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.

Guided by the concept of quality by design(QbD), this study optimizes the calcination and quenching process of calcined Magnetitum and establishes the XRD characteristic spectra of calcined Magnetitum, providing a scientific basis for the formulation of quality standards. Based on the processing methods and quality requirements of Magnetitum in the Chinese Pharmacopoeia, the critical process parameters(CPPs) identified were calcination temperature, calcination time, particle size, laying thickness, and the number of vinegar quenching cycles. The critical quality attributes(CQAs) included Fe mass fraction, Fe~(2+) dissolution, and surface color. The weight coefficients were determined by combining Analytic Hierarchy Process(AHP) and the criteria importance though intercrieria correlation(CRITIC) method, and the calcination process was optimized using orthogonal experimentation. Surface color was selected as a CQA, and based on the principle of color value, the surface color of calcined Magnetitum was objectively quantified. The vinegar quenching process was then optimized to determine the best processing conditions. X-ray diffraction(XRD) was used to establish the characteristic spectra of calcined Magnetitum, and methods such as similarity evaluation, cluster analysis, and orthogonal partial least squares-discriminant analysis(OPLS-DA) were used to evaluate the quality of the spectra. The optimized calcined Magnetitum preparation process was found to be calcination at 750 ℃ for 1 h, with a laying thickness of 4 cm, a particle size of 0.4-0.8 cm, and one vinegar quenching cycle(Magnetitum-vinegar ratio 10∶3), which was stable and feasible. The XRD characteristic spectra analysis method, featuring 9 common peaks as fingerprint information, was established. The average correlation coefficient ranged from 0.839 5-0.988 1, and the average angle cosine ranged from 0.914 4 to 0.995 6, indicating good similarity. Cluster analysis results showed that Magnetitum and calcined Magnetitum could be grouped together, with similar compositions. OPLS-DA discriminant analysis identified three key characteristic peaks, with Fe_2O_3 being the distinguishing component between the two. The final optimized processing method is stable and feasible, and the XRD characteristic spectra of calcined Magnetitum was initially established, providing a reference for subsequent quality control and the formulation of quality standards for calcined Magnetitum.
X-Ray Diffraction/methods* ; Drugs, Chinese Herbal/chemistry* ; Quality Control ; Particle Size

Aromatic traditional Chinese medicine(TCM) has played an important role against epidemics and viruses, and volatile components are the main components that exert the pharmacological effects of aromatic TCM. By screening the related monomer components in aromatic TCM against epidemic and viruses and analyzing and endowing TCM with medicinal properties based on its clinical application and pharmacological research according to the theoretical thinking of TCM, the key technical issues of compatibility of TCM monomer components were solved from a theoretical perspective, providing new ideas and methods for screening raw materials and formulas for the development of new TCM drugs. Based on the conditions of antiviral activity, clinical application foundation, definite therapeutic effect, and high safety, a gradient screening of aromatic TCM was carried out. Firstly, 30 aromatic TCM were screened from anti-epidemic literature and clinical trial formulas, and seven volatile monomers were further screened from them. Then, four monomer components with significant effects, namely patchouli alcohol, carvacrol, p-cymene, and eucalyptol were screened. By adopting the "four-step method for a systematic study of TCM properties", the four monomer components were endowed with medicinal properties, and compatibility and combination studies were conducted to explore the theoretical basis of monomer formulas and form monomer formulas guided by TCM theory. The screening results of volatile monomers in aromatic TCM against viral pneumonia included patchouli alcohol, carvacrol, p-cymene, and eucalyptol. The medicinal properties and compatibility theory of volatile monomer components in TCM were explored. Patchouli alcohol was the main herb, with a cool and pungent nature. It entered the lung meridian to dispel evil Qi and has the effects of aromatization, detoxification, and epidemic prevention. Carvacrol was a minister drug with a cool and pungent taste. It had the effects of aromatizing, moistening, and dissolving the exterior, as well as strengthening the spleen and stomach. p-Cymene was an adjunctive medicine with a mild and pungent nature. It entered the lungs and kidneys and had the effects of aromatic purification, cough relief, and asthma relief. Eucalyptol was also an adjunctive medicine with a pungent and warm taste. It had the functions of aromatic purification, cough relief, phlegm reduction, and pain relief. The combination of the four medicines had the effects of aromatizing, moistening, detoxifying, and epidemic prevention, as well as relieving cough and asthma and strengthening the spleen and stomach. They were used to treat viral pneumonia caused by upper respiratory tract viral infections, with symptoms such as chest tightness, cough, wheezing, fatigue, nasal congestion, runny nose, nausea, and vomiting. This study has laid a literature and theoretical foundation for further drug efficacy verification experiments, compatibility efficacy experiments, and subsequent product development and clinical applications, and it serves as an innovative practice that combines literature research, theoretical research, experimental research, and clinical practice to develop new products.
Drugs, Chinese Herbal/therapeutic use* ; Antiviral Agents/pharmacology* ; Humans ; Pneumonia, Viral/virology* ; Medicine, Chinese Traditional ; Volatile Organic Compounds/pharmacology* ; Animals

