Abstract
OBJECTIVE: To explore the feasibility and clinical value of constructing a therapeutic efficacy prediction model for patients with lower limb motor dysfunction after stroke who received conventional treatment combined with functional electrical stimulation (FES) mirror therapy training, based on age, baseline National Institutes of Health Stroke Scale (NIHSS) score, baseline FMA score, FES stimulation intensity, FES stimulation frequency, and mirror therapy training duration. METHODS: A total of 510 patients with lower limb motor dysfunction after stroke admitted to the hospital from January 2022 to October 2024 were selected and divided into a training set (n = 357) and a validation set (n = 153) at a ratio of 7:3. The clinical data of the patients were collected, and the FES stimulation parameters and mirror therapy training data were recorded. The modified Fugl-Meyer Motor Assessment Scale (FMA) was used to evaluate the therapeutic efficacy (effective was defined as an improvement of FMA score ≥ 15 points). Independent risk factors were screened by univariate and multivariate Logistic regression, a Nomogram model was constructed, and its efficacy was evaluated and verified. RESULTS: The effective treatment rate was 65.83% (235/357) in the training set and 64.05% (98/153) in the validation set. Multivariate regression showed that age, baseline NIHSS score, baseline FMA score, FES stimulation intensity, FES stimulation frequency, and mirror therapy training duration were independent influencing factors (All p < 0.05). The C-indices of the Nomogram model in the training set and the validation set were 0.792 and 0.778 respectively, and the AUCs were 0.789 (95% CI: 0.728-0.851) and 0.774 (95% CI: 0.681-0.867) respectively. The sensitivities and specificities were 0.779, 0.700 and 0.714, 0.738, respectively. The calibration curves showed good consistency between the predicted values and the actual values, and the P-values of the Hosmer-Lemeshow test were 0.866 and 0.442, respectively. CONCLUSION: The Nomogram model constructed based on the above indicators can effectively predict the therapeutic efficacy of patients with lower limb motor dysfunction after stroke, providing a basis for clinical individualized intervention.