Dataset Information

Development of models for classification of action between heat-clearing herbs and blood-activating stasis-resolving herbs based on theory of traditional Chinese medicine.

ABSTRACT:

Background

Action ("gongxiao" in Chinese) of traditional Chinese medicine (TCM) is the high recapitulation for therapeutic and health-preserving effects under the guidance of TCM theory. TCM-defined herbal properties ("yaoxing" in Chinese) had been used in this research. TCM herbal property (TCM-HP) is the high generalization and summary for actions, both of which come from long-term effective clinical practice in two thousands of years in China. However, the specific relationship between TCM-HP and action of TCM is complex and unclear from a scientific perspective. The research about this is conducive to expound the connotation of TCM-HP theory and is of important significance for the development of the TCM-HP theory.

Methods

One hundred and thirty-three herbs including 88 heat-clearing herbs (HCHs) and 45 blood-activating stasis-resolving herbs (BAHRHs) were collected from reputable TCM literatures, and their corresponding TCM-HPs/actions information were collected from Chinese pharmacopoeia (2015 edition). The Kennard-Stone (K-S) algorithm was used to split 133 herbs into 100 calibration samples and 33 validation samples. Then, machine learning methods including supported vector machine (SVM), k-nearest neighbor (kNN) and deep learning methods including deep belief network (DBN), convolutional neutral network (CNN) were adopted to develop action classification models based on TCM-HP theory, respectively. In order to ensure robustness, these four classification methods were evaluated by using the method of tenfold cross validation and 20 external validation samples for prediction.

Results

As results, 72.7-100% of 33 validation samples including 17 HCHs and 16 BASRHs were correctly predicted by these four types of methods. Both of the DBN and CNN methods gave out the best results and their sensitivity, specificity, precision, accuracy were all 100.00%. Especially, the predicted results of external validation set showed that the performance of deep learning methods (DBN, CNN) were better than traditional machine learning methods (kNN, SVM) in terms of their sensitivity, specificity, precision, accuracy. Moreover, the distribution patterns of TCM-HPs of HCHs and BASRHs were also analyzed to detect the featured TCM-HPs of these two types of herbs. The result showed that the featured TCM-HPs of HCHs were cold, bitter, liver and stomach meridians entered, while those of BASRHs were warm, bitter and pungent, liver meridian entered.

Conclusions

The performance on validation set and external validation set of deep learning methods (DBN, CNN) were better than machine learning models (kNN, SVM) in sensitivity, specificity, precision, accuracy when predicting the actions of heat-clearing and blood-activating stasis-resolving based on TCM-HP theory. The deep learning classification methods owned better generalization ability and accuracy when predicting the actions of heat-clearing and blood-activating stasis-resolving based on TCM-HP theory. Besides, the methods of deep learning would help us to improve our understanding about the relationship between herbal property and action, as well as to enrich and develop the theory of TCM-HP scientifically.

SUBMITTER: Chen Z

PROVIDER: S-EPMC5828388 | biostudies-literature | 2018

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Development of models for classification of action between heat-clearing herbs and blood-activating stasis-resolving herbs based on theory of traditional Chinese medicine.

Chen Zhao Z Cao Yanfeng Y He Shuaibing S Qiao Yanjiang Y

Chinese medicine 20180227

<h4>Background</h4>Action ("<i>gongxiao</i>" in Chinese) of traditional Chinese medicine (TCM) is the high recapitulation for therapeutic and health-preserving effects under the guidance of TCM theory. TCM-defined herbal properties ("<i>yaoxing</i>" in Chinese) had been used in this research. TCM herbal property (TCM-HP) is the high generalization and summary for actions, both of which come from long-term effective clinical practice in two thousands of years in China. However, the specific relat ...[more]

