Classifying syndromes in Chinese medicine using multi-label learning algorithm with relevant features for each label

Jin Xu; Zhao-xia Xu; Ping Lu; Rui Guo; Hai-xia Yan; Wen-jie Xu; Yi-qin Wang; Chun-ming Xia

doi:10.1007/s11655-016-2264-0

Your Location：

Home >

Browse articles >

Classifying syndromes in Chinese medicine using multi-label learning algorithm with relevant features for each label

Updated：2021-08-27

- Classifying syndromes in Chinese medicine using multi-label learning algorithm with relevant features for each label
- Chinese Journal of Integrative Medicine Vol. 22, Issue 11, Pages: 867-871(2016)
- Affiliations：
  
  1. School of Basic Medicine, Shanghai University of Traditional Chinese Medicine,Shanghai,China
  2. Center for Mechatronics Engineering, East China University of Science and Technology,Shanghai,China
- Author bio：
- Funds：
  
  Supported by the National Natural Science Foundation of China (No. 81173199), Shanghai Sailing Program (No.15YF1412100), Young Teachers’ Training Funded Project in Shanghai University (No. ZZszy13003) and Budget for Research Shanghai Municipal Education Commission (No. 2013JW06), Chin
- DOI：10.1007/s11655-016-2264-0
  CLC：
- Published：2016，
  
  Published Online：26 October 2016，
Scan for full text
Xu, J., Xu, Zx., Lu, P. et al. Classifying syndromes in Chinese medicine using multi-label learning algorithm with relevant features for each label., Chin. J. Integr. Med. 22, 867–871 (2016). https://doi.org/10.1007/s11655-016-2264-0

Jin Xu, Zhao-xia Xu, Ping Lu, et al. Classifying syndromes in Chinese medicine using multi-label learning algorithm with relevant features for each label. [J]. Chinese Journal of Integrative Medicine 22(11):867-871(2016)
Xu, J., Xu, Zx., Lu, P. et al. Classifying syndromes in Chinese medicine using multi-label learning algorithm with relevant features for each label., Chin. J. Integr. Med. 22, 867–871 (2016). https://doi.org/10.1007/s11655-016-2264-0 DOI：

Jin Xu, Zhao-xia Xu, Ping Lu, et al. Classifying syndromes in Chinese medicine using multi-label learning algorithm with relevant features for each label. [J]. Chinese Journal of Integrative Medicine 22(11):867-871(2016) DOI： 10.1007/s11655-016-2264-0.

摘要

To develop an effective Chinese Medicine (CM) diagnostic model of coronary heart disease (CHD) and to confifirm the scientifific validity of CM theoretical basis from an algorithmic viewpoint. Four types of objective diagnostic data were collected from 835 CHD patients by using a self-developed CM inquiry scale for the diagnosis of heart problems

a tongue diagnosis instrument

a ZBOX-I pulse digital collection instrument

and the sound of an attending acquisition system. These diagnostic data was analyzed and a CM diagnostic model was established using a multi-label learning algorithm (REAL). REAL was employed to establish a Xin (Heart) qi defificiency

Xin yang defificiency

Xin yin defificiency

blood stasis

and phlegm fifive-card CM diagnostic model

which had recognition rates of 80.32%

89.77%

84.93%

85.37%

and 69.90%

respectively. The multi-label learning method established using four diagnostic models based on mutual information feature selection yielded good recognition results. The characteristic model parameters were selected by maximizing the mutual information for each card type. The four diagnostic methods used to obtain information in CM

i.e.

observation

auscultation and olfaction

inquiry

and pulse diagnosis

can be characterized by these parameters

which is consistent with CM theory.

Abstract

a tongue diagnosis instrument

a ZBOX-I pulse digital collection instrument

Xin yang defificiency

Xin yin defificiency

blood stasis

and phlegm fifive-card CM diagnostic model

which had recognition rates of 80.32%

89.77%

84.93%

85.37%

and 69.90%

i.e.

observation

auscultation and olfaction

inquiry

and pulse diagnosis

can be characterized by these parameters

which is consistent with CM theory.

