In traditional Chinese medicine (TCM), it is frequently found that more than one syndrome of a patient are recognized in clinical practice, which has its own symptoms and signs. While, most algorithms are used to solve issues of syndrome diagnosis that only focus on one syndrome. Therefore, we proposed a hybrid intelligent syndrome diagnosis (HISD) model. Methods. The HISD model combined feature selection methods to select the significant symptoms and signs corresponding to syndromes of CHB, and combined probability-classification methods to obtain the main syndrome and accompanying syndromes. The model was carried on 664 records of CHB. Results. 16 features were selected for the syndrome of Damp Heat in the Liver and Gallbladder (DHLG), 20 features were selected for the syndrome of Liver qi Stagnation and Spleen Deficiency (LSSD) and 13 features were selected for the syndrome of Yin Deficiency of Liver and Kidney (YDLK). The lowest average accuracy was 80.52% using logitboost, whereas the accuracy of HISD was 85% for unrecognized cases of CHB. Conclusion. Our method extracts the relevant symptoms and signs for each syndrome, recognizes the main syndrome and accompanying syndromes, and improves its recognition accuracy.
[1]Dalian Neusoft Inst Informat, Dept Comp Sci & Technol, Dalian, Peoples R China.
[2]Shanghai Univ TCM, Ctr Tradit Chinese Med Informat Sci & Technol, Shanghai, Peoples R China.
[3]Henan Univ TCM, Zhengzhou, Peoples R China.
[4]Shanghai Univ TCM, Shanghai Jiaotong Univ, Shanghai, Peoples R China.
(8.0+极速模式)