This paper aims to investigate the influence of eucalyptol on the biological effects of spleen cold and spleen heat syndromes in rats and its regulation of transient receptor potential vanilloid 1(TRPV1), transient receptor potential melastatin 8(TRPM8), and uncoupling protein 1(UCP1), so as to explore the cold-heat properties of eucalyptol. Rats were randomly divided into groups as follows: blank group, spleen cold syndrome model group, spleen cold syndrome+Atractylodis Rhizoma group, spleen cold syndrome + low-dose eucalyptol group, and spleen cold syndrome+high-dose eucalyptol group, as well as blank group, spleen heat syndrome model group, spleen heat syndrome+Coptidis Rhizoma group, spleen heat syndrome + low-dose eucalyptol group, and spleen heat syndrome + high-dose eucalyptol group. Spleen cold and spleen heat syndromes were induced by disorders of hunger and satiety combined with bitter cold drugs, as well as a high-fat diet combined with liquor. Except for the blank and model groups, the other groups were administered once a day during the modeling process for 14 consecutive days. The general condition and body weight of rats in each group were observed, and the histopathological morphology of the gastric antrum and small intestine was observed by hematoxylin-eosin(HE) staining. The contents of cyclic adenosine monophosphate(cAMP), cyclic guanosine monophosphate(cGMP), triiodothyronine(T3), thyroxine(T4), Na~+-K~+-ATPase, total cholesterol(TC), triglyceride(TG), gastrin(GAS), motilin(MTL), D-xylose, and other related indices were detected in rats. The expression levels of TRPV1, TRPM8, and UCP1 in small intestine tissue of rats with spleen cold syndrome were detected. The results showed that eucalyptol had a certain degree of improvement in the overall state and body weight of rats with spleen cold syndrome. Compared with the spleen cold syndrome model group, high-dose eucalyptol significantly increased the levels of serum cAMP, cAMP/cGMP, TG, and TC in rats with spleen cold syndrome(P<0.05, P<0.01), decreased the content of cGMP, and significantly elevated the levels of gastrointestinal function-related indicators GAS, MTL, and D-xylose(P<0.05, P<0.01). Low-dose eucalyptol significantly increased the level of cAMP/cGMP in the serum and Na~+-K~+-ATPase levels in hepatic tissue(P<0.05, P<0.01), and significantly increased the levels of GAS and D-xylose(P<0.01). Eucalyptol showed similar effects to Atractylodis Rhizoma with a warm nature on rats with spleen cold syndrome. Compared with the spleen heat syndrome model group, the high-dose and low-dose eucalyptol groups showed a trend of increase in gastrointestinal indicators, with no significant changes in other indicators. In addition, high-dose eucalyptol increased the expression of TRPV1 and UCP1 and decreased the expression of TRPM8 in the small intestine tissue of rats with spleen cold syndrome. Eucalyptol could affect the cyclic nucleotide and material energy metabolism levels of rats with spleen cold syndrome and had a certain improvement effect on their gastrointestinal digestion and absorption function, thereby improving spleen cold syndrome. Eucalyptol had no significant improvement effect on rats with spleen heat syndrome, suggesting that eucalyptol may have a warm nature and regulate spleen meridians. It is speculated that eucalyptol may exhibit its medicinal properties by activating the TRPV1 pathway, promoting the expression of UCP1, and inhibiting the TRPM8 channel.
Animals ; Rats ; Spleen/metabolism* ; Male ; TRPV Cation Channels/genetics* ; Rats, Sprague-Dawley ; Eucalyptol/administration & dosage* ; TRPM Cation Channels/genetics* ; Uncoupling Protein 1/genetics* ; Humans ; Drugs, Chinese Herbal/administration & dosage* ; Cold Temperature ; Cyclic GMP/metabolism*

