Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Objective: Machine learning (ML) has been reported to have better predictive capability than traditional statistical techniques. The aim of this study was to assess the efficacy of ML algorithms and logistic regression (LR) for predicting depressive symptoms during the COVID-19 pandemic. Methods: Analyses were carried out in a national cross-sectional study involving 21,916 participants. The ML algorithms in this study included random forest (RF), support vector machine (SVM), neural network (NN), and gradient boosting machine (GBM) methods. The performance indices were sensitivity, specificity, accuracy, precision, F1-score, and area under the receiver operating characteristic curve (AUC). Results: LR and NN had the best performance in terms of AUCs. The risk of overfitting was found to be negligible for most ML models except for RF, and GBM obtained the highest sensitivity, specificity, accuracy, precision, and F1-score. Therefore, LR, NN, and GBM models ranked among the best models. Conclusion Compared with ML models, LR model performed comparably to ML models in predicting depressive symptoms and identifying potential risk factors while also exhibiting a lower risk of overfitting.

Natural products are important sources for the discovery of anti-tumor drugs. Evodiamine is the main alkaloid component of the traditional Chinese herb Wu-Chu-Yu, and it has weak antitumor activity. In recent years, a number of highly active antitumor candidates have been discovered with a significant progress. This article reviews the research progress of evodiamine-based antitumor drug design strategies, in order to provide reference for the development of new drugs with natural products as leads.

Objective The volume and cortical thickness of gray matter in patients with multiple sclerosis (MS) and neuromyelitis optica (NMO) were compared and analyzed by voxel⁃based morphometry (VBM) and surface⁃based morphometry (SBM), and the differences in the structural changes of gray matter in the two diseases were discussed. Methods A total of 21 MS patients, 16 NMO patients and 19 healthy controls were scanned by routine MRI sequence. The data were processed and analyzed by VBM and SBM method based on the statistical parameter tool SPM12 of Matlab2014a platform and the small tool CAT12 under SPM12. Results Compared with the normal control group (NC), after Gaussian random field (GRF) correction, the gray matter volume in MS group was significantly reduced in left superior occipital, left cuneus, left calcarine, left precuneus, left postcentral, left central paracentral lobule, right cuneus, left middle frontal, left superior frontal and left superior medial frontal (P<0. 05). After family wise error (FWE) correction, the thickness of left paracentral, left superiorfrontal and left precuneus cortex in MS group was significantly reduced (P<0. 05). Compared with the NC group, after GRF correction, the gray matter volume in the left postcentral, left precentral, left inferior parietal, right precentral and right middle frontal in NMO group was significantly increased (P<0. 05). In NMO group, the volume of gray matter in left middle occipital, left superior occipital, left inferior temporal, right middle occipital, left superior frontal orbital, right middle cingulum, left anterior cingulum, right angular and left precuneus were significantly decreased (P<0. 05). Brain regions showed no significant differences in cortical thickness between NMO groups after FWE correction. Compared with the NMO group, after GRF correction, the gray matter volume in the right fusiform and right middle frontal in MS group was increased significantly(P<0. 05). In MS group, the gray matter volume of left thalamus, left pallidum, left precentral, left middle frontal, left middle temporal, right pallidum, left inferior parietal and right superior parietal were significantly decreased (P<0. 05). After FWE correction, the thickness of left inferiorparietal, left superiorparietal, left supramarginal, left paracentral, left superiorfrontal and left precuneus cortex in MS group decreased significantly (P<0. 05). Conclusion The atrophy of brain gray matter structure in MS patients mainly involves the left parietal region, while NMO patients are not sensitive to the change of brain gray matter structure. The significant difference in brain gray matter volume between MS patients and NMO patients is mainly located in the deep cerebral nucleus mass.

The imprint desorption electrospray photoionization mass spectrometry was employed to locally image the spatial distribution of chemical components in dried tobacco leaves after initial curing. The relative content distribution of different chemical components was obtained in tobacco leaves. The application of imprinting method could transfer tobacco internal compounds to the surface of porous polytetrafluoroethylene plate,which realized the detection and visual analysis of tobacco internal substances. Besides,the imprint desorption electrospray ionization/post-photoionization (Imprint DESI/PI) mass spectrometry imaging technique had the advantages of non-polarity discrimination,soft ionization and high ionization efficiency for plant samples,and could simultaneously detect and image rich compounds in tobacco samples. A total of 40 kinds of chemical components including alkaloids,amino acids,sugars,acids,ketones and phenols were identified based on high resolution mass spectrometry. The results showed that the representative chemical components of tobacco,such as alkaloids,amino acids and sugars,were mainly distributed near the leaf tip from the vertical analysis and at the left and right leaf edges from the horizontal analysis. Amadori compound (1-Deoxy-1-L-proline-d-fructose) was detected,and the content of Amadori was found to be consistent with that of free amino acid (proline). In addition,the technique was further used to study the climate spot disease area of tobacco,and it was found that the compounds had specific distribution in the climate spot area,which further proved the superiority of this method in studying the growth stress of tobacco leaves.

