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 To explore the feasibility of long non-coding RNAs (lncRNAs) as biomarkers for radiation-induced intestinal injury. Methods Mice were exposed to 15 Gy of ⁶⁰Co γ-rays to the abdominal area. The pathological changes in intestinal tissues were analyzed at 72 h post-irradiation to confirm the successful establishment of the radiation-induced intestinal injury model. Real-time quantitative PCR was conducted to detect the expression of candidate radiation-responsive lncRNAs in the jejunum, jejunal crypts, colon tissues, and plasma of irradiated mice. Human intestinal epithelial cell line HIEC-6 and human colon epithelial cell line NCM460 were exposed to 0, 5, 10, and 15 Gy of ⁶⁰Co γ-rays. The expression levels of candidate lncRNAs were measured at 4, 24, 48, and 72 h post-irradiation to observe their changes with the irradiation dose. Results Pathological analysis showed that abdominal irradiation with 15 Gy successfully established an acute radiation-induced intestinal injury mouse model. Real-time quantitative PCR showed that Dino, Lncpint, Meg3, Dnm3os, Trp53cor1, Pvt1, and Neat1 were significantly upregulated following the occurrence of radiation-induced intestinal injury (P < 0.05). Among them, Meg3 and Dnm3os in mouse plasma were significantly upregulated (P < 0.05), while Gas5 was significantly downregulated (P < 0.05). In HIEC-6 and NCM460 cells, the expression levels of DINO, MEG3, DNM3OS, and GAS5 showed dose-dependent patterns at certain time points (P < 0.05). Conclusion The lncRNAs encoded by MEG3, DNM3OS, and GAS5 in intestinal epithelial cells are responsive to ionizing radiation. Consistent differential expression changes were detected in mouse plasma and intestinal tissues, indicating their potential as biomarkers for radiation-induced intestinal injury.

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.

This study aims to comprehensively analyze the material basis of toad visceral oil(hereafter referred to as toad oil), and explore the pharmacological effect of toad oil on atopic dermatitis(AD). Ultra-high performance liquid chromatography-linear ion trap/orbitrap high-resolution mass spectrometry(UHPLC-LTQ-Orbitrap-MS) and gas chromatography-mass spectrometry(GC-MS) were employed to comprehensively identify the chemical components in toad oil. The animal model of AD was prepared by the hapten stimulation method. The modeled animals were respectively administrated with positive drug(0.1% hydrocortisone butyrate cream) and low-and high-doses(1%, 10%) of toad oil by gavage. The effect of toad oil on AD was evaluated with the AD score, ear swelling rate, spleen index, and pathological section results as indicators. A total of 99 components were identified by UHPLC-LTQ-Orbitrap-MS, including 14 bufadienolides, 7 fatty acids, 6 alkaloids, 10 ketones, 18 amides, and other compounds. After methylation of toad oil samples, a total of 20 compounds were identified by GC-MS. Compared with the model group, the low-and high-dose toad oil groups showed declined AD score, ear swelling rate, and spleen index, alleviated skin lesions, and reduced infiltrating mast cells. This study comprehensively analyzes the chemical composition and clarifies the material basis of toad oil. Meanwhile, this study proves that toad oil has a good therapeutic effect on AD and is a reserve resource of traditional Chinese medicine for external use in the treatment of AD.
Animals ; Dermatitis, Atopic/immunology* ; Disease Models, Animal ; Mice ; Male ; Gas Chromatography-Mass Spectrometry ; Humans ; Bufonidae ; Oils/administration & dosage* ; Chromatography, High Pressure Liquid ; Female ; Mice, Inbred BALB C

