Abstract: An electronic apparatus for establishing prediction model based on electroencephalogram (EEG). The electronic apparatus is configured for: acquiring an EEG signal segment related to an epilepsy patient; dividing each EEG signal into EEG components according to a predetermined window size; retrieving datasets corresponding to EEG features from the EEG components of each EEG signal segment; acquiring statistical feature values of each dataset of each EEG signal segment; determining a gain ratio of each of the statistical feature values of each EEG signal segment based on the statistical feature values corresponding to each of the EEG features; selecting specific statistical feature values from the statistical feature values according to the gain ratio of each of the statistical feature values of each EEG signal segment; establishing a prediction model based on the specific statistical feature values of the epilepsy patient.

Abstract: An electroencephalogram signal processing method includes a recording step, a retrieving step, a removing step and a synthesizing step. The recording step retrieves EEG signal components of a testee via a plurality of electrodes, wherein the EEG signal components serve as an input signal. The retrieving step filters the input signal to obtain a predetermined frequency band signal, and subtracts the predetermined frequency band signal from the input signal to obtain a difference signal. The removing step performs an independent component analysis operation between the difference signal and a separating matrix to obtain an analysis signal, generates a separating pseudo inverse and an independent analysis signal, and performs a matrix operation between the separating pseudo inverse and the independent analysis signal to obtain a corrected signal. The synthesizing step adds the corrected signal and the predetermined frequency band signal together to obtain an output signal.

Abstract: An electroencephalogram signal processing method includes a recording step, a retrieving step, a removing step and a synthesizing step. The recording step retrieves EEG signal components of a testee via a plurality of electrodes, wherein the EEG signal components serve as an input signal. The retrieving step filters the input signal to obtain a predetermined frequency band signal, and subtracts the predetermined frequency band signal from the input signal to obtain a difference signal. The removing step performs an independent component analysis operation between the difference signal and a separating matrix to obtain an analysis signal, generates a separating pseudo inverse and an independent analysis signal, and performs a matrix operation between the separating pseudo inverse and the independent analysis signal to obtain a corrected signal. The synthesizing step adds the corrected signal and the predetermined frequency band signal together to obtain an output signal.

Abstract: The invention provides a method for diagnosing Kawaski Disease (KD) in a patient suspected of suffering from KD by using as an index a ratio of the level (by weight/volume, w/v) of haptoglobin (Hp) to the level (by weight/volume, w/v) of apolipoprotein A1 (Apo A1) in a patient. A system for use with the method is also included. In addition, the invention also provides a method for diagnosing Atypical Kawasaki Disease (AKD) in a patient suspected of suffering from KD by identifying the phenotype of haptoglobin in said patient and correlating the presence of Hp2-1 or Hp1-1 haptoglobin phenotype with AKD and providing immediate treatment of the patient.