Characteristics of Pulse Parameters in Patients with Polycystic Ovary Syndrome Varied at Different Body Mass Index Levels.

Objective: To analyze the characteristics of pulse graph parameters in patients with polycystic ovary syndrome (PCOS) varied at different body mass index (BMI) levels and to provide pulse diagnosis basis for syndrome differentiation and treatment of PCOS. Methods: Pulse graph parameters of 152 patients with PCOS (26 lean patients, 63 patients with moderate weight, and 63 overweight patients) were measured by a Z-BOX pulse meter, and the pulse graph parameters of patients with PCOS varied at different BMI levels were analyzed. Results: Fine pulse, slippery pulse, and string-like pulse were the most common pulse conditions in patients with PCOS. The common pulse conditions of patients with PCOS varied at different BMI levels. The order of pulse conditions was as follows: lean group: fine pulse > string-like pulse > slippery pulse; moderate group: fine pulse > slippery pulse > string-like pulse; and overweight group: slippery pulse > fine pulse > sunken pulse. Compared to the overweight group, the pulse graph parameters h1, h3, h4, h5, h4/h1, As, and Ad increased in the moderate group (P < 0.05), and the parameters h1, h3, and Ad increased (P < 0.05) and the parameter t1 decreased (P < 0.05) in the lean group. Conclusion: Pulse graph parameters among patients with PCOS varied at different BMI levels, which can probably provide pulse diagnosis basis for syndrome differentiation and treatment of PCOS by traditional Chinese medicine (TCM).

Status and prospect of international standardization of TCM diagnosis.

The present study aimed to review the current status and development of international standards in the domain of traditional Chinese medicine (TCM) diagnosis. Moreover, the roles and relevant work of different organizations in developing such standards were explored, and the difficulties and challenges encountered were analyzed. The study further elaborated on the approaches to establish a complete set of international standards on TCM diagnosis. It also provided a promising solution for the development of international standards on TCM diagnosis.

Preliminary study on phonetic characteristics of patients with pulmonary nodules.

OBJECTIVE: Pulmonary nodules (PNs) are one of the imaging manifestations of early lung cancer screening, which should receive more attention. Traditional Chinese medicine believes that voice changes occur in patients with pulmonary diseases. The purpose of this study is to explore the differences in phonetic characteristics between patients with PNs and able-bodied persons. METHODS: This study explores the phonetic characteristics of patients with PNs in order to provide a simpler and cheaper method for PN screening. It is a case-control study to explore the differences in phonetic characteristics between individuals with and without PNs. This study performed non-parametric statistics on acoustic parameters of vocalizations, collected from January 2017 to March 2018 in Shanghai, China, from these two groups; it explores the differences in third and fourth acoustic parameters between patients with PNs and a normal control group. At the same time, computed tomography (CT) scans, course of disease, combined disease and other risk factors of the patients were collected in the form of questionnaire. According to the grouping of risk factors, the phonetic characteristics of the patients with PNs were analyzed. RESULTS: This study was comprised of 200 patients with PNs, as confirmed by CT, and 86 healthy people that served as a control group. Among patients with PNs, 43% had ground glass opacity, 32% had nodules with a diameter ≥ 8 mm, 19% had a history of smoking and 31% had hyperlipidemia. Compared with the normal group, there were statistically significant differences in pitch, intensity and shimmer in patients with PNs. Among patients with PNs, patients with diameters ≥ 8 mm had a significantly higher third formant. There was a significant difference in intensity, fourth formant and harmonics-to-noise ratio (HNR) between smoking and non-smoking patients. Compared with non-hyperlipidemia patients, the pitch, jitter and shimmer of patients with PNs and hyperlipidemia were higher and the HNR was lower; these differences were statistically significant. CONCLUSION: This measurable changes in vocalizations can be in patients with PNs. Patients with PNs had lower and weaker voices. The size of PNs had an effect on the phonetic formant. Smoking may contribute to damage to the voice and formant changes. Voice damage is more pronounced in individuals who have PNs accompanied by hyperlipidemia.

[Effect of acupoint catgut embedding on levels of PG-related factors and NF-κB proteins in ute-rine tissues of rats with primary dysmenorrhea].