Objective To investigate the distribution patterns of traditional Chinese medicine(TCM)constitution in 959 patients with endometriosis(EMs).Methods From January 2019 to November 2019,959 EMs patients were selected from Guang'anmen Hospital of China Academy of Chinese Medical Sciences,Beijing Obstetrics and Gynecology Hospital Affiliated to Capital Medical University,Beijing Hospital,Dongfang Hospital of Beijing University of Chinese Medicine,Beijing Friendship Hospital Affiliated to Capital Medical University,and Fuxing Hospital Affiliated to Capital Medical University.The general clinical information of the patients was recorded and then the TCM constitution was identified.After that,the correlation of TCM constitution distribution with concurrent constitution and the relationship of TCM constitution distribution with age and the complication of dysmenorrhea were analyzed.Results(1)The constitution types of EMs patients listed in descending order of the proportion were yang deficiency constitution(65.1％,624/959),qi stagnation constitution(58.4％,560/959),qi deficiency constitution(52.8％,506/959),blood stasis constitution(44.2％,424/959),phlegm-damp constitution(42.5％,408/959),damp-heat constitution(41.9％,402/959),yin deficiency constitution(39.6％,380/959),balanced constitution(26.8％,257/959),and inherited special constitution(16.6％,159/959).Among the patients,there were fewer patients with single constitution,accounting for 20.2％(194/959),and most of them had concurrent constitution types,accounting for 79.8％(765/959).(2)The association rule mining based on Apriori algorithm obtained 33 related rules.The concurrent constitution types of qi deficiency-yang deficiency,blood stasis-yang deficiency,and blood stasis-qi stagnation were the association rules with high confidence.(3)Compared with patients aged 35 years and below,the patients over 35 years old were predominated by high proportion of blood stasis constitution(P＜0.05).Compared with patients without dysmenorrhea,the patients with dysmenorrhea had the increased proportion of biased constitutions and the decreased proportion of balanced constitution(P＜0.05 or P＜0.01).Conclusion Yang deficiency constitution,qi stagnation constitution,qi deficiency constitution and blood stasis constitution are the high-risk constitution types of EMs patients.The concurrent constitution types are commonly seen in EMs patients,which are more common than single biased constitution.Management of EMs patients with the methods of warming yang,relieving stagnation,benefiting qi and activating blood will be helpful for correcting the biased constitutions in time and preventing disease progression,which will achieve the preventive treatment efficacy through TCM constitution correction.

Objective To observe the clinical effect of acupuncture combined with Shenqi Huoxue Decoction in the treatment of adenomyosis of qi deficiency and blood stasis type.Methods Seventy patients with adenomyosis of qi deficiency and blood stasis type were randomly divided into observation group and control group,35 cases in each group.The control group was treated with Levonorgestrel-releasing intrauterine system,and the observation group was treated with acupuncture combined with Shenqi Huoxue Decoction on the basis of the treatment of the control group.One menstrual cycle was a course of treatment,and the treatment lasted for three courses.After 3 months of treatment,the clinical efficacy of the two groups was evaluated,and the changes of Endometriosis Health Profile-5(EHP-5)score,serum superoxide dismutase(SOD)and catalase(CAT)were observed in the two groups before and after treatment.The changes of serum carbohydrate antigen CA125,carbohydrate antigen 199(CA199)and human epididymis protein 4(HE4)levels were compared before and after treatment between the two groups.Results(1)The total effective rate was 97.14％(34/35)in the observation group and 77.14％(27/35)in the control group.The clinical efficacy of the observation group was superior to that of the control group,and the difference was statistically significant(P＜0.05).(2)After treatment,the levels of serum CA125,CA199 and HE4 in the two groups were significantly improved(P＜0.05),and the improvement of serum CA1 25,CA199 and HE4 levels in the observation group was significantly superior to that in the control group,the difference was statistically significant(P＜0.05).(3)After treatment,the levels of serum SOD and CAT in the two groups were significantly improved(P＜0.05),and the improvement of serum SOD and CAT levels in the observation group was significantly superior to that in the control group,the difference was statistically significant(P＜0.05).(4)After treatment,the EHP-5 score of quality of life in the two groups was significantly improved(P＜0.05),and the EHP-5 score of quality of life in the observation group was significantly superior to that in the control group,the difference was statistically significant(P＜0.05).Conclusion Acupuncture combined with Shenqi Huoxue Decoction in the treatment of adenomyosis of qi deficiency and blood stasis type can significantly improve the clinical symptoms of patients,regulate the levels of SOD and CAT,so as to improve the quality of life of patients,and the curative effect is significant.