The effect of Huanglian Jiedu Decoction on the intestinal flora of type 2 diabetes mellitus(T2DM) was investigated using 16S rRNA sequencing technology. Sixty rats were randomly divided into a normal group(10 rats) and a modeling group(50 rats). After one week of adaptive feeding, a high-fat diet + streptozotocin was given for modeling, and fasting blood glucose >16.7 mmol·L~(-1) was considered a sign of successful modeling. The modeling group was randomly divided into the model group, high-, medium-, and low-dose groups of Huanglian Jiedu Decoction, and metformin group. After seven days of intragastric treatment, the feces, colon, and pancreatic tissue of each group of rats were collected, and the pathological changes of the colon and pancreatic tissue of each group were observed by hematoxylin-eosin staining. The changes in the intestinal flora structure of each group were observed by the 16S rRNA sequencing method. The results showed that compared with the model group, the high-, medium-, and low-dose of Huanglian Jiedu Decoction reduced fasting blood glucose levels to different degrees and showed no significant changes in body weight. The number of islet cells increased, and intestinal mucosal damage attenuated. Alpha diversity analysis revealed that Huanglian Jiedu Decoction reduced the abundance and diversity of intestinal flora in rats with T2DM; at the phylum level, low-and mediam-dose of Huanglian Jiedu Decoction reduced the abundance of Bacteroidota, Proteobacteria, and Desulfobacterota and increased the abundance of Firmicute and Bacteroidota/Firmicutes, while the high-dose of Huanglian Jiedu Decoction increased the relative abundance of Proteobacteria and Bacteroidota/Firmicutes ratio, and decreaseal the relative; abundance of Firmicute; at the genus level, Huanglian Jiedu Decoction increased the relative abundance of Allobaculum, Blautia, and Lactobacillus; LEfse analysis revealed that the biomarker of low-and medium-dose groups of Huanglian Jiedu Decoction was Lactobacillus, and the structure of the intestinal flora of the low-dose group of Huanglian Jiedu Decoction was highly similar to that of the metformin group. PICRUSt2 function prediction revealed that Huanglian Jiedu Decoction mainly affected carbohydrate and amino acid metabolic pathways. It suggested that Huanglian Jiedu Decoction could reduce fasting blood glucose and increase the number of islet cells in rats with T2DM, and its mechanism of action may be related to increasing the abundance of short-chain fatty acid-producing strains and Lactobacillus and affecting carbohydrate and amino acid metabolic pathways.
Animals ; Drugs, Chinese Herbal/administration & dosage* ; Diabetes Mellitus, Type 2/metabolism* ; Gastrointestinal Microbiome/drug effects* ; Rats ; Male ; Rats, Sprague-Dawley ; Humans ; Bacteria/drug effects* ; Blood Glucose/metabolism*

The ultra-high performance liquid chromatography( UPLC) characteristic fingerprints of Angelica dahurica and A. dahurica var. formosana were established. The compounds corresponding to common peaks were identified by ultra-high performance liquid chromatography with quadrupole time-of-flight mass spectrometry( UPLC-Q-TOF-MS/MS). The results were combined with chemometrics and quantitative analysis of multi-components with a single-marker method(QAMS) to study the quality control of A. dahurica and A. dahurica var. formosana. The separation was performed on a Titank C_(18) column(2. 1 mm × 150 mm, 1. 8 μm)with a mobile phase of acetonitrile-0. 2% formic acid at a flow rate of 0. 3 m L·min~(-1). The column temperature was 35 ℃ and the injection volume was 1. 2 μL. Seven batches of A. dahurica and 11 batches of A. dahurica var. formosana were injected and analyzed. The UPLC characteristic fingerprints of A. dahurica and A. dahurica var. formosana were established according to the Similarity Evaluation System for Chromatographic Fingerprint of Traditional Chinese Medicine( version 2012), and 19 and 20 characteristic peaks were matched respectively. The common peaks were identified by reference substance comparison and UPLC-Q-TOF-MS/MS. Cluster analysis(CA), principal component analysis(PCA), and orthogonal partial least squares-discriminant analysis(OPLS-DA)were performed to analyze the chemical pattern recognition of A. dahurica and A. dahurica var. formosana. The results of CA and PCA could distinguish Angelicae Dahuricae Radix from different producing areas, and the differential quality markers of A. dahurica and A. dahurica var. formosana were obtained by OPLS-DA. With imperatorin as the internal reference, the relative correction factors of oxypeucedanin hydrate, byakangelicin, bergapten, isopimpinellin, oxypeucedanin, and isoimperatorin were 1. 310, 1. 069, 0. 729, 0. 633, 0. 753, and 1. 010, respectively. There was no significant difference between the QAMS and external standard method(ESM)results of each component, indicating that the QAMS established with imperatorin as the internal reference was accurate and reliable. The characteristic fingerprints, chemometrics, and QAMS established in this study can quickly and efficiently control the quality of A. dahurica and A. dahurica var. formosana.
Quality Control ; Chromatography, High Pressure Liquid/methods* ; Drugs, Chinese Herbal/chemistry* ; Angelica/chemistry* ; Chemometrics/methods* ; Tandem Mass Spectrometry/methods* ; Principal Component Analysis