关键词

Chinese MedicineSyndrome Differentiationmulti-label learning algorithm

Keywords

Chinese MedicineSyndrome Differentiationmulti-label learning algorithm

references

Maglogiannis I, Loukis E, Zafiropoulos E, Stasis A. Support vectors machine-based identification of heart valve diseases using heart sounds. Comput Methods Programs Biomed 2009;95:47–61.

Mou X, Zhou DY, Liu WH. Study on the relationship between Chinese medicine constitutive susceptibility and diversity of syndrome in diabetic nephropathy. Chin J Integr Med 2013;19:656–662.

Yang XB, Liang ZH, Zhang G. A classification algorithm for TCM syndromes based on P-SVM. Proceedings of the Fourth International Conference Machine Learning Cybernetics, Bonn, Germany; 2005:3692–3697.

Zhang T, Zhu Wk, Xu ZL, Zhang LT. Support vector machine and Iits application in Zang-Fu organ differentiation. CD Technol 2007;4:42.

Report of the Joint International Society and Federation of Cardiology/World Health Organization task force on standardization of clinical nomenclature. Nomenclature and criteria for diagnosis of ischemic heart disease. Circulation 1979;59:607–609.

China Society of Integrated Traditional Chinese and Western Medicine. Criteria from standards for differentiation diagnosis of chest pain, chest disease, palptation, short breath or debilitation for coronary heart disease in Chinese medicine. In Annual Conference of Chinese Integrative Medicine Professional Committee of Cardiovascular Research, Qingdao, China;1990:216–223.

Zheng XY, ed. Guiding principle of clinical research on new drugs of traditional Chinese medicine. Beijing: China Medical Science Press; 1993:9194.

Wang YQ, ed. Textbook of traditional Chinese medicine diagnostics (seven-year-version). Beijing: Higher Education Press; 2006:400–446.

Jose M, Filiberto P. Supervised feature selection by clustering using conditional mutual information-based distances. Pattern Recognition 2010;43:2068–2081.

Yang H, Moody J. Data visualization and feature selection: new algorithms for non-gaussian data. Adv Neural Inform Process Syst 1999:12.

Vidal-Naquet M, Ullman S. Object recognition with informative features and linear classification. IEEE Conference on Computer Vision and Pattern Recognition, Madison, USA; 2003:39–45.

Fleuret F. Fast binary feature selection with conditional mutual information. J Machine Learning Res 2004;5:1531–1555.

Peng H, Long F, Ding C. Feature selection based on mutual Information: criteria of max-dependency, max-relevance, and min-redundancy. IEEE Trans Pattern Anal Mach Intell 2005;27:1226–1238.

Lin D, Tang X. Conditional infomax learning: an integrated framework for feature extraction and fusion. In European Conference on Computer Vision, Graz, Austria; 2006:748–763.

FULL TEXT LINK

More>

Views

Downloads

CSCD

Alert me when the article has been cited

Submit

Tools

Publicity Resources

Chinese medicine syndrome distribution of chronic hepatitis b virus carriers in immunotolerant phase

Potential of renal pathology on refining syndrome typing of Chinese medicine in IgA nephropathy

Effect of treatment based on syndrome differentiation by Chinese medicine on post-traumatic elbow arthritis

Approaches of toxicity-reducing and efficacy-enhancing in tumor patients treated with radio- and chemotherapy

Acupuncture for chronic non-specific low back pain: A case series study

Related Author

No data

Related Institution

Traditional Chinese Medicine & Acupuncture Department, The Third Affiliated Hospital of Sun Yet-sen University

Department of Diagnosis of Chinese Medicine, School of Basic Medical Sciences, Beijing University of Chinese Medicine

Institute of Nephrology and Key Laboratory, General Hospital of People’s Liberation Army

Department of Orthopaedics, Jiaxing Traditional Chinese Medicine Hospital Affiliated to Zhejiang University of Traditional Chinese Medicine

Department of Arthropathy, Wangjing Hospital, China Academy of Chinese Medical Sciences

Address：1 Caochang, xiyuan, Beijing, People's Republic of China Postal code：100091
Tel：010-62886827, 62877592 Fax：010-62874291
Technical support is provided by Beijing Founder electronics co., LTD 京ICP备05067934号-1 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