This paper aims to study the effect of p-cymene on mice with deficiency-cold syndrome induced by hydrocortisone and deficiency-heat syndrome induced by dexamethasone and explore the medicinal properties and mechanism of p-cymene with mild and warm nature based on the dominant characteristics of the two-way applicable conditions of mild drugs. A total of 80 KM mice were randomly divided into blank group, deficiency-cold syndrome model group, deficiency-cold syndrome + ginseng group, and deficiency-cold syndrome + low-dose and high-dose p-cymene groups, as well as blank group, deficiency-heat syndrome model group, deficiency-heat syndrome + American ginseng group, and deficiency-heat syndrome + low-dose and high-dose p-cymene groups. Hydrocortisone and dexamethasone solution were intragastrically administered for 14 consecutive days to prepare deficiency-cold syndrome and deficiency-heat syndrome models. Except for the blank group and the model group intragastrically administered with normal saline, the other groups were intragastrically administrated with drugs for 14 days. The levels of cyclic adenosine monophosphate(cAMP), cyclic guanosine monophosphate(cGMP), triiodothyronine(T3), thyroxine(T4), total cholesterol(TC), triglyceride(TG), immunoglobin G(IgG), and immunoglobin M(IgM) in serum, as well as the activity of Na~+-K~+-ATPase in liver tissue were detected. The expression of transient receptor potential melastatin 8(TRPM8), transient receptor potential vanilloid 1(TRPV1), and uncoupling protein 1(UCP1) in brown adipose tissue of deficiency-cold syndrome model after intervention with p-cymene was studied. The results showed that p-cymene could effectively improve the levels of cAMP, cAMP/cGMP, TC, IgM, and IgG in serum and the activity of Na~+-K~+-ATPase in liver tissue of mice with deficiency-cold syndrome and reduce the content of cGMP. The effects on T3, T4, and TG were not statistically significant. At the same time, p-cymene could reduce the levels of cAMP, cAMP/cGMP, and T4 in serum and the activity of Na~+-K~+-ATPase in liver tissue of mice with deficiency-cold syndrome and increase the levels of cGMP, IgM, and IgG, and it had no effect on T3, TC, and TG. In addition, p-cymene could up-regulate the expression of TRPV1 and UCP1 in brown fat of mice with deficiency-cold syndrome and down-regulate the expression of TRPM8. In summary, p-cymene could significantly regulate the syndrome indexes of mice with deficiency-cold syndrome, and some indexes of mice with deficiency-heat syndrome could be improved, but the effects on lipid metabolism and energy metabolism indexes were not obvious, indicating that the regulation effect of p-cymene on deficiency-cold syndrome model was more prominent and that the medicinal properties of p-cymene were mild and warm. The regulation of TRPV1/TRPM8/UCP1 channel expression may be the molecular biological mechanism of p-cymene with mild and warm nature affecting the energy metabolism of the body.
Animals ; Cymenes ; Mice ; Drugs, Chinese Herbal/administration & dosage* ; Male ; Disease Models, Animal ; Humans ; Cyclic AMP/metabolism* ; Monoterpenes/administration & dosage* ; Liver/metabolism* ; Cyclic GMP/metabolism* ; TRPV Cation Channels/genetics* ; Uncoupling Protein 1/genetics*

Retrieving keyframes most relevant to text from small intestine videos with given labels can efficiently and accurately locate pathological regions. However, training directly on raw video data is extremely slow, while learning visual representations from image-text datasets leads to computational inconsistency. To tackle this challenge, a small bowel video keyframe retrieval based on multi-modal contrastive learning (KRCL) is proposed. This framework fully utilizes textual information from video category labels to learn video features closely related to text, while modeling temporal information within a pretrained image-text model. It transfers knowledge learned from image-text multimodal models to the video domain, enabling interaction among medical videos, images, and text data. Experimental results on the hyper-spectral and Kvasir dataset for gastrointestinal disease detection (Hyper-Kvasir) and the Microsoft Research video-to-text (MSR-VTT) retrieval dataset demonstrate the effectiveness and robustness of KRCL, with the proposed method achieving state-of-the-art performance across nearly all evaluation metrics.
Humans ; Video Recording ; Intestine, Small/diagnostic imaging* ; Machine Learning ; Image Processing, Computer-Assisted/methods* ; Algorithms

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.