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.

Testicular histology based on testicular biopsy is an important factor for determining appropriate testicular sperm extraction surgery and predicting sperm retrieval outcomes in patients with azoospermia. Therefore, we developed a deep learning (DL) model to establish the associations between testicular grayscale ultrasound images and testicular histology. We retrospectively included two-dimensional testicular grayscale ultrasound from patients with azoospermia (353 men with 4357 images between July 2017 and December 2021 in The First Affiliated Hospital of Sun Yat-sen University, Guangzhou, China) to develop a DL model. We obtained testicular histology during conventional testicular sperm extraction. Our DL model was trained based on ultrasound images or fusion data (ultrasound images fused with the corresponding testicular volume) to distinguish spermatozoa presence in pathology (SPP) and spermatozoa absence in pathology (SAP) and to classify maturation arrest (MA) and Sertoli cell-only syndrome (SCOS) in patients with SAP. Areas under the receiver operating characteristic curve (AUCs), accuracy, sensitivity, and specificity were used to analyze model performance. DL based on images achieved an AUC of 0.922 (95% confidence interval [CI]: 0.908-0.935), a sensitivity of 80.9%, a specificity of 84.6%, and an accuracy of 83.5% in predicting SPP (including normal spermatogenesis and hypospermatogenesis) and SAP (including MA and SCOS). In the identification of SCOS and MA, DL on fusion data yielded better diagnostic performance with an AUC of 0.979 (95% CI: 0.969-0.989), a sensitivity of 89.7%, a specificity of 97.1%, and an accuracy of 92.1%. Our study provides a noninvasive method to predict testicular histology for patients with azoospermia, which would avoid unnecessary testicular biopsy.
Humans ; Male ; Azoospermia/diagnostic imaging* ; Deep Learning ; Testis/pathology* ; Retrospective Studies ; Adult ; Ultrasonography/methods* ; Sperm Retrieval ; Sertoli Cell-Only Syndrome/diagnostic imaging*

OBJECTIVE: To investigate the mechanism of electroacupuncture (EA) in treating diabetic gastroparesis (DGP) by inhibiting the activation of Nod-like receptor family pyrin domain-containing protein 3 (NLRP3) inflammasome and pyroptosis mediated via NLRP3/cysteinyl aspartate specific proteinase-1 (caspase-1)/gasdermin D (GSDMD) signaling pathway. METHODS: Forty Sprague-Dawley rats were randomly divided into 4 groups including the control, DGP model, EA, and MCC950 groups. The DGP model was established by a one-time high-dose intraperitoneal injection of 2% streptozotocin and a high-glucose and high-fat diet for 8 weeks. EA intervention was conducted at Zusanli (ST 36), Liangmen (ST 21) and Sanyinjiao (SP 6) with sparse-dense wave for 15 min, and was administered for 3 courses of 5 days. After intervention, the blood glucose, urine glucose, gastric emptying, and intestinal propulsive rate were observed. Besides, HE staining was used to observe histopathological changes in gastric antrum tissues, and TUNEL staining was utilized to detect DNA damage. Protein expression levels of NLRP3, apoptosis-associated speck-like protein containing CARD (ASC), pro-caspase-1, caspase-1 and GSDMD were measured by Western blot. Immunofluorescence staining was employed to assess the activity of GSDMD-N. Lactate dehydrogenase (LDH) levels were detected by using a biochemical kit. RESULTS: DGP rats showed persistent hyperglycemia and a significant decrease in gastrointestinal motility (P<0.05 or P<0.01), accompanied by pathological damage in their gastric antrum tissues. Cellular DNA was obviously damaged, and the expressions of NLRP3, ASC, pro-caspase-1, caspase-1 and GSDMD proteins were significantly elevated, along with enhanced fluorescence signals of GSDMD-N and increased LDH release (P<0.01). EA mitigated hyperglycemia, improved gastrointestinal motility in DGP rats and alleviated their pathological injury (P<0.05). Furthermore, EA reduced cellular DNA damage, lowered the protein levels of NLRP3, ASC, pro-caspase-1, caspase-1 and GSDMD, suppressed GSDMD-N activity, and decreased LDH release (P<0.05 or P<0.01), demonstrating effects comparable to MCC950. CONCLUSION EA promotes gastrointestinal motility and repairs the pathological damage in DGP rats, and its mechanism may be related to the inhibition of NLRP3 inflammasome and pyroptosis mediated by NLRP3/caspase-1/GSDMD pathway.
Animals ; Electroacupuncture ; NLR Family, Pyrin Domain-Containing 3 Protein/metabolism* ; Pyroptosis ; Rats, Sprague-Dawley ; Caspase 1/metabolism* ; Gastroparesis/physiopathology* ; Signal Transduction ; Male ; Diabetes Mellitus, Experimental/physiopathology* ; Phosphate-Binding Proteins/metabolism* ; Gastrointestinal Motility ; Rats ; Intracellular Signaling Peptides and Proteins/metabolism* ; Diabetes Complications/physiopathology* ; Gasdermins

