Prediction of 6-month poststroke spasticity in patients with acute first-ever stroke by machine learning.

OBJECTIVE: Poststroke spasticity (PSS) reduces arm function and leads to low levels of independence. This study suggested applying machine learning (ML) from routinely available data to support the clinical management of PSS. DESIGN: 172 patients with acute first-ever stroke were included in this prospective cohort study. Twenty clinical information and rehabilitation assessments were obtained to train various ML algorithms for predicting 6-month PSS defined by a modified Ashworth scale (MAS) score ≥ 1. Factors significantly relevant were also defined. RESULTS: The study results indicated that multivariate adaptive regression spline (area under the curve (AUC) value: 0.916; 95% confidence interval (CI): 0.906-0.923), adaptive boosting (AUC: 0.962; 95% CI: 0.952-0.973), random forest (RF) (AUC: 0.975; 95% CI: 0.968-0.981), support vector machine (SVM) (AUC: 0.980; 95% CI: 0.970-0.989) outperformed the traditional logistic model (AUC: 0.897; 95% CI: 0.884-0.910) (P < 0.05). Among all of the algorithms, the RF and SVM models outperformed the others (P < 0.05). FMA score, days in hospital, age, stroke location, and paretic side were the most important features. CONCLUSION: These findings suggest that ML algorithms can help augment clinical decision-making processes for the assessment of PSS occurrence, which may enhance the efficacy of management for patients with PSS in the future.

Correlation of N30 somatosensory evoked potentials with spasticity and neurological function after stroke: A cross-sectional study.

OBJECTIVE: To test whether the presence of N30 somatosensory evoked potentials, generated from the supplementary motor area and premotor cortex, correlate with post-stroke spasticity, motor deficits, or motor recovery stage. DESIGN: A cross-sectional study. PATIENTS: A total of 43 patients with stroke hospitalized at Maoming People's Hospital, Maoming, China. METHODS: Forty-three stroke patients underwent neurofunctional tests, including Modified Ashworth Scale (MAS), Brunnstrom stage, manual muscle test and neurophysiological tests, including N30 somatosensory evoked potentials, N20 somatosensory evoked potentials, motor evoked potentials, H-reflex. The results were compared between groups. Correlation and regression analyses were performed as well. RESULTS: Patients with absence of N30 somatosensory evoked potential exhibited stronger flexor carpi radialis muscle spasticity (r = -0.50, p < 0.05) and worse motor function (r = 0.57, p < 0.05) than patients with presence of N30 somatosensory evoked potential. The generalized linear model (GLM) including both N30 somatosensory evoked potentials and motor evoked potentials (Akaike Information Criterion (AIC) = 121.99) better reflected the recovery stage of the affected proximal upper limb than the models including N30 somatosensory evoked potentials (AIC = 125.06) or motor evoked potentials alone (AIC = 127.45). CONCLUSION: N30 somatosensory evoked potential status correlates with the degrees of spasticity and motor function of stroke patients. The results showed that N30 somatosensory evoked potentials hold promise as a biomarker for the development of spasticity and the recovery of proximal limbs.