Limits...
Application of multilabel learning using the relevant feature for each label in chronic gastritis syndrome diagnosis.

Liu GP, Yan JJ, Wang YQ, Fu JJ, Xu ZX, Guo R, Qian P - Evid Based Complement Alternat Med (2012)

Bottom Line: Methods.Results.Moreover, the studies will provide a reference for constructing syndrome diagnostic models and guide clinical practice.

View Article: PubMed Central - PubMed

Affiliation: Laboratory of Information Access and Synthesis of TCM Four Diagnosis, Basic Medical College, Shanghai University of Traditional Chinese Medicine, Shanghai 201203, China.

ABSTRACT
Background. In Traditional Chinese Medicine (TCM), most of the algorithms are used to solve problems of syndrome diagnosis that only focus on one syndrome, that is, single label learning. However, in clinical practice, patients may simultaneously have more than one syndrome, which has its own symptoms (signs). Methods. We employed a multilabel learning using the relevant feature for each label (REAL) algorithm to construct a syndrome diagnostic model for chronic gastritis (CG) in TCM. REAL combines feature selection methods to select the significant symptoms (signs) of CG. The method was tested on 919 patients using the standard scale. Results. The highest prediction accuracy was achieved when 20 features were selected. The features selected with the information gain were more consistent with the TCM theory. The lowest average accuracy was 54% using multi-label neural networks (BP-MLL), whereas the highest was 82% using REAL for constructing the diagnostic model. For coverage, hamming loss, and ranking loss, the values obtained using the REAL algorithm were the lowest at 0.160, 0.142, and 0.177, respectively. Conclusion. REAL extracts the relevant symptoms (signs) for each syndrome and improves its recognition accuracy. Moreover, the studies will provide a reference for constructing syndrome diagnostic models and guide clinical practice.

No MeSH data available.


Related in: MedlinePlus

REAL algorithm.
© Copyright Policy - open-access
Related In: Results  -  Collection


getmorefigures.php?uid=PMC3376946&req=5

alg1: REAL algorithm.

Mentions: Most traditional multilabel classification approaches to learning methods in vector spaces are used based on the assumption that the instances should have the same set of features in the input space for each label. However, for specific labels, not all the features have strong correlations. ML-kNN is the lazy multilabel learning algorithm based on k-nearest neighbor techniques (kNN) [19]. Similar to the kNN algorithm, it finds the k nearest neighbors for each test instance; however, in ML-kNN, the label of each test instance is estimated directly using the k nearest neighbors in instance. We applied a new algorithm called REAL to fit the characteristics for inquiry diagnosis in TCM based on ML-kNN. The REAL algorithm extracts the best feature subset correlated with a certain label as its input space and then calculates the posterior probability combined with the ML-kNN algorithm. The REAL algorithm is shown in Algorithm 1.


Application of multilabel learning using the relevant feature for each label in chronic gastritis syndrome diagnosis.

Liu GP, Yan JJ, Wang YQ, Fu JJ, Xu ZX, Guo R, Qian P - Evid Based Complement Alternat Med (2012)

REAL algorithm.
© Copyright Policy - open-access
Related In: Results  -  Collection

Show All Figures
getmorefigures.php?uid=PMC3376946&req=5

alg1: REAL algorithm.
Mentions: Most traditional multilabel classification approaches to learning methods in vector spaces are used based on the assumption that the instances should have the same set of features in the input space for each label. However, for specific labels, not all the features have strong correlations. ML-kNN is the lazy multilabel learning algorithm based on k-nearest neighbor techniques (kNN) [19]. Similar to the kNN algorithm, it finds the k nearest neighbors for each test instance; however, in ML-kNN, the label of each test instance is estimated directly using the k nearest neighbors in instance. We applied a new algorithm called REAL to fit the characteristics for inquiry diagnosis in TCM based on ML-kNN. The REAL algorithm extracts the best feature subset correlated with a certain label as its input space and then calculates the posterior probability combined with the ML-kNN algorithm. The REAL algorithm is shown in Algorithm 1.

Bottom Line: Methods.Results.Moreover, the studies will provide a reference for constructing syndrome diagnostic models and guide clinical practice.

View Article: PubMed Central - PubMed

Affiliation: Laboratory of Information Access and Synthesis of TCM Four Diagnosis, Basic Medical College, Shanghai University of Traditional Chinese Medicine, Shanghai 201203, China.

ABSTRACT
Background. In Traditional Chinese Medicine (TCM), most of the algorithms are used to solve problems of syndrome diagnosis that only focus on one syndrome, that is, single label learning. However, in clinical practice, patients may simultaneously have more than one syndrome, which has its own symptoms (signs). Methods. We employed a multilabel learning using the relevant feature for each label (REAL) algorithm to construct a syndrome diagnostic model for chronic gastritis (CG) in TCM. REAL combines feature selection methods to select the significant symptoms (signs) of CG. The method was tested on 919 patients using the standard scale. Results. The highest prediction accuracy was achieved when 20 features were selected. The features selected with the information gain were more consistent with the TCM theory. The lowest average accuracy was 54% using multi-label neural networks (BP-MLL), whereas the highest was 82% using REAL for constructing the diagnostic model. For coverage, hamming loss, and ranking loss, the values obtained using the REAL algorithm were the lowest at 0.160, 0.142, and 0.177, respectively. Conclusion. REAL extracts the relevant symptoms (signs) for each syndrome and improves its recognition accuracy. Moreover, the studies will provide a reference for constructing syndrome diagnostic models and guide clinical practice.

No MeSH data available.


Related in: MedlinePlus