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.

ObjectiveMagnetoencephalography (MEG), a non-invasive neuroimaging technique, meticulously captures the magnetic fields emanating from brain electrical activity. Compared with MEG based on superconducting quantum interference devices (SQUID), MEG based on optically pump magnetometer (OPM) has the advantages of higher sensitivity, better spatial resolution and lower cost. However, most of the current studies are clinical studies, and there is a lack of animal studies on MEG based on OPM technology. Pain, a multifaceted sensory and emotional phenomenon, induces intricate alterations in brain activity, exhibiting notable sex differences. Despite clinical revelations of pain-related neuronal activity through MEG, specific properties remain elusive, and comprehensive laboratory studies on pain-associated brain activity alterations are lacking. The aim of this study was to investigate the effects of inflammatory pain (induced by Complete Freund’s Adjuvant (CFA)) on brain activity in a rat model using the MEG technique, to analysis changes in brain activity during pain perception, and to explore sex differences in pain-related MEG signaling. MethodsThis study utilized adult male and female Sprague-Dawley rats. Inflammatory pain was induced via intraplantar injection of CFA (100 μl, 50% in saline) in the left hind paw, with control groups receiving saline. Pain behavior was assessed using von Frey filaments at baseline and 1 h post-injection. For MEG recording, anesthetized rats had an OPM positioned on their head within a magnetic shield, undergoing two 15-minute sessions: a 5-minute baseline followed by a 10-minute mechanical stimulation phase. Data analysis included artifact removal and time-frequency analysis of spontaneous brain activity using accumulated spectrograms, generating spectrograms focused on the 4-30 Hz frequency range. ResultsMEG recordings in anesthetized rats during resting states and hind paw mechanical stimulation were compared, before and after saline/CFA injections. Mechanical stimulation elevated alpha activity in both male and female rats pre- and post-saline/CFA injections. Saline/CFA injections augmented average power in both sexes compared to pre-injection states. Remarkably, female rats exhibited higher average spectral power 1 h after CFA injection than after saline injection during resting states. Furthermore, despite comparable pain thresholds measured by classical pain behavioral tests post-CFA treatment, female rats displayed higher average power than males in the resting state after CFA injection. ConclusionThese results imply an enhanced perception of inflammatory pain in female rats compared to their male counterparts. Our study exhibits sex differences in alpha activities following CFA injection, highlighting heightened brain alpha activity in female rats during acute inflammatory pain in the resting state. Our study provides a method for OPM-based MEG recordings to be used to study brain activity in anaesthetized animals. In addition, the findings of this study contribute to a deeper understanding of pain-related neural activity and pain sex differences.

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 observe the value of left atrial strain combined with electrocardiogram(ECG)P-wave parameters for predicting recurrence of paroxysmal atrial fibrillation(PAF)after pulmonary vein isolation(PVI)using radiofrequency catheter.Methods Totally 88 PAF patients who planned to receive the first PVI were prospectively enrolled and divided into recurrence group(n=30)and non-recurrence group(n=58)according to results of ECG within 6 months after PVI.The patients'basic data,the transthoracic echocardiography(TTE)parameters,including left atrial reservoir strain(LASr),left atrial conduct strain(LAScd)and left atrial contraction strain(LASct),as well as ECG parameters including P-wave duration,PR interval and P/PR(the ratio of P-wave duration to PR interval)were compared between groups.Multivariate logistic regression analysis was performed of parameters being statistically different between groups to screen independent predictors for recurrence of PAF after PVI.The receiver operating characteristic curve and the area under the curve(AUC)were used to evaluate the predicting efficacy of individual independent predictors alone and their combination,and DeLong test was used for comparison.Results No significant difference of patients'basic data was found between groups(all P＞0.05).Compared with those in non-recurrence group,LASr and LAScd decreased while P/PR increased in recurrent group(all P＜0.05).LASr(OR=0.805),LAScd(OR=0.850)and P/PR(OR=1.119)were all independent predictors for recurrence of PAF after PVI(all P＜0.05),with AUC of 0.755,0.643 and 0.771,respectively,all lower than their combination(AUC=0.869)(all P＜0.05).Conclusion TTE and ECG parameters could be used to predict recurrence of PAF after PVI.The predicting efficacy of the combination of LASr,LAScd and P/PR was better than that of each alone.