OBJECTIVE: To observe the effect of acupoint catgut embedding on levels of prostaglandin F2α(PGF2α), cyclooxygenase-2(COX-2) and nuclear factor kappa B(NF-κB) in the uteruses of rats with primary dysmenorrhea (PD), so as to explore its mechanisms underlying improvement of PD. METHODS: Forty female SD rats were randomly divided into normal, model, acupoint catgut embedment and medication groups, with 10 rats in each group. The PD model was established by subcutaneous injection of estradiol benzoate (0.5 mg on the 1st day, and 0.2 mg thereafter) once daily for 10 days, followed by i．p. of oxytocin 2 U(0.5 mg•5 U－1•mL－1) on the 11th day. Catgut embedment was applied to "Guanyuan"(CV4) and "Sanyinjiao"(SP6) on day 1 and 5 while modeling, and rats of the medication group received gavage of ibuprofen (1.25 mg/mL, 0.8 mL/rat) once daily for 10 d. The level of PGF2αin the uterus tissuewas assayed by ELISA, and the expression levels of uterine COX-2, phospho (p)-NF-κB p65, NF-κB p65 proteins were detected by Western blot. RESULTS: Compared with the normal group, the levels of PGF2α， COX-2, p-NF-κB p65 and NF-κB p65 in the uterine tissues were significantly increased in the model group (P<0.05). Compared with the model group, the levels of PGF2α and COX-2 in both catgut embedment and medication groups as well as p-NF-κB p65 in the catgut embedment group were significantly decreased (P<0.05). Compared with the medication group, the level of p-NF-κB 65 in the catgut embedment group was significantly decreased (P<0.05). CONCLUSION: The analgesic effect of acupoint catgut embedding may be related to its effects in down-regulating the expression of p-NF-κB and the levels of COX-2 and PGF2αin uteruses of PD rats.

[Material basis and molecular mechanism of Dachengqi Decoction in treatment of acute pancreatitis based on network pharmacology].

The network pharmacology was used to investigate the material basis and molecular mechanism of Dachengqi Decoction(DCQD) in the treatment of acute pancreatitis(AP). Potential targets of components from DCQD and relevant pathogenic genes of AP were identified through database retrieval. Then, crucial targets were verified with relevant active chemical components via molecular docking. DAVID database was used to explore the functions and pathways involved in the treatment of AP. A total of 108 components were correlated with 28 targets. Molecular docking showed a strong binding ability of key targets and their corresponding compounds. DAVID enrichment analysis showed 438 biological process, 31 molecular functions, 17 cellular components and 96 KEGG pathways. DCQD may achieve its pharmacological effects through anti-inflammatory and anti-oxidative effects, negative regulation of apoptosis and regulation of pancreatic secretion, involving multiple signals, such as IL-17, TNF and NF-κB signaling pathway. In this study, it is the first time to use the method of network pharmacology to reveal the molecular mechanism of DCQD in the treatment of AP by multiple components and multi-signaling pathways, which provides a basis for further biological experiments of AP.

[Acupoint catgut embedding improves dysmenorrhea by suppressing activation of NLRP3 inflammasomes in uterine tissues in primary dysmenorrhea rats].

OBJECTIVE: To observe the effect of acupoint catgut embedding on the expression of nucleotide-binding oligomerization domain (NOD)-like receptor protein 3 (NLRP3) inflammasome, interleukin (IL)-1ß and IL-18 in the uterine tissue of primary dysmenorrhea (PD) rats, so as to explore its underlying mechanisms in improving PD. METHODS: Forty female SD rats were randomly divided into control, model, acupoint catgut embedding and medication groups (n＝10 in each group). The PD model was established by subcutaneous injection of Estradiol Benzoate (0.5 mg/rat on the 1st and 10thday, and 0.2 mg/rat from 2nd to 9thday) and Oxytocin (2 U/rat, i．p.). The catgut embedding was applied to bilateral "Sanyinjiao" (SP6) and "Guanyuan" (CV4) on the 1st and 5th day after modeling. Rats of the medication group were treated by intragastric perfusion of Fenbid (0.8 mL/rat, 125 mg/100 mL) once daily for 10 days. The body writhing times in 30 min were recorded. The histopathological changes of the uterine were observed by H．E. staining. Western blot was used to detect the expression of NLRP 3, caspase-1, IL-1ß and IL-18 in uterine tissues. RESULTS: The body writhing times were notably more in the model group than in the control group (P<0.01), and obviously fewer in both medication and catgut embedding groups than in the model group (P<0.05, P<0.01). After modeling, the rats' endometrium was extensively exfoliated and got swelling, the histopathological score and the expression levels of NLRP3, caspase-1, IL-1ß and IL-18 proteins in the uterus tissue were evidently increased in the model group relevant to the control group (P<0.01). Following the treatment, the degree of endometrial exfoliation and edema of the uterus tissue was lightened, the pathological score was significantly reduced (P<0.01), and the expression levels of caspase-1, IL-1ß and IL-18 protein in uterus tissue were markedly decreased in both acupoint catgut embedding and medication groups (P<0.01, P<0.05). The NLRP3 protein expression was significantly decreased in the acupoint catgut embedding group compared with that in the model group (P<0.01). The therapeutic effect of acupoint catgut embedding was significantly superior to that of medication in reducing writhing times and down-regulating expression of NLPR3 protein (P<0.01). No significant differences were found between catgut embedding and medication in histopathological score, and expression levels of caspase-1, IL-1ß and IL-18 proteins (P>0.05). CONCLUSION: The acupoint catgut embedding can significantly alleviate the symptoms and pathological damage in PD rats, which may be related to its effect in inhibiting the activation of NLRP3 inflammasome in the uterine tissue.