This study aims to explore the effects and action mechanisms of the active ingredients in Buyang Huanwu Decoction(BYHWD), namely tetramethylpyrazine(TMP) and hydroxy-safflor yellow A(HSYA), on oxygen-glucose deprivation/reglucose-reoxygenation(OGD/R)-induced inflammation and oxidative stress of microglia(MG). Network pharmacology was used to screen the effective monomer ingredients of BYHWD and determine the safe concentration range for each component. Inflammation and oxidative stress models were established to further screen the best ingredient combination and optimal concentration ratio with the most effective anti-inflammatory and antioxidant effects. OGD/R BV2 cell models were constructed, and BV2 cells in the logarithmic growth phase were divided into a normal group, a model group, an HSYA group, a TMP group, and an HSYA + TMP group. Enzyme-linked immunosorbent assay(ELISA) was used to detect the levels of inflammatory cytokines such as interleukin-1β(IL-1β), tumor necrosis factor-α(TNF-α), and interleukin-6(IL-6). Oxidative stress markers, including superoxide dismutase(SOD), nitric oxide(NO), and malondialdehyde(MDA), were also measured. Western blot was used to analyze the protein expression of both inflammation-related pathway [Toll-like receptor 4(TLR4)/nuclear factor-kappa B(NF-κB)] and oxidative stress-related pathway [nuclear factor erythroid 2-related factor 2(Nrf2)/heme oxygenase-1(HO-1)]. Immunofluorescence was used to assess the expression of proteins such as inducible nitric oxide synthase(iNOS) and arginase-1(Arg-1). The most effective ingredients for anti-inflammatory and antioxidant effects in BYHWD were TMP and HSYA. Compared to the normal group, the model group showed significantly increased levels of IL-1β, TNF-α, IL-6, NO, and MDA, along with significantly higher protein expression of NF-κB, TLR4, Nrf2, and HO-1 and significantly lower SOD levels. The differences between the two groups were statistically significant. Compared to the model group, both the HSYA group and the TMP group showed significantly reduced levels of IL-1β, TNF-α, IL-6, NO, and MDA, lower expression of NF-κB and TLR4 proteins, higher levels of SOD, and significantly increased protein expression of Nrf2 and HO-1. Additionally, the expression of the M1-type MG marker iNOS was significantly reduced, while the expression of the M2-type MG marker Arg-1 was significantly increased. The results of the HSYA group and the TMP group had statistically significant differences from those of the model group. Compared to the HSYA group and the TMP group, the HSYA + TMP group showed further significant reductions in IL-1β, TNF-α, IL-6, NO, and MDA levels, along with significant reductions in NF-κB and TLR4 protein expression, an increase in SOD levels, and elevated Nrf2 and HO-1 protein expression. Additionally, the expression of the M1-type MG marker iNOS was reduced, while the M2-type MG marker Arg-1 expression increased significantly in the HSYA + TMP group compared to the TMP or HSYA group. The differences in the results were statistically significant between the HSYA + TMP group and the TMP or HSYA group. The findings indicated that the combined use of HSYA and TMP, the active ingredients of BYHWD, can effectively inhibit OGD/R-induced inflammation and oxidative stress of MG, showing superior effects compared to the individual use of either component.
Oxidative Stress/drug effects* ; Drugs, Chinese Herbal/pharmacology* ; Animals ; Mice ; Glucose/metabolism* ; Cell Line ; Inflammation/genetics* ; Oxygen/metabolism* ; Pyrazines/pharmacology* ; Microglia/metabolism* ; NF-E2-Related Factor 2/immunology* ; NF-kappa B/immunology* ; Toll-Like Receptor 4/immunology* ; Anti-Inflammatory Agents/pharmacology* ; Humans