Zhaoxia Xu

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

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.

Statistical validation of Traditional Chinese Medicine syndrome postulates in the context of patients with cardiovascular disease.

OBJECTIVE Traditional Chinese Medicine (TCM) has many postulates that explain the occurrence and co-occurrence of symptoms using syndrome factors such as yang deficiency and yin deficiency. A fundamental question is whether the syndrome factors have verifiable scientific content or are purely subjective notions. This analysis investigated the issue in the context of patients with cardiovascular disease (CVD). DESIGN In the past, researchers have tried to show that TCM syndrome factors correspond to real entities by means of laboratory tests, with little success. An alternative approach, called latent tree analysis, has recently been proposed. The idea is to discover latent variables behind symptom variables by analyzing symptom data and comparing them with TCM syndrome factors. If there is a good match, then statistical evidence supports the validity of the relevant TCM postulates. This study used latent tree analysis. SETTING TCM symptom data of 3021 patients with CVD were collected from the cardiology departments of four hospitals in Shanghai, China, between January 2008 and June 2010. RESULTS Latent tree analysis of the data yielded a model with 34 latent variables. Many of them correspond to TCM syndrome factors. CONCLUSIONS The results provide statistical evidence for the validity of TCM postulates in the context of patients with CVD; in other words, they show that TCM postulates are applicable to such patients. This finding is important because it is a precondition for the TCM treatment of those patients.

Association study of ACE polymorphisms and systemic lupus erythematosus in Northern Chinese Han population

Systemic lupus erythematosus (SLE) is an autoimmune disease, with multiple genetic and environmental factors involving in its etiology. Angiotensin converting enzyme (ACE) gene was reported to have important roles in the development and progression of SLE. In this study, a case–control study was carried out to investigate the effects of seven SNPs and I/D in ACE gene in the development of SLE in Northern China. Seven SNPs including A5466C, T3892C, A240T, C1237T, G2215A, A2350G and C3409T were genotyped by PCR-RFLP method, and I/D was examined by agarose gel electrophoresis followed PCR directly. 314 SLE patients were compared to 320 normal controls in the study. Data were analyzed by SPSS 13.0 and HaploView software. The frequency distribution of SNP A2350G and Alu I/D and five haplotypes (AAAACCCI, AGAACCTD, AAAATCTI, TAAATTTI and TAAATCTI) were demonstrated to be different between case and control groups significantly. Whereas other SNPs and haplotypes had no differences in two cohorts. The results revealed that variations of ACE gene had association with SLE, which indicated ACE gene may play an important role in pathogenesis of SLE in Northern Chinese Han population.

Analysis of the diagnostic consistency of Chinese medicine specialists in cardiovascular disease cases and syndrome identification based on the relevant feature for each label learning method

ObjectiveTo analyze the diagnostic consistency of Chinese medicine (CM) specialists in patients with cardiovascular disease and to study syndrome classification and identification based on the multi-label learning method.MethodsUsing self-developed CM clinical scales to collect cases, inquiry information, complexity, tongue manifestation and pulse manifestation were assessed. The number of cases collected was 2,218. Firstly, each case was differentiated by two CM specialists according to the same diagnostic criteria. The consistency of the diagnosis based on Cohen’s Kappa coefficient was analyzed. Secondly, take the same diagnosis syndromes of two specialists as the results of the cases. According to injury information in the CM scale “yes” or “no” was assigned “1” or “0”, and according to the syndrome type in each case “yes” or “no” was assigned “1” or “0”. CM information data on cardiovascular disease cases were established. We studied CM syndrome classification and identification based on the relevant feature for each label (REAL) learning method, and the diagnostic rate of the syndrome was studied using the REAL method when the number of features selected was 5, 10, 15, 20, 30, 50, 70, and 100, respectively.ResultsThe syndromes with good diagnostic consistency were Heart (Xin)-qi deficiency, Heart-yang deficiency, Heart-yin deficiency, phlegm, stagnation of blood and stagnation of qi. Syndromes with poor diagnostic consistency were heartblood deficiency and blood deficiency of Heart and Liver (Gan). The highest diagnostic rates using the REAL method were Heart-yang deficiency followed by Heart-qi deficiency. A different number of features, such as 5, 10, 15, 20, 30, 40, 50, 70, and 100, respectively, were selected and the diagnostic accuracy based on five features showed the highest diagnostic accuracy. The top five features which had a strong correlation with the syndromes were in accordance with the CM theory.ConclusionsCM syndrome differentiation is strongly subjective and it is difficult to obtain good diagnostic consistency. The REAL method fully considers the relationship between syndrome types and injury symptoms, and is suitable for the establishment of models for CM syndrome classification and identification. This method can probably provide the prerequisite for objectivity and standardization of CM differentiation.

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

ObjectiveTo 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.MethodsFour 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).ResultsREAL 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.ConclusionsThe 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.

