record system. Patients were divided into a training cohort (270 patients, 2021-2022) and a validation cohort (165 patients, 2023-2024). ADL independence was defined by a Barthel Index (BI) score of ≥60. The primary outcome was the ADL status at 3 months after the initiation of rehabilitation. Feature selection was performed using univariate analysis and Elastic Net regression, followed by logistic regression modeling. The optimal model was selected based on its AUC in the validation cohort, ensuring a balance between sensitivity and specificity. The final model was presented as a nomogram.

The 3-month prediction model (ADL-3 M) includes the Braden score, baseline BI score, and age. SHAP analysis revealed that the Braden score was the most significant predictor for the 3-month outcome. The AUC for ADL-3 M was 0.832 (95% CI: 0.779-0.885) in the training cohort and 0.866 (95% CI: 0.806-0.926) in the validation cohort.

The simplified model constructed using routine bedside indicators (age, baseline BI score, and Braden score) effectively predicts the ADL recovery of subacute stroke patients at 3 months post-rehabilitation. This nomogram tool is intuitive and easy to use, providing clinical support for individualized rehabilitation plan development, patient prognosis communication, and resource allocation.