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.

Humans ; Aged ; Lung Diseases ; Pneumonia/drug therapy* ; Adrenal Cortex Hormones/therapeutic use* ; Pulmonary Disease, Chronic Obstructive/drug therapy* ; Administration, Inhalation ; Community-Acquired Infections/drug therapy*

Objective:To evaluate the immunogenicity, safety, and immune persistence of the sequential booster with the recombinant protein-based COVID-19 vaccine (CHO cell) in healthy people aged 18-84 years.Methods:An open-label, multi-center trial was conducted in October 2021. The eligible healthy individuals, aged 18-84 years who had completed primary immunization with the inactivated COVID-19 vaccine 3 to 9 months before, were recruited from Shangyu district of Shaoxing and Kaihua county of Quzhou, Zhejiang province. All participants were divided into three groups based on the differences in prime-boost intervals: Group A (3-4 months), Group B (5-6 months) and Group C (7-9 months), with 320 persons per group. All participants received the recombinant COVID-19 vaccine (CHO cell). Blood samples were collected before the vaccination and after receiving the booster at 14 days, 30 days, and 180 days for analysis of GMTs, antibody positivity rates, and seroconversion rates. All adverse events were collected within one month and serious adverse events were collected within six months. The incidences of adverse reactions were analyzed after the booster.Results:The age of 960 participants was (52.3±11.5) years old, and 47.4% were males (455). The GMTs of Groups B and C were 65.26 (54.51-78.12) and 60.97 (50.61-73.45) at 14 days after the booster, both higher than Group A′s 44.79 (36.94-54.30) ( P value<0.05). The GMTs of Groups B and C were 23.95 (20.18-28.42) and 27.98 (23.45-33.39) at 30 days after the booster, both higher than Group A′s 15.71 (13.24-18.63) ( P value <0.05). At 14 days after the booster, the antibody positivity rates in Groups A, B, and C were 91.69% (276/301), 94.38% (302/320), and 93.95% (295/314), respectively. The seroconversion rates in the three groups were 90.37% (272/301), 93.75% (300/320), and 93.31% (293/314), respectively. There was no significant difference among these rates in the three groups (all P values >0.05). At 30 days after the booster, antibody positivity rates in Groups A, B, and C were 79.60% (238/299), 87.74% (279/318), and 90.48% (285/315), respectively. The seroconversion rates in the three groups were 76.92% (230/299), 85.85% (273/318), and 88.25% (278/315), respectively. There was a significant difference among these rates in the three groups (all P values <0.001). During the sequential booster immunization, the incidence of adverse events in 960 participants was 15.31% (147/960), with rates of about 14.38% (46/320), 17.50% (56/320), and 14.06% (45/320) in Groups A, B, and C, respectively. The incidence of adverse reactions was 8.02% (77/960), with rates of about 7.50% (24/320), 6.88% (22/320), and 9.69% (31/320) in Groups A, B, and C, respectively. No serious adverse events related to the booster were reported. Conclusion:Healthy individuals aged 18-84 years, who had completed primary immunization with the inactivated COVID-19 vaccine 3 to 9 months before, have good immunogenicity and safety profiles following the sequential booster with the recombinant COVID-19 vaccine (CHO cell).

Cardiovascular diseases(CVDs)are a leading factor driving mortality worldwide.Iron,an essential trace mineral,is important in numerous biological processes,and its role in CVDs has raised broad discussion for decades.Iron-mediated cell death,namely ferroptosis,has attracted much attention due to its critical role in cardiomyocyte damage and CVDs.Furthermore,ferritinophagy is the upstream mechanism that induces ferroptosis,and is closely related to CVDs.This review aims to delineate the processes and mechanisms of ferroptosis and ferritinophagy,and the regulatory pathways and molecular targets involved in ferritinophagy,and to determine their roles in CVDs.Furthermore,we discuss the possibility of targeting ferritinophagy-induced ferroptosis modulators for treating CVDs.Collectively,this review offers some new insights into the pathology of CVDs and identifies possible therapeutic targets.

Microplastics(MPs)and nanoplastics(NPs)have become hazardous materials due to the massive amount of plastic waste and disposable masks,but their specific health effects remain uncertain.In this study,fluorescence-labeled polystyrene NPs(PS-NPs)were injected into the circulatory systems of mice to determine the distribution and potential toxic effects of NPs in vivo.Interestingly,whole-body imaging found that PS-NPs accumulated in the testes of mice.Therefore,the toxic effects of PS-NPs on the reproduction systems and the spermatocytes cell line of male mice,and their mechanisms,were investigated.After oral exposure to PS-NPs,their spermatogenesis was affected and the spermatogenic cells were damaged.The spermatocyte cell line GC-2 was exposed to PS-NPs and analyzed using RNA sequencing(RNA-seq)to determine the toxic mechanisms;a ferroptosis pathway was found after PS-NP exposure.The phenomena and indicators of ferroptosis were then determined and verified by ferroptosis inhibitor ferrostatin-1(Fer-1),and it was also found that nuclear factor erythroid 2-related factor 2(Nrf2)played an important role in spermatogenic cell ferroptosis induced by PS-NPs.Finally,it was confirmed in vivo that this mechanism of Nrf2 played a protective role in PS-NPs-induced male reproductive toxicity.This study demonstrated that PS-NPs induce male reproductive dysfunction in mice by causing spermatogenic cell ferroptosis dependent on Nrf2.

Objective To investigate the incidence rate,clinical characteristics,and prognosis of neonatal stroke in Shenzhen,China.Methods Led by Shenzhen Children's Hospital,the Shenzhen Neonatal Data Collaboration Network organized 21 institutions to collect 36 cases of neonatal stroke from January 2020 to December 2022.The incidence,clinical characteristics,treatment,and prognosis of neonatal stroke in Shenzhen were analyzed.Results The incidence rate of neonatal stroke in 21 hospitals from 2020 to 2022 was 1/15 137,1/6 060,and 1/7 704,respectively.Ischemic stroke accounted for 75％(27/36);boys accounted for 64％(23/36).Among the 36 neonates,31(86％)had disease onset within 3 days after birth,and 19(53％)had convulsion as the initial presentation.Cerebral MRI showed that 22 neonates(61％)had left cerebral infarction and 13(36％)had basal ganglia infarction.Magnetic resonance angiography was performed for 12 neonates,among whom 9(75％)had involvement of the middle cerebral artery.Electroencephalography was performed for 29 neonates,with sharp waves in 21 neonates(72％)and seizures in 10 neonates(34％).Symptomatic/supportive treatment varied across different hospitals.Neonatal Behavioral Neurological Assessment was performed for 12 neonates(33％,12/36),with a mean score of(32±4)points.The prognosis of 27 neonates was followed up to around 12 months of age,with 44％(12/27)of the neonates having a good prognosis.Conclusions Ischemic stroke is the main type of neonatal stroke,often with convulsions as the initial presentation,involvement of the middle cerebral artery,sharp waves on electroencephalography,and a relatively low neurodevelopment score.Symptomatic/supportive treatment is the main treatment method,and some neonates tend to have a poor prognosis.