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.

Transcranial temporal interference stimulation (tTIS) is a novel non-invasive neuromodulation technique with the potential to precisely target deep brain structures. This study explores the neural and behavioral effects of tTIS on the superior colliculus (SC), a region involved in eye movement control, in mice. Computational modeling revealed that tTIS delivers more focused stimulation to the SC than traditional transcranial alternating current stimulation. In vivo experiments, including Ca²⁺ signal recordings and eye movement tracking, showed that tTIS effectively modulates SC neural activity and induces eye movements. A significant correlation was found between stimulation frequency and saccade frequency, suggesting direct tTIS-induced modulation of SC activity. These results demonstrate the precision of tTIS in targeting deep brain regions and regulating eye movements, highlighting its potential for neuroscientific research and therapeutic applications.
Animals ; Superior Colliculi/physiology* ; Transcranial Direct Current Stimulation/methods* ; Eye Movements/physiology* ; Male ; Mice ; Mice, Inbred C57BL

Objective To estimate adolescents and children age using stepwise regression and machine learning methods based on the pulp and tooth volumes of the left maxillary central incisor and cuspid on cone beam computed tomography(CBCT)images,and to compare and analyze the estimation re-sults.Methods A total of 498 Shanghai Han adolescents and children CBCT images of the oral and maxillofacial regions were collected.The pulp and tooth volumes of the left maxillary central incisor and cuspid were measured and calculated.Three machine learning algorithms(K-nearest neighbor,ridge regression,and decision tree)and stepwise regression were used to establish four age estimation models.The coefficient of determination,mean error,root mean square error,mean square error and mean ab-solute error were computed and compared.A correlation heatmap was drawn to visualize and the monotonic relationship between parameters was visually analyzed.Results The K-nearest neighbor model(R2=0.779)and the ridge regression model(R2=0.729)outperformed stepwise regression(R2=0.617),while the decision tree model(R2=0.494)showed poor fitting.The correlation heatmap demon-strated a monotonically negative correlation between age and the parameters including pulp volume,the ratio of pulp volume to hard tissue volume,and the ratio of pulp volume to tooth volume.Con-clusion Pulp volume and pulp volume proportion are closely related to age.The application of CBCT-based machine learning methods can provide more accurate age estimation results,which lays a founda-tion for further CBCT-based deep learning dental age estimation research.

Objective To prepare a nano drug(PFOB@Lip-MMC)with liposome as the carrier,liquid perfluorooc-tyl bromide(PFOB)as core and mitomycin C(MMC)loading on the liposome shell and study its inhibitory effect on the proliferation of human pterygium fibroblasts(HPFs).Methods The thin film dispersion-hydration ultrasonic method was used to prepare PFOB@Lip-MMC and detect its physical and chemical properties.Cell Counting Kit-8,Cam-PI cell viability staining and flow cytometry were employed to detect the impact of different concentrations of PFOB@Lip-MMC on the via-bility of HPFs.DiI fluorescence labeled PFOB@Lip-MMC was used to observe the permeability of the nano drug to HPFs under a laser confocal microscope.After establishing HPF inflammatory cell models,they were divided into the control group(with sterile phosphate-buffered saline solution added),PFOB@Lip group(with PFOB@Lip added),MMC group(with MMC added),PFOB@Lip-MMC group(with PFOB@Lip-MMC added)and normal group(with fresh culture medi-um added)according to the experimental requirements.After co-incubation for 24 h,flow cytometer was used to detect the apoptosis rate of inflammatory cells,and the gene expression levels of interleukin(IL)-1β,prostaglandin E2(PGE2),tumor necrosis factor(TNF)-α and vascular endothelial growth factor(VEGF)in cells were analyzed by PCR.Results The average particle size and Zeta potential of PFOB@Lip-MMC were(103.45±2.17)nm and(27.34±1.03)mV,respec-tively,and its entrapped efficiency and drug loading rate were(72.85±3.28)％and(34.27±2.04)％,respectively.The sustained-release MMC of drug-loaded nanospheres reached(78.34±2.92)％in vitro in a 24-hour ocular surface environ-ment.The biological safety of PFOB@Lip-MMC significantly improved compared to MMC.In terms of the DiI fluorescence labeled PFOB@Lip-MMC,after co-incubation with inflammatory HPFs for 2 h,DiI fluorescence labeling was diffusely dis-tributed in the cytoplasm of inflammatory HPFs.The apoptosis rate of inflammatory HPFs in the PFOB@Lip-MMC group[(77.23±4.93)％]was significantly higher than that in the MMC group[(51.62±3.28)％].The PCR examination results showed that the gene transcription levels of IL-1 β,PGE2,TNF-α and VEGF in other groups were significantly reduced com-pared to the control group and PFOB@Lip group,with the most significant decrease in the PFOB@Lip-MMC group(all P＜0.05).Conclusion In this study,a novel nano drug(PFOB@LIP-MMC)that inhibited the proliferation of HPFs was successfully synthesized,and its cytotoxicity was significantly reduced compared to the original drugs.It has good bio-compatibility and anti-inflammatory effects,providing a new treatment approach for reducing the recurrence rate after pte-rygium surgery.

