The invention relates to the technical field of medical auxiliary diagnosis, and particularly discloses an auxiliary diagnosis method for multifocal motor neuropathy and peingshan
disease, which comprises the following steps: step S100: performing electromyogram detection, serological examination and
muscle biopsy on an examined object to obtain electromyogram
signal data, serological examination result data and
muscle biopsy result data; s200, performing
feature extraction on the electromyogram
signal data, the serological examination result data and the
muscle biopsy result data, and combining the extracted features to form a
feature vector; step S300, obtaining output classification probabilities, wherein the classification probabilities correspond to the multi-focus motor neuropathy and the Pingshan
disease, and excluding three categories of the multi-focus motor neuropathy and the Pingshan
disease; electromyogram signals, serological examination and muscle biopsy multi-
source data are fused to extract core features, a classification model is constructed by using a
random forest or XGBoost
algorithm, and the
automation and standard unification of the whole diagnosis process are realized.