With the rapid development of economy and the improvement of human living standard,vari-ous metabolic disorders such as obesity,type 2 diabetes mellitus and non-alcoholic fatty liver disease have become important public health problems in China.Thermogenic adipocytes are rich in mitochondria and uncoupling protein 1(UCP1),which maintain mammalian core body temperature through the consump-tion of triglycerides and glucose and non-shivering thermogenesis.Since activated thermogenic adipocytes are believed to possess anti-obesity and anti-diabetes potential,they have attracted considerable research interests.Mitochondria,as highly functionally conserved organelles in thermogenic adipocytes,respond to alterations in thermogenic capacity through metabolic adaptation in the process of thermogenic activa-tion or inactivation.However,the dysfunction of mitochondrial metabolic adaptation in thermogenic adi-pocytes may result in thermogenic defects and even systemic metabolic disorders.Here,we summarize the recent progress in mitochondrial remodeling in thermogenic adipocytes,including mitochondrial dy-namics,phospholipid and cristae remodeling,and regulation of mitochondrial ROS and oxidative stress.The relevant regulatory factors are summarized,which will provide new insights into how mitochondria maintain thermogenic capacity in thermogenic adipocytes,aiming to help the development of pharmaceuti-cal drugs to activate adaptive thermogenesis for fighting against metabolic diseases.

Objective To investigate the application value of coronary CT angiography(CCTA)and CT angiography derived fractional flow reserve(CT-FFR)in diagnosis of coronary ischemic disease(CID).Methods A total of 108 patients with coronary heart disease treated in Jinhua People's Hospital from May 2021 to June 2023 were selected as study objects.Using coronary angiography as the gold standard,the patients were divided into CID group(n=66)and non-CID group(n=42)according to myocardial fractional flow reserve.CCTA parameters[minimum lumen area(MLA),minimum lumen diameter(MLD),percentage of area stenosis(%AS),percentage of diameter stenosis(%DS)]and CT-FFR were compared between two groups.The relationship between clinical features and MLA,MLD,%AS,%DS and CT-FFR in CID group was analyzed.Receiver operating characteristic(ROC)curve was drawn to analyze the effectiveness of CCTA and CT-FFR in diagnosing CID.Results MLA,MLD and CT-FFR in CID group were significantly lower than those in non-CID group,and%AS and%DS were significantly higher than those in non-CID group(P<0.05).MLA,MLD,and CT-FFR in patients with severe calcification or stenosis were lower than those in patients with mild-to-moderate calcification or stenosis,while%AS and%DS were higher than those in patients with mild-to-moderate calcification or stenosis(P<0.05).MLA,MLD,and CT-FFR were negatively correlated with the degree of calcification and stenosis,and%AS and%DS were positively correlated with the degree of calcification and stenosis(P<0.05).The diagnostic accuracy of CT-FFR was higher than that of CCTA(86.11%vs.70.37%,χ2=7.859,P<0.05).ROC curve analysis showed that area under the curve(AUC)of CCTA and CT-FFR for diagnosing CID were 0.706 and 0.860,respectively.AUC of CT-FFR was higher than that of CCTA(Z=2.347,P<0.05).Conclusion Both CCTA and CT-FFR have certain value in diagnosis of CID,but CT-FFR is more efficient and provides more comprehensive information of myocardial ischemia.

Objective To explore the efficacy and safety of Kegel exercise combined with biofeedback electrical stimulation in the treatment of postpartum pelvic floor dysfunction(PFD).Methods A total of 100 postpartum PFD patients diagnosed and treated in Shaoxing Maternal and Child Health Care Hospital from January 2022 to May 2023 were selected and divided into KEG group and combination group according to random number table method,with 50 cases in each group.Patients in KEG group were given Kegel exercise,and patients in combination group were treated with Kegel exercise combined with biofeedback electrical stimulation.The clinical efficacy,pelvic floor electrophysiological indexes,bladder neck mobility,urethral rotation angle and sexual function were compared between two groups.Results The total effective rate of combination group was significantly higher than that of KEG group(x2=4.891,P=0.026).After treatment,the anterior resting average electromyogram value(aEMG),posterior resting aEMG,slow muscle aEMG and fast muscle maximum electromyogram value(mEMG)of pelvic floor muscles and sexual satisfaction scores in two groups were significantly higher than before treatment,bladder neck mobility and urethral rotation angle in combination group were significantly lower than before treatment,the duration of vaginal contraction in combination group was significantly longer than before treatment,and the pain score of coitus in combination group was significantly lower than before treatment(P＜0.05).The anterior resting aEMG,posterior resting aEMG,slow muscle aEMG and fast muscle mEMG of pelvic floor muscles and sexual satisfaction scores in combination group were significantly higher than those in KEG group,bladder neck mobility and urethral rotation angle were significantly lower than those in KEG group,the duration of vaginal contraction was significantly longer than that in KEG group,and the pain score of coitus was significantly lower than that in KEG group(P＜0.05).No complications occurred in both groups after treatment.Conclusion Kegel exercise combined with biofeedback electrical stimulation can significantly improve pelvic floor muscle function,sexual function and urinary function in patients with postpartum PFD with good safety,and its efficacy is better than Kegel exercise.