Objective:To investigate the efficacy of different doses of bortezomib combined with chemotherapy for multiple myeloma (MM).Methods:A prospective case series study was performed. A total of 81 MM patients at Leshan People's Hospital from February 2022 to May 2023 were collected as study subjects. According to the random number table method, patients were divided into high-dose bortezomib group (39 cases treated with 1.6 mg/m 2 bortezomib combined with dexamethasone and thalidomide) and low-dose bortezomib group (42 cases treated with 1.3 mg/m 2 bortezomib combined with dexamethasone and thalidomide). The clinical efficacy after 4 courses of treatment, adverse reactions, C-reactive protein (CRP), β 2 microglobulin (β 2-MG) and serum creatinine levels before and after treatment, survival and prognosis of patients in both groups were compared. Results:There were 29 males and 10 females in the high-dose bortezomib group and the age was (59±5) years; there were 31 males and 11 females in the low-dose bortezomib group and the age was (59±6) years. The differences in the general data of both groups were statistically significant (all P > 0.05). The overall effectiveness rate was 87.2% (34/39) and 80.9% (34/42), respectively in the high-dose bortezomib group and the low-dose bortezomib group, and the difference was not statistically significant of both groups ( χ2 = 0.58, P = 0.446). The incidence rate of adverse reactions was 30.8% (12/39), 19.0% (8/39), respectively in the high-dose bortezomib group and the low-dose bortezomib group, and the difference was not statistically significant of both groups ( χ2 = 1.49, P = 0.222). Before treatment, there were no statistically significant differences in the levels of CRP, β 2-MG and serum creatinine between the 2 groups (all P > 0.05); after treatment, there were statistically significant differences in the levels of CRP [(23.6±2.2) g/L vs. (31.5±3.6) g/L)], β 2-MG [(2 317±63) μg/L vs. (4 212±114) μg/L] and serum creatinine [(70±5) μmol/L vs. (79±7) μmol/L] in the high-dose bortezomib group and the low-dose bortezomib group ( t value was 4.28, 18.29, 4.00, all P<0.05); and the levels of above 3 indicators after treatment were lower than those before treatment of both groups (all P < 0.05). The mortality rate was 10.3% (4/39) and 14.3% (6/42), respectively in the high-dose bortezomib group and the low-dose bortezomib group 1-year follow-up after treatment, and the difference was not statistically significant ( χ2 = 0.30, P = 0.582). Conclusions:The efficacy and safety of high-dose bortezomib combined with chemotherapy are comparable to those of low-dose bortezomib combined with chemotherapy in treatment of MM, while the former could improve renal function and inflammatory status of MM patients.

Patients with severe trauma require an extremely timely treatment and transfusion plays an irreplaceable role in the emergency treatment of such patients. An increasing number of evidence-based medicinal evidences and clinical practices suggest that patients with severe traumatic bleeding benefit from early transfusion of low-titer group O whole blood or hemostatic resuscitation with red blood cells, plasma and platelet of a balanced ratio. However, the current domestic mode of blood supply cannot fully meet the requirements of timely and effective blood transfusion for emergency treatment of patients with severe trauma in clinical practice. In order to solve the key problems in blood supply and blood transfusion strategies for emergency treatment of severe trauma, Branch of Clinical Transfusion Medicine of Chinese Medical Association, Group for Trauma Emergency Care and Multiple Injuries of Trauma Branch of Chinese Medical Association, Young Scholar Group of Disaster Medicine Branch of Chinese Medical Association organized domestic experts of blood transfusion medicine and trauma treatment to jointly formulate Chinese expert consensus on blood support mode and blood transfusion strategies for emergency treatment of severe trauma patients ( version 2024). Based on the evidence-based medical evidence and Delphi method of expert consultation and voting, 10 recommendations were put forward from two aspects of blood support mode and transfusion strategies, aiming to provide a reference for transfusion resuscitation in the emergency treatment of severe trauma and further improve the success rate of treatment of patients with severe trauma.