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: To comprehensively evaluate the effect of icariin in alleviating reproductive function damage (RFD) in male mice via in vitro and in vivo experiments. METHODS: We isolated Leydig cells from 60 KM male mice in vitro, and examined the toxic effect of icariin on the Leydig cells using Cell Counting Kit-8 (CCK-8). We equally randomized the mice into six groups: normal control, RFD model control (made by intraperitoneal injection of busulfan at 10 mg/kg combined with cyclophosphamide (CP) at 120 mg/kg), positive control, and low-, medium- and high-dose icariin. After modeling, we treated the mice in the positive control group with Wuziyanzong Pills and those in the low-, medium- and high-dose icariin groups by intragastrical administration of icariin at 20, 40 and 80 mg/kg-1, respectively, for 30 successive days. Then we obtained the weight and visceral coefficients of the reproductive organs, calculated the sperm count, observed the pathological changes in the testis tissue by HE staining, measured the serum testosterone (T) level by ELISA, determined the indexes of testicular oxidative stress and nitric oxide (NO) signaling pathway by colorimetric assay, and detected the expression levels of the pro-apoptotic genes Fas and Bax by qRT-PCR. RESULTS: CCK-8 assay confirmed that icariin had no toxic effect on the isolated Leydig cells of the mice, and could effectively reduce busulfan- and CP-induced cytotoxicity and promote the secretion of serum T. Icariin at 80 mg/kg significantly increased the visceral coefficient of the testis and promoted spermatogenesis (P<0.05), but had little effect on the visceral coefficient of the epididymis in the RFD model mice. Testicular histomorphometric observation revealed significantly improved testis structure, intact boundary membrane of seminiferous tubules and increased numbers of various types of spermatogenic cells of the model mice after treated with icariin. Compared with the mice in the model control group, those treated with high-dose icariin showed a significantly reduced content of malondialdehyde (MDA) (by 35.3%, P<0.01), elevated total antioxidant capacity (TAOC) and superoxide dismutase (T-SOD) activity (P<0.05), and decreased NO content and nitric oxide synthase (NOS) activity in the testis tissue (P<0.01). In addition, icariin exhibited an evident inhibitory effect on the expressions of the pro-apoptotic genes Bax and Fas. CONCLUSION Icariin can ameliorate oxidative stress-induced damage to the testicular function and protect spermatogenesis of male mice by elevating TAOC, decreasing NOS activity, inhibiting the NO level in the testis, and suppressing busulfan- and CP-induced apoptosis of testicular cells.
Animals ; Male ; Cyclophosphamide/adverse effects* ; Mice ; Busulfan/adverse effects* ; Flavonoids/pharmacology* ; Leydig Cells/drug effects* ; Oxidative Stress/drug effects* ; Testis/drug effects* ; Apoptosis/drug effects* ; Testosterone/blood*

Objective To investigate the status of population dynamics and distribution changes of Aedes aegypti in Guangdong Province.Methods Continuous monitoring was conducted from May 2018 to July 2024 in Wushi Town and Qishui Town,Leizhou City,Zhanjiang City,Guangdong Province.Additionally,a survey of the distribution of Ae.aegypti along the Leizhou Peninsula coast was carried out.Results The density of Ae.aegypti in Zhanjiang showed a gradual decline from 2018 to 2024.The last detection of adult Ae.aegypti in Wushi Town was in September 2021,and the last larva was found in October 2023.No Ae.aegypti was detected in Qishui Town during surveys from 2021 to 2024.A survey of 18 coastal villages in the Leizhou Peninsula revealed no detections of Ae.aegypti.Conclusions This study provides a basis for understanding the distribution and population density fluctuations of Ae.aegypti,assessing its invasion risk,and scientifically conducting relevant prevention and control efforts.

