Subtype-specific optimal cut-off values of the berg balance scale for predicting independent walking in inpatient stroke rehabilitation: a multicentre cohort study

OBJECTIVE: To determine whether admission Berg Balance Scale score independently predicts independent walking on discharge after adjustment for major confounders, and to derive subtype-specific optimal cut-off values for ischaemic and haemorrhagic stroke. DESIGN: Multicentre retrospective cohort study. SUBJECTS/PATIENTS: A total of 565 stroke patients (316 ischaemic, 249 haemorrhagic) admitted to 3 inpatient rehabilitation centres in the Republic of Korea. METHODS: Multivariable logistic regression was used to evaluate the independent predictive value of the Berg Balance Scale. Optimal cut-off values were derived using receiver operating characteristic curve analysis and the Youden index. Bootstrap internal validation, calibration analysis, and decision curve analysis were performed. RESULTS: Admission Berg Balance Scale was a significant independent predictor of independent walking (adjusted odds ratio 1.053, 95% confidence interval 1.030-1.076). The difference in discriminative ability between the Berg Balance Scale only and multivariable models was not statistically significant (p = 0.097). The overall optimal cut-off was 24 points; subtype-specific cut-offs were 33 for ischaemic and 12 for haemorrhagic stroke. CONCLUSION: The Berg Balance Scale has different optimal cut-off values by stroke subtype and, as a standalone assessment, maintains discriminative ability equivalent to a multivariable model, providing clinical evidence for subtype-specific precision rehabilitation strategies.