Abstract
To evaluate the feasibility of brainstem auditory evoked potential (BAEP) for rehabilitation prognosis prediction in patients with ischemic stroke, 181 patients were tested using the Korean version of the modified Barthel index (K-MBI) at admission (basal K-MBI) and discharge (follow-up K-MBI). The BAEP measurements were performed within two weeks of admission on average. The criterion between favorable and unfavorable outcomes was defined as a K-MBI score of 75 at discharge, which was the boundary between moderate and mild dependence in daily living activities. The changes in the K-MBI scores (discharge-admission) were analyzed by nonlinear regression models, including the artificial neural network (ANN) and support vector machine (SVM), with the basal K-MBI score, age, and interpeak latencies (IPLs) of the BAEP (waves I, I–III, and III–V). When including the BAEP features, the correlations of the ANN and SVM regression models increased to 0.70 and 0.64, respectively. In the outcome prediction, the ANN model with the basal K-MBI score, age, and BAEP IPLs exhibited a sensitivity of 92% and specificity of 90%. Our results suggest that the BAEP IPLs used with the basal K-MBI score and age can play an adjunctive role in the prediction of patient rehabilitation prognoses.
Highlights
In terms of rehabilitation in patients with stroke, the decision making relating to “how to” and “how long” is quite challenging because accurate prognosis of the outcome remains difficult [1]
The present study focused on the feasibility of BAEPand machine-learning-based prognosis in the Korean version of the modified Barthel index (K-MBI) [18,19] of patients with ischemic stroke, which is the most common stroke type [20]
When adding the three brainstem auditory evoked potential (BAEP) interpeak latencies (IPLs) as input features, the sensitivity and specificity in the artificial neural network (ANN) model increased to 92% and 90%, respectively, whereas those in the support vector machine (SVM) model were 88% and 86%, respectively
Summary
In terms of rehabilitation in patients with stroke, the decision making relating to “how to” and “how long” is quite challenging because accurate prognosis of the outcome remains difficult [1]. The clinical need for the prediction of rehabilitation outcomes in patients with stroke is constantly increasing [2]. If it were possible to predict the degree of recovery, a more appropriate treatment strategy and a reasonable rehabilitation goal could be planned according to the patient’s condition [3]. Evoked potentials (EPs) have been widely applied in assessing sensory and motor organs, as well as afferent neural pathways, for clinical diagnosis and for intraoperative neurophysiology monitoring [4]. Steube and colleagues found that patients with loss of motor evoked potentials (MEPs) from the anterior tibial muscle had lower Motricity Index (MI) scores and reduced rehabilitation effects than those with preserved MEP [10]. MEP has been used as a motor excitation threshold for personalized treatment when applying transcranial magnetic stimulation to improve stroke recovery [11]
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have