Objective:To describe the prevalence of non-alcoholic fatty liver disease (NAFLD) in people living with HIV in Taizhou, Zhejiang Province, and identify the factors associated with NAFLD in this population.Methods:A cross-sectional survey was conducted from 2021 to 2023. Based on the routine follow-up management of people living with HIV, liver ultrasound examination, physical examination and laboratory test were conducted to collect the information about the diagnosis of NAFLD and biochemical indicators in this population. Logistic regression model was used to identify the factors associated with the prevalence of NAFLD.Results:In the 2 550 study participants, the prevalence of NAFLD was 21.5% (548/2 550), abnormal liver function was found in 23.7% (604/2 550) of the study participants, and liver fibrosis was found in 45.2% (1 152/2 550) of the study participants. Multivariable logistic regression analyses showed that being women (a OR=0.55, 95% CI: 0.42-0.73), being overweight or obese (a OR=3.22, 95% CI: 2.59-4.01), having diabetes (a OR=3.37, 95% CI: 2.15-5.29), having dyslipidemia (a OR=2.96, 95% CI: 2.25-3.89), CD4 + T lymphocyte (CD4) counts <200 cells/μl (a OR=0.61, 95% CI: 0.42-0.88), and receiving Efavirenz (EFV) + Lamivudine (3TC) + Zidovudine (AZT) for antiretroviral therapy (ART)(a OR=1.52, 95% CI: 1.17-1.98) were associated with NAFLD. NAFLD was positively associated with abnormal liver function (a OR=2.01, 95% CI: 1.60-2.52) and inversely associated with liver fibrosis (a OR=0.76, 95% CI: 0.59-0.98). The 45-59 age group (a OR=7.05, 95% CI: 5.65-8.80), CD4 counts <200 cells/μl (a OR=1.45, 95% CI: 1.06-1.97) and receiving Nevirapine (NVP)+3TC+AZT of ART (a OR=1.87,95% CI: 1.44-2.43) were the main factors associated with liver fibrosis. Conclusions:The prevalence of NAFLD in people living with HIV Taizhou was more than 20.0%, with a significant proportion of them having abnormal liver function and liver fibrosis. Being overweight or obese, suffering from diabetes, having dyslipidemia, low CD4 counts, and receiving specific ART were associated with NAFLD. NAFLD, CD4 counts and specific ART were the main factors associated with abnormal liver function and liver fibrosis.

Objective To explore the predictive factors of recurrence of chronic suppurative otitis media(CSOM)after otoendoscopic surgery,and construct a risk quantified nomogram model.Methods The clinical data of 485 patients with CSOM who underwent otoendoscopic surgery in our hospital from February 2021 to February 2023 were retrospectively analyzed.The patients were divided into the recurrence group and the non-recurrence group according to the recurrence situation during the follow-up period.The clinical data of patients between the two groups were compared,and the predictive factors of postoperative recurrence were analyzed by Cox regression method.A risk quantified nomogram model was constructed based on these predictive factors.The predictive efficiency of the model was verified by receiver operating characteristic(ROC)curve,and the calibration degree of the model was verified by Hosmer-Lemeshow goodness of fit analysis,and the clinical net benefit of the model was evaluated by decision curve analysis(DCA)method.Results Follow-up ranged from 6 to 39 months,with a median of 21(11,32)months,the postoperative recurrence rate was 14.64%(71/485).Combined with recurrent upper respiratory tract infections(HR=3.019,95%CI:1.609 to 5.664),combined with chronic rhinosinusitis(HR=2.428,95%CI:1.529 to 3.856),combined with adenoid hypertrophy(HR=2.214,95%CI:1.381 to 3.551),middle ear risk index(MERI)score(HR=2.863,95%CI:1.445 to 5.675),the seven-item eustachian tube dysfunction questionnaire(ETDQ-7)score(HR=2.679,95%CI:1.505 to 4.765)and inadequate drainage of the surgical cavity(HR=2.373,95%CI:1.503 to 3.746)were the risk factors for postoperative recurrence(P<0.05).A risk quantified nomogram model of recurrence after otoendoscopic surgery in CSOM patients was constructed based on the predictive factors of Cox regression analysis,among them the risk value ranges of patients who combined with recurrent upper respiratory tract infections,combined with chronic rhinosinusitis,combined with adenoid hypertrophy,MERI score,ETDQ-7 score,and inadequate drainage of the surgical cavity were 0 to 65 points,0 to 56 points,0 to 52 points,0 to 76 points,0 to 64 points,and 0 to 76 points,respectively.The area under the curve of ROC,sensitivity and specificity of the model for predicting postoperative recurrence were 0.928(95%CI:0.875 to 0.948),85.92%and 88.89%,respectively.There was no significant difference between the predicted probability of postoperative recurrence and the actual probability(P>0.05).The threshold probability of postoperative recurrence predicted by the model in the range of 4%to 92%could obtain clinical net benefit.Conclusion The predictive factors of recurrence after otoendoscopic surgery in CSOM patients include combined with recurrent upper respiratory tract infections,combined with chronic rhinosinusitis,combined with adenoid hypertrophy,MERI score,ETDQ-7 score and inadequate drainage of the surgical cavity,the risk quantified nomogram model based on these factors is highly effective in predicting postoperative recurrence.

