Prescription Function Prediction Using Topic Model and Multilabel Classifiers

Prescription Function Prediction Using Topic Model and Multilabel Classifiers

Determining a prescription’s function is one of the challenging problems in Traditional Chinese Medicine (TCM). In past decades, TCM has been widely researched through various methods in computer science, but none concentrates on the prediction method for a new prescription’s function. In this study...

Full description

Bibliographic Details
Main Authors: Lidong Wang, Yin Zhang, Yun Zhang, Xiaodong Xu, Shihua Cao
Format: Article
Language:English
Published: Hindawi Limited 2017-01-01
Series:Evidence-Based Complementary and Alternative Medicine
Online Access:http://dx.doi.org/10.1155/2017/8279109
id doaj-365866a7529f4188a06737a5eca3b8d6
record_format Article
spelling doaj-365866a7529f4188a06737a5eca3b8d62020-11-24T22:40:52ZengHindawi LimitedEvidence-Based Complementary and Alternative Medicine1741-427X1741-42882017-01-01201710.1155/2017/82791098279109Prescription Function Prediction Using Topic Model and Multilabel ClassifiersLidong Wang0Yin Zhang1Yun Zhang2Xiaodong Xu3Shihua Cao4Qianjiang College, Hangzhou Normal University, Hangzhou 310018, ChinaCollege of Computer Science and Technology, Zhejiang University, Hangzhou, Zhejiang 310027, ChinaZhejiang University of Media and Communications, Hangzhou, Zhejiang 310018, ChinaZhejiang Chinese Medical University, Hangzhou, Zhejiang 310053, ChinaQianjiang College, Hangzhou Normal University, Hangzhou 310018, ChinaDetermining a prescription’s function is one of the challenging problems in Traditional Chinese Medicine (TCM). In past decades, TCM has been widely researched through various methods in computer science, but none concentrates on the prediction method for a new prescription’s function. In this study, two methods are presented concerning this issue. The first method is based on a novel supervised topic model named Label-Prescription-Herb (LPH), which incorporates herb-herb compatibility rules into learning process. The second method is based on multilabel classifiers built by TFIDF features and herbal attribute features. Experiments undertaken reveal that both methods perform well, but the multilabel classifiers slightly outperform LPH-based method. The prediction results can provide valuable information for new prescription discovery before clinical test.http://dx.doi.org/10.1155/2017/8279109
collection DOAJ
language English
format Article
sources DOAJ
author Lidong Wang
Yin Zhang
Yun Zhang
Xiaodong Xu
Shihua Cao
spellingShingle Lidong Wang
Yin Zhang
Yun Zhang
Xiaodong Xu
Shihua Cao
Prescription Function Prediction Using Topic Model and Multilabel Classifiers
Evidence-Based Complementary and Alternative Medicine
author_facet Lidong Wang
Yin Zhang
Yun Zhang
Xiaodong Xu
Shihua Cao
author_sort Lidong Wang
title Prescription Function Prediction Using Topic Model and Multilabel Classifiers
title_short Prescription Function Prediction Using Topic Model and Multilabel Classifiers
title_full Prescription Function Prediction Using Topic Model and Multilabel Classifiers
title_fullStr Prescription Function Prediction Using Topic Model and Multilabel Classifiers
title_full_unstemmed Prescription Function Prediction Using Topic Model and Multilabel Classifiers
title_sort prescription function prediction using topic model and multilabel classifiers
publisher Hindawi Limited
series Evidence-Based Complementary and Alternative Medicine
issn 1741-427X
1741-4288
publishDate 2017-01-01
description Determining a prescription’s function is one of the challenging problems in Traditional Chinese Medicine (TCM). In past decades, TCM has been widely researched through various methods in computer science, but none concentrates on the prediction method for a new prescription’s function. In this study, two methods are presented concerning this issue. The first method is based on a novel supervised topic model named Label-Prescription-Herb (LPH), which incorporates herb-herb compatibility rules into learning process. The second method is based on multilabel classifiers built by TFIDF features and herbal attribute features. Experiments undertaken reveal that both methods perform well, but the multilabel classifiers slightly outperform LPH-based method. The prediction results can provide valuable information for new prescription discovery before clinical test.
url http://dx.doi.org/10.1155/2017/8279109
work_keys_str_mv AT lidongwang prescriptionfunctionpredictionusingtopicmodelandmultilabelclassifiers
AT yinzhang prescriptionfunctionpredictionusingtopicmodelandmultilabelclassifiers
AT yunzhang prescriptionfunctionpredictionusingtopicmodelandmultilabelclassifiers
AT xiaodongxu prescriptionfunctionpredictionusingtopicmodelandmultilabelclassifiers
AT shihuacao prescriptionfunctionpredictionusingtopicmodelandmultilabelclassifiers
_version_ 1725703060703936512

Similar Items