| dc.description.abstract | This study is a prospective study, aiming at accurate prediction of the rehabilitation outcome after stroke by using the pre-rehab electroencephalogram (EEG) and machine learning technique. 37 stroke patients, who admitted to the Rehabilitation Center at Taipei Veterans General Hospital from January 2012 to December 2013, were recruited for this study. All patients underwent 24-hour rehab program and the rehabilitation outcomes were measured with FM, TEMP and WMFT. For supervised machine learning methods, we first divided the data into two groups : good and general recovery, according to two criteria - (1) Type I : a level of 10% improvement of any above mentioned measures (i.e. ∆FM> =6.6 ; ∆WMFT >=8.5; ∆TEMPA >=13.8 ) after rehab was considered as good recovery as suggested in several studies, resulting in 20 good recovery patients (out of 37); and (2) Type II: the scale after rehab up to 60 % of full scales of any above mentioned measures (i.e. FM >=40 ; WMFT >=45, TEMPA> =-55 ) was labeled as good recovery, resulting in 23 good recovery patients. The EEG data were acquired during the shoulder flexion for eighty trials before the rehabilitation and were pre-processed offline for filtering and epoching. The spectral density from 4-48Hz at contralesional primary motor cortex (CM1), ipsilateral primary motor cortex (IM1), contralesional premotor area (CPM), ipsilateral premotor area (IPM) and the supplementary motor area (SMA) were obtained by projecting the EEG data to the chosen sources using the generalized inverse of the lead-field matrix over peri-stimulus time and then used a time-frequency Morlet wavelet transform (wavelet number: 7). The absolute value of the resulting time-frequency responses were averaged over trials and entered dynamic causal modeling for induced responses (DCM_IR) as the observations that the model is trying to explain. Both the spectral density at all sources and the parameters given by DCM were served as the data features. These features entered Wrapper method to select features, and the selected features went into the four different classifiers：SVM, Logistic Regression, NaiveBayes, J48 for two-class classification.
The classification result suggests that, the best accuracy rate was 92.95 % when using DCM features of β+γ frequencies of Type I data partition and Logistic Regression. Furthermore, the classification accuracy rate was up to 83.19 % when using only β frequency DCM features, indicating that beta rhythm within the motor network have a significant impact for recovery. We believe that our finding can help to facilitate the result of rehab by developing a knowledge-based rehab program. | en_US |