PMID: 29492098

Similar Datasets

Project description:Background and objectiveIschaemic encephalopathy is a common cerebrovascular disease caused by insufficient blood supply to the cerebral vessels. The ischaemic encephalopathy is closely associated with the development of many chronic diseases such as obesity, hypertension and diabetes. Neurotrophic therapy has become the main therapeutic strategy for ischaemic encephalopathy. However, neurotrophic drugs only slightly recover the neurological function of patients, and their long-term efficacy is uncertain. Previous reports revealed that the active ingredients of natural medicines play important roles in the treatment of cerebral ischemia. In this study, we reviewed clearing herbs with anti-ischaemic encephalopathy functions using the data from quantitative statistical and network pharmacological exploration methods. We also discussed the different bioactive components and pharmacological effects of these herbs.MethodsFirst, we collected Chinese herbal prescriptions against ischaemic encephalopathy in four databases. Then, we statistically analysed the frequency of application of heat-clearing herbs to obtain the commonly used heat-clearing herbs against ischaemic encephalopathy, and classified them according to their efficacy according to the statistical results, to summarize the mechanism of anti-ischaemic effects of different bioactive components; Second, the network database was used to obtain the above components of heat-clearing Chinese medicines and their corresponding targets of action, disease targets of ischaemic stroke; Venny 2.1.0 was used to obtain component-disease target intersections; Cytoscape was used to construct the 'Drug-Active Ingredient-Target Network Graph '; DAVID was used for GO and KEGG enrichment analysis.ResultsLiterature and database screening involved 149 prescriptions, with a total of 269 flavours of Chinese medicines and 20 flavours of single-flavour heat-clearing Chinese medicines; The top nine in terms of frequency of use were Radix Paeoniae Rubra、Rehmanniae Radix Praeparata、Figwort Root、Cortex Moutan、Scutellariae Radix、Coptidis Rhizoma、Gardeniae Fructus、Cassiae Semen、Lonicerae Japonicae Flos. The common components obtained from network pharmacology were beta-sitosterol, quercetin, and stigmasterol, which mainly act on key targets such as RELA, AKT1, JUN, PRKACA, PTGS2, RAF1 and CHUK; and their active ingredients are mainly involved in signalling pathways such as Calcium, PI3K-Ak, MAPK, cAMP, IL-17, HIF-1, TNF, T-cell receptor, NF-kappa B and JAK-STAT.ConclusionsHeat-clearing herbs are useful and promising for the protection against and prevention of ischemic encephalopathy. The results of the network pharmacological studies are similar to the mechanisms of anti-ischemic encephalopathy of the active ingredients of the purgative herbs we have listed; Thin either directly protects cerebrovascular tissues by improving vascular permeability and reducing the area of infarcted tissues, or produces protective effects through molecular signaling pathways. It can be seen that the components of heat-clearing Chinese medicines can exert cerebroprotective effects through multiple pathways, which provides us with a reference for further development and study of heat-clearing Chinese medicines in the treatment of ischemic cerebrovascular diseases.

Project description:PurposeThe purpose of this study is to study the effects of heat-clearing Traditional Chinese Medicine (TCM) in the stable stage of bronchiectasis via N-of-1 trials.MethodsThe N-of-1 trials in this study were randomized and double-blinded with crossover comparisons consisting of three pairs. Each pair was of two 4-week periods. Each patient took the individualized decoction in the experimental period and the individualized decoction was removed of heat-clearing drugs, mainly including heat-clearing and detoxifying drugs, in the control period for three weeks. After three weeks, the patients stopped taking the decoction for one week. The primary outcome was from patients' self-reporting symptoms scores on a 1-7-point Likert scale. Mixed-effects models were used to conduct statistical analysis on these N-of-1 trials.ResultsOf the 21 patients enrolled, 15 completed three pairs of N-of-1 trials (71.43%). (1) Seen from the individual level, no statistical difference between the experimental decoction and the control (P > 0.05) was observed. However, 5 patients found better decoctions according to the clinical criteria. (2) As revealed by the group data of all the N-of-1 trials, the control was better than the individualized decoction in terms of symptom scores on the Likert scale (1.94 ± 0.69 versus 2.08 ± 0.68, P = 0.04, mean difference, and 95% CI: 0.19 (0.01, 0.37)) and on CAT scores (13.66 ± 6.57 versus 13.95 ± 6.97, P = 0.04, mean difference, and 95% CI: 0.86 (0.042, 1.67)), but such differences were not clinically significant. The other outcomes, such as Likert scale score of respiratory symptoms and 24-hour sputum volume, showed no statistical difference.ConclusionThe experimental design of this study can make the TCM individualized treatment fully play its role and can detect the individualized tendencies according to the severity of phlegm and heat in some subjects. With the intermittent use or reduced use of heat-clearing drugs, most of the subjects, at the group level, enrolled in the series of N-of-1 trials may improve the symptoms and quality of life while saving the cost of TCM and reducing the potential side effects of heat-clearing TCM. This trial is registered with clinicaltrials.goc (NCT03147443).

Dataset Information

Development of models for classification of action between heat-clearing herbs and blood-activating stasis-resolving herbs based on theory of traditional Chinese medicine.

Background

Methods

Results

Conclusions

Publications

Development of models for classification of action between heat-clearing herbs and blood-activating stasis-resolving herbs based on theory of traditional Chinese medicine.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets