ObjectiveTo explore a rapid and accurate method for evaluating the quality of Prunus mandshurica (Maxim.) Koehne (P. mandshurica, Ku Xing Ren) during rancidity using machine vision and learning.MethodsSensory evaluation and chemometrics were used to classify P. mandshurica quality grades after rancidity. Chemical indicators of the P. mandshurica quality change were determined to verify the obtained grades and support the subsequent modeling. The International Commission on Illumination color space was used to extract the color features of the P. mandshurica. Discrimination and prediction models based on color features combined with multiple machine learning algorithms were established using 10-fold cross-validation and external test set validation.ResultsThe P. mandshurica rancidity samples were allocated to three quality grades. The Bayes net model based on powder color successfully identified the P. mandshurica at different grades with an accuracy of 88.89% and 100% using two validations, and the naive Bayes model based on section color achieved the same accuracy with an receiver operating characteristic area of 0.979. The instance-based k-nearest neighbors model based on powder color performed best in predicting the amygdalin content [R2 = 0.9801, mean absolute error (MAE) = 0.2071, root mean squared error (RMSE) = 0.4170], followed by the random committee model in predicting the acid value (R2 = 0.9580, MAE = 1.5121, RMSE = 1.9099) and the random forest model in predicting the peroxide value (R2 = 0.8857, MAE = 0.0027, RMSE = 0.0035).ConclusionThis study demonstrates that color digitization analysis is a potential method for rapidly evaluating the quality of P. mandshurica across the rancidity process, providing a new reference for the quality assessment of traditional Chinese medicines.

ObjectiveTo observe the clinical effect of Xijiao Dihuangtang combined with acupuncture on the treatment of systemic lupus erythematosus （SLE） with syndrome of intense heat toxin. MethodA total of 102 cases of SLE with syndrome of intense heat toxin （admitted from January 2020 to December 2021） were divided into a control group and an observation group by random number table method， with 51 cases in each group. Patients in the control group received conventional western medicine treatment （hydroxychloroquine sulfate + poonisone acetate tablets）. Patients in the observation group were given Xijiao Dihuangtang combined with acupuncture based on the treatment of the control group. Clinical efficacy， onset time， symptom improvement time， skin lesion regression time， and hospital stays were recorded. Blood routine index change， 24 h urine protein levels， double-stranded DNA （ds-DNA） antibodies resistance index changes， traditional Chinese medicine （TCM） syndrome integral changes， and changes in serum cytokine indexes， blood rheology indexes， and T lymphocyte subsets indexes were observed. SLE changes in disease activity index （SLEDAI-2000）， quality of life （SF-36） scores， and adverse reactions were explored. ResultThe total effective rate was 96.08% （49/51） in the observation group， higher than 84.31% （43/51） in the control group （χ²=3.991， P<0.05）. The onset time， symptom improvement time， skin lesion regression time， and hospital stays in the observation group were shorter than those in the control group （P<0.05，P<0.01）. Before treatment， erythrocyte sedimentation rate （ESR）， platelet count （PLT）， hemoglobin （HGB）， white blood cell count （WBC）， and other blood routine indexes， 24h urinary protein levels， anti-ds-DNA， TCM syndrome integral core， serum cytokine indexes including interleukin-4 （IL-4）， IL-6， soluble interleukin-2 receptor （sIL-2R）， blood rheology indexes （fibrinogen， plasma viscosity， and whole blood viscosity），T lymphocyte subsets indexes （CD4⁺， CD8⁺， and CD4⁺/CD8⁺）， SLEDAI-2000， and SF-36 score comparison in both groups had no statistical significance. After treatment， the above indicators were improved in each group （P<0.05）， and the indicators in the observation group was better than that in the control group （P<0.05）. In terms of the adverse reactions， there was 1 case of digestive tract reaction， 1 case of elevated aminotransferase， and 1 case of insomnia in the observation group. There were 2 cases of digestive tract reaction，1 case of infection， and 1 case of elevated transaminase in the control group. The difference of the adverse reactions between the two groups had no statistical significance. ConclusionXijiao Dihuangtang combined with acupuncture has good clinical effect on the treatment of SLE with syndrome of intense heat toxin， and the method is safe， reliable， and worthy of application.

Objective: To analyze the clinical risk factors of bronchopulmonary dysplasia(BPD) in very premature infants and provide reference for the prevention and treatment of BPD in order to improve the prognosis of premature infants. Methods: From January 2015 to December 2017, 263 very premature infants(referring to premature infants with gestational age between 28 weeks and 32 weeks) in the neonatology department of the Maternal and Child Health Care Hospital Affiliated to Anhui Medical University were selected.They were divided into BPD group(108 cases) and non-BPD group(155 cases) according to the diagnostic criteria of BPD.The clinical data of the patients and the hospitalized patients were retrospectively investigated.The general conditions of the very premature infants in the two groups were compared.The clinical risk factors for BPD in very premature infants were analyzed. Results: There were 263 very preterm infants included in the study, 108 cases in the BPD group, the incidence was 41.1%.The data analysis showed that BPD occurred in premature infants with sex(χ²=4.311), gestational age(Z=-6.544), birth weight(t=-5.382), maternal chorioamnionitis(χ²=4.946), neonatal respiratory distress syndrome(χ²=25.424), anemia(χ²=22.443), multiple blood transfusion(Z=-8.101), mechanical ventilation time greater than 7 days(χ²=10.946), high oxygen concentration(χ²=25.028), the differences were statistically significant(all P<0.05). The multivariate logistic regression analysis suggested that gestational age(OR=1.478, 95% CI: 1.140-1.914), maternal pregnancy with chorioamnionitis (OR=0.152, 95% CI: 0.029-0.797), maximum oxygen concentration>40%(OR=0.261, 95% CI: 0.136-0.502), number of blood transfusions(OR=0.582, 95% CI: 0.456-0.742) were independent risk factors for BPD in preterm infants. Conclusion There are many factors leading to BPD in premature infants, including maternal comorbidities and neonatal factors, and its pathogenesis is complex and diverse.It is necessary to further study these related factors, timely intervention, strengthen maternal health care, and minimize risk factors, thus to reduce the incidence of BPD, improve the prognosis of premature infants.

Glycyrrhizae Radix et Rhizoma is one of the traditional herbal medicine used in China, study on the correlation between the cross-section color and HPLC fingerprints of them have important significance for promoting the development of traditional disciplines. Quantitative analysis of the color of sample cross section was carried out by color digital method, fingerprint analysis was carried out by HPLC, and the canonical correlation analysis was carried out between them. The results showed that there was a significant correlation between the color of Glycyrrhizae Radix et Rhizoma cross section and the information of HPLC fingerprinting. Results indicated that, The digitized indexes of color of cross section could reflect the result of fingerprint analysis to some extent.

Objective: To comprehensively evaluate the quality of Radix et Rhizoma Rhei based on gray correlationalanalysis and functional components, and to explore the difference of Radix et Rhizoma Rhei in different genuineproducing areas. Methods: HPLC was utilized to analyze 14 main compositions contained in the samples, includingemodin, rhein, chrysophanol, aloe-emodin, physcion, rheinoside, physcion glucoside, chrysophan, aloe-emodinglucoside, emodin methyl glycoside, sennoside, sennoside B, catechin and gallic acid. Then python 2.7 software wasemployed for gray correlation analysis of functional components closely related to the traditional efficacy of Radix et Rhizoma Rhei. Results: The qualities of Radix et Rhizoma Rhei grow in different areas were different. Tanggute Radix et Rhizoma Rhei grew in Tianzhu Gansu had the best effects of "expelling water retention and attacking the accumulation", and that grew in Yajiang Sichuan had the best effects of "clearing heat and removing toxin". Zhangye Radix et Rhizoma Rhei grew in Lixian Gansu had the best effect of"expelling stasis and unblocking the channels". Conclusion: Patternrecognition has broad prospects in the field of quality evaluation of traditional Chinese medicine. From the clinicalefficacy of traditional Chinese medicine, pattern recognition at the level of efficacy components can provide a new ideafor establishing a more complete and scientific quality evaluation system for traditional Chinese medicine.

This study was aimed to establish an objective and convenient method to evaluate the quality of licorice through the study on correlation between the cross section color and contents of active ingredients of licorice.Therefore,colorimeter was introduced and applied to determinate cross section color of licorice.Meanwhile,contents of five active ingredients of licorice were also determined.HPLC was used to determine liquiritin and glycyrrhizic acid.Colorimetric method was used to determine total saponins.Ultraviolet spectrophotometry was used to determine total flavonoids.Sulphuric acid-phenol colorimetry was used to determine polysaccharides.Correlation between the cross section color and content determination result was analyzed.The results showed that the correlation coefficient of glycyrrhizic acid content and L* was-0.578,P ＜ 0.001,the correlation coefficient with b* was 0.596,P ＜ 0.001;the correlation coefficient of liquiritin content and L* was-0.503,P =0.002,the correlation coefficient with b* was 0.890,P ＜ 0.001;the correlation coefficient of total flavonoids content and L* was-0.729,P ＜ 0.001,the correlation coefficient with b* was 0.724,P ＜ 0.001;the correlation coefficient of polysaccharides content and L* was 0.230,P =0.190,the correlation coefficient with b* was-0.390,P =0.023;the correlation coefficient of total saponins content and L* was-0.411,P =0.016,the correlation coefficient with b* was 0.738,P ＜ 0.001.It was concluded that the cross section color index of licorice has significant correlation with contents of glycyrrhizic acid,liquiritin,total flavonoids and total saponins.There was no significant correlation with content of polysaccharides.It illustrated the close correlation between cross section color of licorice and its active ingredients.Through the digitalized determination on color,contents of chemical composition in licorice can be initially determined or predicted objectively.It provided a new idea and method for the quality evaluation of Chinese herbal medicine.

After the present situation and characteristics of literature novelty assessment of traditional Chinese medicine were described, the importance of characteristic traditional Chinese medicine literacy of literature novelty assessors of traditional Chinese medicine was elaborated, the effect of literature novelty assessors on the literature novelty assessment of traditional Chinese medicine and the training of literature novelty assessors were studied in order to provide reference for other colleges and universities or scientific research institutions.

Objective To prevent unplanned extubation,reduce complications caused by restraint, improve satisfaction degree of patients′relatives,and to lower nurses′work stress.Methods Transparent restraint protection gloves were developed,within which fingers could move freely and with the help of which unplanned extubation could be prevented.A total of 1 00 ICU patients were selected and divided into intervention group and control group randomly,each with 50 cases.Patients in the intervention group used the new type restraint gloves,while patients in the control group used traditional ones.Restraint effects of the two groups were compared.Results Unplanned extubation happened to non patient in the intervention group,while it happened to 6 cases in the control group,Fisher′s exact test was used in comparison between the two groups (P <0.05). Scores of satisfaction degree in the intervention group were (3.1 4 ±0.639)points,while the scores in the control group were (2.20 ±0.756)points (t =6.71 4,P <0.01 );scores of nurses′work stress on accident extubation of patients in the intervention group were (2.1 2 ±0.761 )points,lower than that in the control group with (t =-8.696,P <0.01 ).Conclusions Transparent restraint protection gloves can effectively prevent unplanned extubation,reduce complications caused by restraint,improve satisfaction degree of patients′relatives,and lower nurses′work stress.

Objective Fructus Amomi(Sharen) is derived from the dry ripe fruit of Amomum villosum Lour., A.villosum Lour. var. xanthioides T.L. Wu et Senjen and A.longiligulate T.L.Wu, which is widely utilized for its clinic effects on digestive system. However, Fructus Amomi from different species and habitats, possessing different quality, is difficult to identify. In this study, we aim to develop a simple, rapid and reliable method for authentication of Fructus Amomi. Methods Twenty-five batches of samples of Fructus Amomi were collected and electronic nose was introduced into analyzing their odor with multiple mathematical statistics methods. Na?ve bayes network (NBN), radical basis function (RBF) and random forest (RF) were applied to establish different classifiers while BestFirst+CfsSubsetEval (BC) was used to screen the attributes for searching sensor array with higher contributions. Results Firstly, after attribute-screening via BC, the established discriminative models via NBN, RBF and RF could successfully identify genuine and non-genuine samples, presenting correct judging ratios of 78% and 84% through ten-fold cross validation and external test set validation, respectively. Besides, quantity predictive models were constructed as well. In case of content of bornyl acetate, one of the effective components in Fructus Amomi, values were higher than 3.5 mg/g and lower than 1.8 mg/g with sensor response of 0.04 and 0.03, respectively. Conclusion In this paper, quality discriminative model and quantity predictive model of Fructus Amomi were established via electronic nose and multiple mathematical statistics methods. It indicates that electronic nose could be a promising method for quality evaluation of Chinese material medica.

This study was aimed to identify Chrysanthemi Flosbefore and after sulfur fumigation based on its different odour by the electronic nose technology.It was expected to explore a new method for the Chrysanthemi Flos identification according to the odour.The electronic nose technology was used in the detection of peak response values of Chrysanthemi Flos on sensor array.The principal component analysis (PCA) and 10 machine learning (ML) ways were used in the analysis of response values and establishment of optimized identification models.The results showed that there was a significant difference in the odour between sulfur fumigated Chrysanthemi Flos and non-sulfur fumigated ones.The identification models were successful with high correct judge rate by PCA and 6 ML ways including BF Tree,J48 and Random Tree.It was concluded that the electronic nose technology can be used for the accurate identification of sulfur fumigated Chrysanthemi Flos and non-sulfur fumigated ones.The electronic nose technology combined with multiple ML methods can be introduced in the quality evaluation of Chrysanthemi Flos.It provided more ideas for the application of electronic nose in data mining for traditional Chinese medicine (TCM) studies.