Abstract:

Objective   To identify the feasibility of principal component analysislinear discriminant analysis (PCA-LDA) to discriminate properties of Traditional Chinese Medicines (TCM) based on their efficacy and indication characters. Methods   Information on efficacies, indications, and properties of 1725 kinds of TCM was collected from “Chinese Herbal Medicine”. PCA-LDA was applied to construct a model and to discriminate properties of TCM based on efficacies and indications of 1725 kinds of TCM. 10 times 5-fold cross-validation was used to evaluate the stability of this model. The overall data was randomly divided into two subsets: 80% of the data (1380 samples) from TCM of cold nature and hot nature as the training set to construct the model, and the remaining 20%(345 samples) as the testing set to evaluate the prediction accuracy. Results   According to the PCA-LDA model, the consistent accuracy was 94.43% for 1725 kinds of TCM, the mean accuracy of 10 times 5-fold cross-validation was 91.54%. The consistent accuracy in the training set was 94.78% and the predication accuracy in the testing set was 90.14%. Conclusion   PCA-LDA discriminating properties of TCM could make sure linear discrimination and guide clinical prescription with high discriminant accuracy and stability.