OBJECTIVE: This study reports the first imported case of Lassa fever (LF) in China. Laboratory detection and molecular epidemiological analysis of the Lassa virus (LASV) from this case offer valuable insights for the prevention and control of LF. METHODS: Samples of cerebrospinal fluid (CSF), blood, urine, saliva, and environmental materials were collected from the patient and their close contacts for LASV nucleotide detection. Whole-genome sequencing was performed on positive samples to analyze the genetic characteristics of the virus. RESULTS: LASV was detected in the patient's CSF, blood, and urine, while all samples from close contacts and the environment tested negative. The virus belongs to the lineage IV strain and shares the highest homology with strains from Sierra Leone. The variability in the glycoprotein complex (GPC) among different strains ranged from 3.9% to 15.1%, higher than previously reported for the seven known lineages. Amino acid mutation analysis revealed multiple mutations within the GPC immunogenic epitopes, increasing strain diversity and potentially impacting immune response. CONCLUSION The case was confirmed through nucleotide detection, with no evidence of secondary transmission or viral spread. The LASV strain identified belongs to lineage IV, with broader GPC variability than previously reported. Mutations in the immune-related sites of GPC may affect immune responses, necessitating heightened vigilance regarding the virus.
Humans ; China/epidemiology* ; Genome, Viral ; Lassa Fever/virology* ; Lassa virus/classification* ; Molecular Epidemiology ; Phylogeny

Objective To summarize the epidemiological and clinical features of infectious diseases of the central nervous system(CNS)by a single-center analysis.Methods A retrospective analysis was conducted on the data of 1247 cases of CNS infectious diseases diagnosed and treated in the First Medical Center of PLA General Hospital from 2001 to 2020.Results The data for this group of CNS infectious diseases by disease type in descending order of number of cases were viruses 743(59.6％),Mycobacterium tuberculosis 249(20.0％),other bacteria 150(12.0％),fungi 68(5.5％),parasites 18(1.4％),Treponema pallidum 18(1.4％)and rickettsia 1(0.1％).The number of cases increased by 177 cases(33.1％)in the latter 10 years compared to the previous 10 years(P<0.05).No significant difference in seasonal distribution pattern of data between disease types(P>0.05).Male to female ratio is 1.87︰1,mostly under 60 years of age.Viruses are more likely to infect students,most often at university/college level and above,farmers are overrepresented among bacteria and Mycobacterium tuberculosis,and more infections of Treponema pallidum in workers.CNS infectious diseases are characterized by fever,headache and signs of meningeal irritation,with the adductor nerve being the more commonly involved cranial nerve.Matagenomic next-generation sequencing improves clinical diagnostic capabilities.The median hospital days for CNS infectious diseases are 18.00(11.00,27.00)and median hospital costs are ￥29,500(￥16,000,￥59,200).The mortality rate from CNS infectious diseases is 1.6％.Conclusions The incidence of CNS infectious diseases is increasing last ten years,with complex clinical presentation,severe symptoms and poor prognosis.Early and accurate diagnosis and standardized clinical treatment can significantly reduce the morbidity and mortality rate and ease the burden of disease.

Objective To explore the efficacy and safety of ticagrelor de-escalation and nicorandil therapy in elderly patients with acute coronary syndrome(ACS)after percutaneous coronary intervention(PCI).Methods A total of 300 elderly patients with ACS were selected from the Sixth and Seventh Medical Center of Chinese PLA General Hospital and Beijing Chaoyang Integrative Medicine Emergency Rescue and First Aid Hospital from November 2016 to June 2019,including 153 males and 147 females,aged>65 years old.All the patients received PCI,and all had double antiplatelet therapy(DAPT)scores≥2 and a new DAPT(PRECISE-DAPT)score of≥25.All patients were divided into two groups by random number table method before operation:ticagrelor group(n=146,ticagrelor 180 mg load dose followed by PCI,and ticagrelor 90 mg bid after surgery)and ticagrelor de-escalation + nicorandil group(n=154,ticagrelor 180 mg load dose followed by PCI,ticagrelor 90 mg bid+nicorandil 5 mg tid after surgery,changed to ticagrelor 60 mg bid+ nicorandil 5 mg tid 6 months later).Follow-up was 12 months.The composite end points of cardiovascular death,myocardial infarction and stroke,the composite end points of mild hemorrhage,minor hemorrhage,other major hemorrhage and major fatal/life-threatening hemorrhage as defined by the PLATO study,and the composite end points of cardiovascular death,myocardial infarction,stroke and bleeding within 12 months in the two groups were observed.Results The comparison of general baseline data between the two groups showed no statistically significant difference(P>0.05).There was also no significant difference in the composite end points of cardiovascular death,myocardial infarction and stroke between the two groups(P>0.05).The cumulative incidence of bleeding events in ticagrelor de-escalation + nicorandil group was significantly lower than that in ticagrelor group(P<0.05),while the composite end points of cardiovascular death,myocardial infarction,stroke and bleeding were also significantly lower than those in tecagrelor group(P<0.05).Conclusion In elderly patients with ACS,the treatment of ticagrelor de-escalation + nicorandil after PCI may not increase the incidence of ischemic events such as cardiovascular death,myocardial infarction or stroke,and it may reduce the incidence of hemorrhagic events.