Joint imbalanced classification and feature selection for hospital readmissions

Evidence-Based Complementary and Alternative Medicine

et al. 2020

Self Cite

Background. Metabolic syndrome (MS) is a complex multisystem disease. Traditional Chinese medicine (TCM) is effective in preventing and treating MS. Syndrome differentiation is the basis of TCM treatment, which is composed of location and/or nature syndrome elements. At present, there are still some problems for objective and comprehensive syndrome differentiation in MS. This study mainly proposes a solution to two problems. Firstly, TCM syndromes are concurrent, that is, multiple TCM syndromes may develop in the same patient. Secondly, there is a lack of holistic exploration of the relationship between microscopic indexes, and TCM syndromes. In regard to these two problems, multilabel learning (MLL) method in machine learning can be used to solve them, and a microcosmic syndrome differentiation model can also be built innovatively, which can provide a foundation for the establishment of the next model of multidimensional syndrome differentiation in MS. Methods. The standardization scale of TCM four diagnostic information for MS was designed, which was used to obtain the results of TCM diagnosis. The model of microcosmic syndrome differentiation was constructed based on 39 physicochemical indexes by MLL techniques, called ML-kNN. Firstly, the multilabel learning method was compared with three commonly used single learning algorithms. Then, the results from ML-kNN were compared between physicochemical indexes and TCM information. Finally, the influence of the parameter k on the diagnostic model was investigated and the best k value was chosen for TCM diagnosis. Results. A total of 698 cases were collected for the modeling of the microcosmic diagnosis of MS. The comprehensive performance of the ML-kNN model worked obviously better than the others, where the average precision of diagnosis was 71.4%. The results from ML-kNN based on physicochemical indexes were similar to the results based on TCM information. On the other hand, the k value had less influence on the prediction results from ML-kNN. Conclusions. In the present study, the microcosmic syndrome differentiation model of MS with MLL techniques was good at predicting syndrome elements and could be used to solve the diagnosis problems of multiple labels. Besides, it was suggested that there was a complex correlation between TCM syndrome elements and physicochemical indexes, which worth future investigation to promote the development of objective differentiation of MS.

Section: Discussionmentioning

confidence: 99%

A Microcosmic Syndrome Differentiation Model for Metabolic Syndrome with Multilabel Learning

Xia

Evidence-Based Complementary and Alternative Medicine

et al. 2020

Self Cite

“…It has the advantages in consideration of the simplicity, feasibility and low error rate [24,25]. Considering that symptoms and signs or microcosmic indicators often do not appear singly, and the syndrome elements are also related to each other, ML-kNN model estimates the posterior probability of multiple labels related to the final diagnosis as a whole [26], so it is more in accord with the core of TCM holistic concept. This study shows that…”

Section: Discussionmentioning

confidence: 99%

A microcosmic syndrome differentiation model for metabolic syndrome with multi-label learning

Xia

et al. 2020

Preprint

Self Cite

Background: Metabolic Syndrome (MS) is a complex multi-system disease. Traditional Chinese medicine (TCM) is satisfactory in preventing and treating MS. Syndrome differentiation is the basis of TCM treatment, which is composed of location and/or nature syndrome elements. Many studies have found TCM syndromes are correlated with biological indicators. However, there are various data that mainly come from point-to-point studies, which can’t fully summarize the many to many relationship of TCM syndromes and biological indicators. Thus, it is also hard to deal with the problem that several types of syndromes may possibly happen to a patient at once in the real world. The purpose of this study is to find out the potential relationship between microcosmic index and syndrome elements from a holistic view by means of multi-label learning (MLL) technique, and to provide a multi-label model for TCM syndrome differentiation. Methods: The standardization scale on TCM four diagnostic information for MS is designed, which is used to obtain the results of TCM diagnosis. The model of microcosmic syndrome differentiation is constructed based on 39 physicochemical indexes, such as BMI, abdominal circumference, blood pressure，platelet，fasting blood sugar, insulin, blood lipid，by MLL techniques, called ML-kNN. First, the multi-label learning method is compared with three commonly used single learning algorithms. Then, the comparison of results of ML-kNN between physicochemical indexes and TCM information is also made. Next. the influence of parameter k of ML-kNN to the diagnostic model is investigated and then the best k-value is chosen for the TCM diagnosis. Results: A total of 698 cases are collected for the modeling of the microcosmic diagnosis of MS. The comprehensive performance of the ML-kNN model works obviously better than the others, whose average precision of diagnosis reach 71.4%. The results of ML-kNN based on microcosmic indexes are close to the results based on TCM information. The k value has less influence on the prediction results of ML- kNN. Conclusions: The MLL techniques facilitate building microcosmic syndrome differentiation model in MS and the experiments show this is a practical approach to solve the problem of labeling multiple syndromes simultaneously. Besides, it is also suggested that there is many to many relationships between TCM syndrome elements and physicochemical indexes, which will be conducive to the future objective and comprehensive study of syndrome differentiation in MS.

“…In real‐world applications, one instance may be associated with multiple class labels simultaneously. For example, a disease is caused by multiple patterns of syndromes, 1 a gene may be relevant to multiple functions, 2 and a piece of music may be related to several genres 3 . Hence, multilabel learning has attracted significant attention from researchers in recent years 4 …”

Section: Introductionmentioning

confidence: 99%

“…Consequently, multilabel feature selection techniques are employed to prevent the curse of dimensionality 17 . In order to improve the performance of multilabel classification, feature selection transforms the original features into a low‐dimensional subspace and then selects the most representative features 18‐21 …”

Section: Introductionmentioning

confidence: 99%

“…17 In order to improve the performance of multilabel classification, feature selection transforms the original features into a low-dimensional subspace and then selects the most representative features. [18][19][20][21] The existing multilabel feature selection algorithms can be broadly organized into three groups : that is, filter, wrapper, and embedded. [22][23][24] Filter methods assess the discrimination capacity of features according to certain valuation criteria, and then the feature ranking is generated.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Joint multilabel classification and feature selection based on deep canonical correlation analysis

Dai

Concurrency and Computation

et al. 2020

Self Cite

In recent years, multilabel learning has been applied to a lot of application areas and is yet a challenging task. In multilabel learning, an instance often belongs to multiple class labels simultaneously. The labels usually have correlations with others, and mining label correlations is helpful to enhance the multilabel classification performance. Aiming at increasing the accuracy of prediction, Label embedding (LE) is an important technique, and conducive to extracting label information for multilabel learning. In this paper, we present a novel multilabel learning approach via exploiting label correlations, which can be naturally extended to tackle feature selection problem. First, to obtain the discriminative features shared by all labels, the proposed algorithm learns a latent space by employing deep canonical correlation analysis. Then we exploit label correlations by enforcing predictions on similar labels to be similar, thereby improving the prediction performance. Results on several multiple datasets illustrate that the proposed algorithm has the advantages on multilabel classification and feature selection.