Analysis and Recognition of Traditional Chinese Medicine Pulse Based on the Hilbert-Huang Transform and Random Forest in Patients with Coronary Heart Disease

Objective. This research provides objective and quantitative parameters of the traditional Chinese medicine (TCM) pulse conditions for distinguishing between patients with the coronary heart disease (CHD) and normal people by using the proposed classification approach based on Hilbert-Huang transform (HHT) and random forest. Methods. The energy and the sample entropy features were extracted by applying the HHT to TCM pulse by treating these pulse signals as time series. By using the random forest classifier, the extracted two types of features and their combination were, respectively, used as input data to establish classification model. Results. Statistical results showed that there were significant differences in the pulse energy and sample entropy between the CHD group and the normal group. Moreover, the energy features, sample entropy features, and their combination were inputted as pulse feature vectors; the corresponding average recognition rates were 84%, 76.35%, and 90.21%, respectively. Conclusion. The proposed approach could be appropriately used to analyze pulses of patients with CHD, which can lay a foundation for research on objective and quantitative criteria on disease diagnosis or Zheng differentiation.

Classification Research on Syndromes of TCM Based on SVM

Syndrome is a unique TCM concept, which is an abstractive collection of symptoms and signs. Several modern algorithms have been applied to classify syndromes, but no satisfied results have been obtained because of the complexity of diagnosis procedure. Support vector machine (SVM) has been found to be very efficient to solve the classification problems, especially for binary classification with good generalization properties. In this paper, firstly patients’ clinic data of heart disease were preprocessed, then chose the optimal kernel function and used the cross-validation method to find the best parameters for SVM model, finally, the accuracy of testing different syndromes in accordance with pathology of heart disease was obtained. The results indicated that SVM was the best identifier with 81.08% accuracy on samples than the stepwise regression with 77.30% and the neural network with 73.72%. In addition, by comparing with four different kernel functions of SVM, radial basis function (RBF) was the best identifier than the others. Keywords-Syndrome; Traditional Chinese Medicine; Support Vector Machine

Multi-SVM based differential diagnostics in TCM

The differential diagnostics of Traditional Chinese Medicine is the kernel of TCM. The objective study of TCM diagnostics is a research hot spot at present. The differential diagnostics process of TCM is very complex and nonlinear. Support Vector Machine (SVM) is a novel method to establish the diagnosis model of TCM. In this paper, the differential diagnostics model is constructed base on multi-SVM. A comparison is made between gaussian and poly kernel functions in SVM for differential diagnostics. The model based on multi-SVM presented can deal with accompanying syndromes better. The model can provide a new way to solve TCM differential diagnostics.

Objective study for pulse diagnosis of Traditional Chinese Medicine: Pulse signal analysis of patients with Coronary Heart Disease

Objectives: Coronary Heart Disease (CHD) is the leading cause of death for adults worldwide. Pulse diagnosis is a specific diagnostic method in the Traditional Chinese Medicine (TCM). The purpose of this study is to identify the differences of the pulse among CHD patients, cardiovascular disease patients without CHD (Non-CHD) and healthy individuals (Normal). Additionally, to calculate the classification recognition rates with the significant pulse parameters. Methods: 251 subjects were recruited (102 in the CHD group, 94 in the Non-CHD group and 55 in the Normal group). Pulse signals were collected by a pressure sensor (ZBOX-I Digital Pulse Analysis System, designed by Shanghai University of TCM, China) from left-Guan. The time-domain parameters were extracted from the ZBOX-I system. The original data were transformed to frequency-domain and then the relative parameters were calculated. The differences of the parameters among these three groups were compared and contrasted. Moreover, a Fisher Linear Discriminant (FLD) was used to verify the accuracy of the significant parameters. Results: This research showed that the parameters such as: h1, h3, h4, t1, t4, t5, h3/h1, h4/h1, w/t, pulse rate and maximum power value were significantly different. About 81.5% accuracy was attained between CHD group and Normal group in the classification, while 68.5% accuracy between CHD group and Non-CHD group. Conclusions: These results demonstrate that some parameters in time-domain and frequency-domain are good indicators to distinguish CHD patients from healthy individuals as well as cardiovascular disease patients without CHD. Furthermore, they prove that pulse diagnosis, which is a non-invasive and inexpensive method, is a valuable auxiliary tool for the CHD diagnosis and its treatment evaluation.

Research on Zheng Classification Fusing Pulse Parameters in Coronary Heart Disease

This study was conducted to illustrate that nonlinear dynamic variables of Traditional Chinese Medicine (TCM) pulse can improve the performances of TCM Zheng classification models. Pulse recordings of 334 coronary heart disease (CHD) patients and 117 normal subjects were collected in this study. Recurrence quantification analysis (RQA) was employed to acquire nonlinear dynamic variables of pulse. TCM Zheng models in CHD were constructed, and predictions using a novel multilabel learning algorithm based on different datasets were carried out. Datasets were designed as follows: dataset1, TCM inquiry information including inspection information; dataset2, time-domain variables of pulse and dataset1; dataset3, RQA variables of pulse and dataset1; and dataset4, major principal components of RQA variables and dataset1. The performances of the different models for Zheng differentiation were compared. The model for Zheng differentiation based on RQA variables integrated with inquiry information had the best performance, whereas that based only on inquiry had the worst performance. Meanwhile, the model based on time-domain variables of pulse integrated with inquiry fell between the above two. This result showed that RQA variables of pulse can be used to construct models of TCM Zheng and improve the performance of Zheng differentiation models.