Search JIM Advanced Search

Journal of Integrative Medicine ›› 2021, Vol. 19 ›› Issue (5): 395-407.doi: 10.1016/j.joim.2021.08.001

• Methodology • Previous Articles     Next Articles

Application of an extreme learning machine network with particle swarm optimization in syndrome classification of primary liver cancer

Liang Dinga, Xin-you Zhanga, Di-yao Wub, Meng-ling Liua   

  1. a. School of Computer, Jiangxi University of Traditional Chinese Medicine, Nanchang 330004, Jiangxi Province, China
    b. School of Pharmacy, Jiangxi University of Traditional Chinese Medicine, Nanchang 330004, Jiangxi Province, China
  • Received:2020-07-16 Accepted:2021-03-02 Online:2021-09-15 Published:2021-09-30
  • Contact: Xin-you Zhang


By optimizing the extreme learning machine network with particle swarm optimization, we established a syndrome classification and prediction model for primary liver cancer (PLC), classified and predicted the syndrome diagnosis of medical record data for PLC and compared and analyzed the prediction results with different algorithms and the clinical diagnosis results. This paper provides modern technical support for clinical diagnosis and treatment, and improves the objectivity, accuracy and rigor of the classification of traditional Chinese medicine (TCM) syndromes.


From three top-level TCM hospitals in Nanchang, 10,602 electronic medical records from patients with PLC were collected, dating from January 2009 to May 2020. We removed the electronic medical records of 542 cases of syndromes and adopted the cross-validation method in the remaining 10,060 electronic medical records, which were randomly divided into a training set and a test set. Based on fuzzy mathematics theory, we quantified the syndrome-related factors of TCM symptoms and signs, and information from the TCM four diagnostic methods. Next, using an extreme learning machine network with particle swarm optimization, we constructed a neural network syndrome classification and prediction model that used “TCM symptoms + signs + tongue diagnosis information + pulse diagnosis information” as input, and PLC syndrome as output. This approach was used to mine the nonlinear relationship between clinical data in electronic medical records and different syndrome types. The accuracy rate of classification was used to compare this model to other machine learning classification models.


The classification accuracy rate of the model developed here was 86.26%. The classification accuracy rates of models using support vector machine and Bayesian networks were 82.79% and 85.84%, respectively. The classification accuracy rates of the models for all syndromes in this paper were between 82.15% and 93.82%.


Compared with the case of data processed using traditional binary inputs, the experiment shows that the medical record data processed by fuzzy mathematics was more accurate, and closer to clinical findings. In addition, the model developed here was more refined, more accurate, and quicker than other classification models. This model provides reliable diagnosis for clinical treatment of PLC and a method to study of the rules of syndrome differentiation and treatment in TCM.

Key words: Primary liver cancer, Syndrome type, Particle swarm, Extreme learning machine, Fuzzy mathematics

No related articles found!
Full text



[1] Dong Yang, Yong-ping Du, Qing Shen, Wei Chen, Yan Yu, Guang-lei Chen. Expression of alpha-smooth muscle actin in renal tubulointerstitium in patients with kidney collateral stasis. Journal of Chinese Integrative Medicine, 2008, 6(1): 41-44
[2] Hai-feng Wei, Bai-liu Ya, Ling Zhao, Cui-fei Ye, Li Zhang, Lin Li. Evaluation of tongue manifestation of blood stasis syndrome and its relationship with blood rheological disorder in a rat model of transient brain ischemia. Journal of Chinese Integrative Medicine, 2008, 6(1): 73-76
[3] Xi Lin, Jian-ping Liu. Herbal medicines for viral myocarditis. Journal of Chinese Integrative Medicine, 2008, 6(1): 76
[4] Xi Lin, Jian-ping Liu. Tai chi for treating rheumatoid arthritis. Journal of Chinese Integrative Medicine, 2008, 6(1): 82
[5] Liang-ping Hu, Hui Gao. Discrimination of errors in statistical analysis of medical papers published in the first issue of 2006 in Journal of Chinese Integrative Medicine. Journal of Chinese Integrative Medicine, 2008, 6(1): 98-106
[6] Yan-bo Zhu , Qi Wang, Cheng-yu Wu, Guo-ming Pang, Jian-xiong Zhao, Shi-lin Shen, Zhong-yuan Xia , Xue Yan . Logistic regression analysis on relationships between traditional Chinese medicine constitutional types and overweight or obesity. Journal of Chinese Integrative Medicine, 2010, 8(11): 1023-1035
[7] Wei Xu, Meng Shi, Jian-gang Liu, Cheng-long Wang . Collagen protein expressions in ischemic myocardium of rats with acute myocardial infarction and effects of qi-tonifying, yin-tonifying and blood-activating herbs and detoxifying and blood-activating herbs. Journal of Chinese Integrative Medicine, 2010, 8(11): 1041-1047
[8] Tao Wang , Feng Qin. Effects of Chinese herbal medicine Xiaoyao Powder on monoamine neurotransmitters in hippocampus of rats with postpartum depression. Journal of Chinese Integrative Medicine, 2010, 8(11): 1075-1079
[9] Ying Xu , Chang-chun Zeng , Xiu-yu Cai , Rong-ping Guo , Guang Nie , Ying Jin. Chromaticity and optical spectrum colorimetry of the tongue color in different syndromes of primary hepatic carcinoma. Journal of Chinese Integrative Medicine, 2012, 10(11): 1263-1271
[10] Xiang-ying Mao , Qin Bian , Zi-yin Shen. Analysis of the osteogenetic effects exerted on mesenchymal stem cell strain C3H10T1/2 by icariin via MAPK signaling pathway in vitro. Journal of Chinese Integrative Medicine, 2012, 10(11): 1272-1278