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

OBJECTIVE: To 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. METHODS: Four 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). RESULTS: REAL 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. CONCLUSIONS: The 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.

Prenatal choline supplementation attenuates spatial learning deficits of offspring rats exposed to low-protein diet during fetal period.

Prenatal intake of choline has been reported to lead to enhanced cognitive function in offspring, but little is known about the effects on spatial learning deficits. The present study examined the effects of prenatal choline supplementation on developmental low-protein exposure and its potential mechanisms. Pregnant female rats were fed either a normal or low-protein diet containing sufficient choline (1.1g/kg choline chloride) or supplemented choline (5.0g/kg choline chloride) until delivery. The Barnes maze test was performed at postnatal days 31-37. Choline and its metabolites, the synaptic structural parameters of the CA1 region in the brain of the newborn rat, were measured. The Barnes maze test demonstrated that prenatal low-protein pups had significantly greater error scale values, hole deviation scores, strategy scores and spatial search strategy and had lesser random search strategy values than normal protein pups (all P<.05). These alterations were significantly reversed by choline supplementation. Choline supplementation increased the brain levels of choline, betaine, phosphatidylethanolamine and phosphatidylcholine of newborns by 51.35% (P<.05), 33.33% (P<.001), 28.68% (P<.01) and 23.58% (P<.05), respectively, compared with the LPD group. Prenatal choline supplementation reversed the increased width of the synaptic cleft (P<.05) and decreased the curvature of the synaptic interface (P<.05) induced by a low-protein diet. Prenatal choline supplementation could attenuate the spatial learning deficits caused by prenatal protein malnutrition by increasing brain choline, betaine and phospholipids and by influencing the hippocampus structure.

Pulse signal analysis of patients with coronary heart diseases using Hilbert-Huang transformation and time-domain method.

OBJECTIVE: To explore characteristic of pulse signal to distinguish patients with coronary heart diseases (CHD) from patients without CHD and healthy adults, and accordingly evaluate the potential role of pulse signal to diagnosis CHD. METHODS: Totally 407 patients enrolled from 4 collaborating medical centers were assigned to a CHD group (205 patients) and a non-CHD group (202 patients). The healthy control group (62 adults) enrolled from Shanghai University of Traditional Chinese Medicine. Pulse signals were collected using the synchronous multiplex pulse signal acquisition system. The pulse signals were analyzed and extracted using Hilbert-Huang transformation (HHT) and time-domain, respectively. The time-domain parameters of pulse signal were processed by the analysis of variance (SNK test). RESULTS: Special patterns in the CHD group pulse signal were found in this study: (1) time-domain parameters of pulse signal, h1, h3, h4, h3/h1, ts, t4/t were increased and w was wider; (2) 44% of C2 waves in HHT were chaotic and disordered and 72% of C waves were exhibited irregularly with average amplitude over 10 g-forces, which were all significantly different from controls. CONCLUSION: Characteristic wave and time-domain parameters of pulse signal were extracted using HHT and time-domain which could be served as a non-invasive approach for assessing patients with CHD.

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.

OBJECTIVE: To 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. METHODS: Using 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. RESULTS: The 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 heart-blood 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. CONCLUSIONS: CM 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.

Objective Auscultation of TCM Based on Wavelet Packet Fractal Dimension and Support Vector Machine.

This study was conducted to illustrate that auscultation features based on the fractal dimension combined with wavelet packet transform (WPT) were conducive to the identification the pattern of syndromes of Traditional Chinese Medicine (TCM). The WPT and the fractal dimension were employed to extract features of auscultation signals of 137 patients with lung Qi-deficient pattern, 49 patients with lung Yin-deficient pattern, and 43 healthy subjects. With these features, the classification model was constructed based on multiclass support vector machine (SVM). When all auscultation signals were trained by SVM to decide the patterns of TCM syndromes, the overall recognition rate of model was 79.49%; when male and female auscultation signals were trained, respectively, to decide the patterns, the overall recognition rate of model reached 86.05%. The results showed that the methods proposed in this paper were effective to analyze auscultation signals, and the performance of model can be greatly improved when the distinction of gender was considered.