OBJECTIVE: To investigate the association between long-term glycemic control and cerebral infarction risk in patients with diabetes through a large-scale cohort study. METHODS: This prospective, community-based cohort study included 12,054 patients with diabetes. From 2006 to 2012, 38,272 fasting blood glucose (FBG) measurements were obtained from these participants. FBG trajectory patterns were generated using latent mixture modelling. Cox proportional hazards models were applied to assess the subsequent risk of cerebral infarction associated with different FBG trajectory patterns. RESULTS: At baseline, the mean age of the participants was 55.2 years. Four distinct FBG trajectories were identified based on FBG concentrations and their changes over the 6-year follow-up period. After a median follow-up of 6.9 years, 786 cerebral infarction events were recorded. Different trajectory patterns were associated with significantly varied outcome risks (Log-Rank P < 0.001). Compared with the low-stability group, Hazard Ratio ( HR) adjusted for potential confounders were 1.37 for the moderate-increasing group, 1.23 for the elevated-decreasing group, and 2.08 for the elevated-stable group. CONCLUSION Sustained high FBG levels were found to play a critical role in the development of ischemic stroke among patients with diabetes. Controlling FBG levels may reduce the risk of cerebral infarction.
Humans ; Cerebral Infarction/blood* ; Middle Aged ; Male ; Female ; Blood Glucose/analysis* ; Fasting/blood* ; Aged ; Prospective Studies ; Risk Factors ; Diabetes Mellitus/blood* ; Adult ; Proportional Hazards Models

OBJECTIVE: This study aimed to reexplore minimum iodine excretion and to build a dietary iodine recommendation for Chinese adults using the obligatory iodine loss hypothesis. METHODS: Data from 171 Chinese adults (19-21 years old) were collected and analyzed based on three balance studies in Shenzhen, Yinchuan, and Changzhi. The single exponential equation was accordingly used to simulate the trajectory of 24 h urinary iodine excretion as the low iodine experimental diets offered (iodine intake: 11-26 μg/day) and to further deduce the dietary reference intakes (DRIs) for iodine, including estimated average requirement (EAR) and recommended nutrient intake (RNI). RESULTS: The minimum iodine excretion was estimated as 57, 58, and 51 μg/day in three balance studies, respectively. Moreover, it was further suggested as 57, 58, and 51 μg/day for iodine EAR, and 80, 81, and 71 μg/day for iodine RNI or expressed as 1.42, 1.41, and 1.20 μg/(day·kg) of body weight. CONCLUSION The iodine DRIs for Chinese adults were established based on the obligatory iodine loss hypothesis, which provides scientific support for the amendment of nutrient requirements.
Humans ; Iodine/administration & dosage* ; Male ; Female ; China ; Young Adult ; Diet ; Adult ; Nutritional Requirements ; East Asian People