Patient classification of hypertension in Traditional Chinese Medicine using multi-label learning techniquesReport as inadecuate




Patient classification of hypertension in Traditional Chinese Medicine using multi-label learning techniques - Download this document for free, or read online. Document in PDF available to download.

BMC Medical Genomics

, 8:S4

First Online: 23 September 2015

Abstract

BackgroundHypertension is one of the major risk factors for cardiovascular diseases. Research on the patient classification of hypertension has become an important topic because Traditional Chinese Medicine lies primarily in -treatment based on syndromes differentiation of the patients-.

MethodsClinical data of hypertension was collected with 12 syndromes and 129 symptoms including inspection, tongue, inquiry, and palpation symptoms. Syndromes differentiation was modeled as a patient classification problem in the field of data mining, and a new multi-label learning model BrSmoteSvm was built dealing with the class-imbalanced of the dataset.

ResultsThe experiments showed that the BrSmoteSvm had a better results comparing to other multi-label classifiers in the evaluation criteria of Average precision, Coverage, One-error, Ranking loss.

ConclusionsBrSmoteSvm can model the hypertension-s syndromes differentiation better considering the imbalanced problem.

KeywordsTraditional Chinese medicine Multi-label learning Data mining Feature selection Abbreviations usedBRBinary Relevance

SMOTESynthetic Minority Over-sampling Technique

SVMSupport Vector Machine

Guo-Zheng Li, Zehui He contributed equally to this work.

Download fulltext PDF



Author: Guo-Zheng Li - Zehui He - Feng-Feng Shao - Ai-Hua Ou - Xiao-Zhong Lin

Source: https://link.springer.com/







Related documents