Deep learning based syndrome diagnosis of chronic gastritis.

In Traditional Chinese Medicine (TCM), most of the algorithms used to solve problems of syndrome diagnosis are superficial structure algorithms and not considering the cognitive perspective from the brain. However, in clinical practice, there is complex and nonlinear relationship between symptoms (signs) and syndrome. So we employed deep leaning and multilabel learning to construct the syndrome diagnostic model for chronic gastritis (CG) in TCM. The results showed that deep learning could improve the accuracy of syndrome recognition. Moreover, the studies will provide a reference for constructing syndrome diagnostic models and guide clinical practice.

Metabolic markers and microecological characteristics of tongue coating in patients with chronic gastritis.

BACKGROUND: In Traditional Chinese Medicine (TCM), tongue diagnosis has been an important diagnostic method for the last 3000 years. Tongue diagnosis is a non-invasive, simple and valuable diagnostic tool. TCM treats the tongue coating on a very sensitive scale that reflects physiological and pathological changes in the organs, especially the spleen and stomach. Tongue coating can diagnose disease severity and determine the TCM syndrome ("Zheng" in Chinese). The biological bases of different tongue coating appearances are still poorly understood and lack systematic investigation at the molecular level. METHODS: Tongue coating samples were collected from 70 chronic gastritis patients and 20 normal controls. 16S rRNA denatured gradient gel electrophoresis (16S rRNA-DGGE) and liquid chromatography and mass spectrometry (LC-MS) were designed to profile tongue coatings. The statistical techniques used were principal component analysis and partial least squares-discriminate analysis. RESULTS: Ten potential metabolites or markers were found in chronic gastritis patients, including UDP-D-galactose, 3-ketolactose, and vitamin D2, based on LC-MS. Eight significantly different strips were observed in samples from chronic gastritis patients based on 16S rRNA-DGGE. Two strips, Strips 8 and 10, were selected for gene sequencing. Strip 10 sequencing showed a 100% similarity to Rothia mucilaginosa. Strip 8 sequencing showed a 96.2% similarity to Moraxella catarrhalis. CONCLUSIONS: Changes in glucose metabolism could possibly form the basis of tongue coating conformation in chronic gastritis patients. The study revealed important connections between metabolic components, microecological components and tongue coating in chronic gastritis patients. Compared with other diagnostic regimens, such as blood tests or tissue biopsies, tongue coating is more amenable to, and more convenient for, both patients and doctors.

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.

[Metabolite changes in the greasy tongue coating of patients with chronic gastritis].

OBJECTIVE: To explore the changes in metabolites in the greasy tongue coating in patients with chronic gastritis. METHODS: Forty chronic gastritis patients presenting with greasy tongue coating, 30 chronic gastritis patients presenting with non-greasy tongue coating, and 20 healthy control persons presenting with light red tongues and thin white coating were enrolled, and the tongue coating was detected by combining artificial diagnosis and the Z-BOX Tongue Digital Analyzer's diagnosis. Samples of all the tongue coatings were collected before treatment. The metabolic fingerprinting of the tongue coating samples was obtained using ultra-performance liquid chromatography and mass spectrometry (UPLC-MS), and the metabolic components in the tongue coating samples were detected. After this, principal component analysis, partial least squares discriminant analysis and orthogonal partial least squares discriminant analysis (OPLS-DA) were used to identify potential metabolic markers. Finally, the components were identified using the Chemspider and HMDB searching. RESULTS: UPLC-MS results were analyzed by OPLS-DA and showed that the metabolites among the three groups were distributed in different regions. The different potential metabolic markers between the patients with or without greasy coating were 3-ketolactose, 2-deoxy-D-ribose, UDP-D-galactose metarhodopsin, ascorbate, picolinate and histidine. The different potential metabolic markers between the greasy coating group and the normal group were 3-ketolactose, UDP-D-galactose, leukotriene A4 and vitamin D(2). CONCLUSION: The metabolites of the greasy coating group, the non-greasy coating group and the normal group show significant differences in energy metabolism, mainly of glucose metabolism. This demonstrated that glucose metabolism may be one of the mechanisms leading to the formation of greasy coating.

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.

Nonlinear Analysis of Auscultation Signals in TCM Using the Combination of Wavelet Packet Transform and Sample Entropy.

