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: To investigate the characteristics of gut microbiota changes in patients with acute myeloid leukemia (AML) undergoing induction chemotherapy and to explore the relationship between infectious complications and gut microbiota. METHODS: Fecal samples were collected from 37 newly diagnosed AML patients at four time points: before induction chemotherapy, during chemotherapy, during the neutropenic phase, and during the recovery phase. Metagenomic sequencing was used to analyze the dynamic changes in gut microbiota. Correlation analyses were conducted to assess the relationship between changes in gut microbiota and the occurrence of infectious complications. RESULTS: During chemotherapy, the gut microbiota α-diversity (Shannon index) of AML patients exhibited significant fluctuations. Specifically, the diversity decreased significantly during induction chemotherapy, further declined during the neutropenic phase (P < 0.05, compared to baseline), and gradually recovered during the recovery phase, though not fully returning to baseline levels.The abundances of beneficial bacteria, such as Firmicutes and Bacteroidetes, gradually decreased during chemotherapy, whereas the abundances of opportunistic pathogens, including Enterococcus, Klebsiella, and Escherichia coli, progressively increased.Analysis of the dynamic changes in gut microbiota of seven patients with bloodstream infections revealed that the bloodstream infection pathogens could be detected in the gut microbiota of the corresponding patients, with their abundance gradually increasing during the course of infection. This finding suggests that bloodstream infections may be associated with opportunistic pathogens originating from the gut microbiota.Compared to non-infected patients, the baseline samples of infected patients showed a significantly lower relative abundance of Bacteroidetes (P < 0.05). Regression analysis indicated that Bacteroidetes abundance is an independent predictive factor for infectious complications (P < 0.05, OR =13.143). CONCLUSION During induction chemotherapy in AML patients, gut microbiota α-diversity fluctuates significantly, and the abundance of opportunistic pathogens increase, which may be associated with bloodstream infections. Patients with lower baseline Bacteroidetes abundance are more prone to infections, and its abundance can serve as an independent predictor of infectious complications.
Humans ; Gastrointestinal Microbiome ; Leukemia, Myeloid, Acute/microbiology* ; Induction Chemotherapy ; Feces/microbiology* ; Male ; Female ; Middle Aged

OBJECTIVE: To evaluate the dynamic changes of glucocorticoid (GC) dose and the feasibility of GC discontinuation in rheumatoid arthritis (RA) patients under the background of Chinese medicine (CM). METHODS: This multicenter retrospective cohort study included 1,196 RA patients enrolled in the China Rheumatoid Arthritis Registry of Patients with Chinese Medicine (CERTAIN) from September 1, 2019 to December 4, 2023, who initiated GC therapy. Participants were divided into the Western medicine (WM) and integrative medicine (IM, combination of CM and WM) groups based on medication regimen. Follow-up was performed at least every 3 months to assess dynamic changes in GC dose. Changes in GC dose were analyzed by generalized estimator equation, the probability of GC discontinuation was assessed using Kaplan-Meier curve, and predictors of GC discontinuation were analyzed by Cox regression. Patients with <12 months of follow-up were excluded for the sensitivity analysis. RESULTS: Among 1,196 patients (85.4% female; median age 56.4 years), 880 (73.6%) received IM. Over a median 12-month follow-up, 34.3% (410 cases) discontinued GC, with significantly higher rates in the IM group (40.8% vs. 16.1% in WM; P<0.05). GC dose declined progressively, with IM patients demonstrating faster reductions (median 3.75 mg vs. 5.00 mg in WM at 12 months; P<0.05). Multivariate Cox analysis identified age <60 years [P<0.001, hazard ratios (HR)=2.142, 95% confidence interval (CI): 1.523-3.012], IM therapy (P=0.001, HR=2.175, 95% CI: 1.369-3.456), baseline GC dose ⩽7.5 mg (P=0.003, HR=1.637, 95% CI: 1.177-2.275), and absence of non-steroidal anti-inflammatory drugs use (P=0.001, HR=2.546, 95% CI: 1.432-4.527) as significant predictors of GC discontinuation. Sensitivity analysis (545 cases) confirmed these findings. CONCLUSIONS RA patients receiving CM face difficulties in following guideline-recommended GC discontinuation protocols. IM can promote GC discontinuation and is a promising strategy to reduce GC dependency in RA management. (Trial registration: ClinicalTrials.gov, No. NCT05219214).
Adult ; Aged ; Female ; Humans ; Male ; Middle Aged ; Arthritis, Rheumatoid/drug therapy* ; Glucocorticoids/therapeutic use* ; Medicine, Chinese Traditional ; Retrospective Studies

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: To investigate the effect of manual acupuncture manipulations (MAMs) on subcutaneous muscle tissue, by developing quantitative models of "lifting and thrusting" and "twisting and rotating", based on machine learning techniques. METHODS: A depth camera was used to capture the acupuncture operator's hand movements during "lifting and thrusting" and "twisting and rotating" of needle. Simultaneously, the ultrasound imaging was employed to record the muscle tissue responses of the participants. Amplitude and angular features were extracted from the movement data of operators, and muscle fascicle slope features were derived from the data of ultrasound images. The dynamic time warping barycenter averaging algorithm was adopted to align the dual-source data. Various machine learning techniques were applied to build quantitative models, and the performance of each model was compared. The most optimal model was further analyzed for its interpretability. RESULTS: Among the quantitative models built for the two types of MAMs, the random forest model demonstrated the best performance. For the quantitative model of the "lifting and thrusting" technique, the coefficient of determination (R²) was 0.825. For the "twisting and rotating" technique, R² reached 0.872. CONCLUSION Machine learning can be used to effectively develop the models and quantify the effects of MAMs on subcutaneous muscle tissue. It provides a new perspective to understand the mechanism of acupuncture therapy and lays a foundation for optimizing acupuncture technology and designing personalized treatment regimen in the future.
Humans ; Acupuncture Therapy/methods* ; Machine Learning ; Male ; Adult ; Female ; Subcutaneous Tissue/diagnostic imaging* ; Young Adult

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*