Auscultation signals are nonstationary in nature. Wavelet packet transform (WPT) has currently become a very useful tool in analyzing nonstationary signals. Sample entropy (SampEn) has recently been proposed to act as a measurement for quantifying regularity and complexity of time series data. WPT and SampEn were combined in this paper to analyze auscultation signals in traditional Chinese medicine (TCM). SampEns for WPT coefficients were computed to quantify the signals from qi- and yin-deficient, as well as healthy, subjects. The complexity of the signal can be evaluated with this scheme in different time-frequency resolutions. First, the voice signals were decomposed into approximated and detailed WPT coefficients. Then, SampEn values for approximated and detailed coefficients were calculated. Finally, SampEn values with significant differences in the three kinds of samples were chosen as the feature parameters for the support vector machine to identify the three types of auscultation signals. The recognition accuracy rates were higher than 90%.

[Study of traditional Chinese medicine pulse signals in patients with coronary heart disease based on recurrence quantification analysis].

OBJECTIVE: By using recurrence quantification analysis (RQA) to analyze traditional Chinese medicine pulse signals of patients with coronary heart disease (CHD), this study aims to find nonlinear dynamic parameters of pulses to distinguish patients with CHD from normal subjects. METHODS: First, pulse signals were collected using ZBOX-I pulse digitization gathering analyzer from October 2007 to June 2008. RQA was used to analyze RQA parameters of pulses of 63 patients with CHD and 61 normal subjects. RQA parameters included recurrence rate (RR), determinism (DET), averaged diagonal length (L), entropy of diagonal length (ENTR), length of longest diagonal line (L(max)), laminarity (LAM), trapping time (TT) and length of longest vertical line (V(max)). Then, rank-sum test and BoxPlot were employed to find significant difference and distribution of RQA parameters. Lastly, receiver operating characteristic (ROC) curves were used to assess the diagnostic value of the measurements with significant difference. RESULTS: There were significant differences in RQA parameters of pulse signals between the two groups, including RR, DET, L, ENTR, LAM, TT and V(max), and their areas under the ROC curves were 1.000, 0.898, 0.653, 0.673, 0.885, 0.898, 0.986 and 0.994, respectively. CONCLUSION: Compared with the normal subjects, the pulse signals of the patients with CHD are presented with more certainty, regularity and stability. RQA measurements of RR, TT, Vmax, DET and LAM show good diagnostic value according to their ROC curves.

Study on intelligent syndrome differentiation in traditional Chinese medicine based on multiple information fusion methods.

Numerous researchers have taken the solid step forward towards the objectification research of Traditional Chinese Medicine (TCM) four diagnostic methods. However, it is deficient in studies on information fusion of the four diagnostic methods. We establish four-diagnosis syndrome differentiation model of TCM based on information fusion technology. The objective detection instruments of four-diagnostic method are applied to collect four-diagnosis objective information of 506 cases of clinical heart-system patients. Then multiple information fusion methods are adopted to establish recognition model of syndromes. The results of our experiments show that recognition rates of the six syndromes using multi-label learning is better than OCON artificial neural network and multiple support vector machine.

Application of voice signal collection and analysis in traditional Chinese medicine syndrome differentiation of deficiency and excess.

OBJECTIVE: To provide more objective basis for traditional Chinese medicine (TCM) syndrome differentiation of deficiency and excess by collecting and analyzing voice signals and extracting characteristic parameters. METHODS: All of 308 samples including 150 samples of qi-deficiency, 52 yin-deficiency, 55 excess and 51 normal were collected by "Voice Collecting System of TCM" and analyzed by wavelet packet transform (WPT) combined with approximate entropy (ApEn). The characteristic parameters with remarkable differences were chosen as input vectors for support vector machine (SVM) classifier to obtain classification results. RESULTS: Comparison between the normal and non-healthy showed that ApEn values of several nodes in 2 to 3 kHz, 3.5 to 4 kHz and 5 to 8 kHz frequencies were significantly different (P≤0.05); comparison between the deficiency and excess showed that ApEn values of several nodes in 0 to 2.5 kHz and 6 to 6.5 kHz frequencies were significantly different (P≤0.05); comparison between the qi-deficiency and yin-deficiency showed that ApEn values of node in 2 to 4 kHz frequency were significantly different(P≤0.05). The outputs of SVM showed that accuracies of samples in each group had good classification results by analyzing the ApEn values in different frequencies through WPT. CONCLUSION: The methods of voice collection and analysis used in the auscultation of TCM can provide objective basis for syndrome differentiation of deficiency and excess.