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.

PURPOSE: Septic shock is associated with high mortality and poor outcomes among sepsis patients with coagulopathy. Although traditional statistical methods or machine learning (ML) algorithms have been proposed to predict septic shock, these potential approaches have never been systematically compared. The present work aimed to develop and compare models to predict septic shock among patients with sepsis. METHODS: It is a retrospective cohort study based on 484 patients with sepsis who were admitted to our intensive care units between May 2018 and November 2022. Patients from the 908th Hospital of Chinese PLA Logistical Support Force and Nanchang Hongdu Hospital of Traditional Chinese Medicine were respectively allocated to training (n=311) and validation (n=173) sets. All clinical and laboratory data of sepsis patients characterized by comprehensive coagulation indexes were collected. We developed 5 models based on ML algorithms and 1 model based on a traditional statistical method to predict septic shock in the training cohort. The performance of all models was assessed using the area under the receiver operating characteristic curve and calibration plots. Decision curve analysis was used to evaluate the net benefit of the models. The validation set was applied to verify the predictive accuracy of the models. This study also used Shapley additive explanations method to assess variable importance and explain the prediction made by a ML algorithm. RESULTS: Among all patients, 37.2% experienced septic shock. The characteristic curves of the 6 models ranged from 0.833 to 0.962 and 0.630 to 0.744 in the training and validation sets, respectively. The model with the best prediction performance was based on the support vector machine (SVM) algorithm, which was constructed by age, tissue plasminogen activator-inhibitor complex, prothrombin time, international normalized ratio, white blood cells, and platelet counts. The SVM model showed good calibration and discrimination and a greater net benefit in decision curve analysis. CONCLUSION The SVM algorithm may be superior to other ML and traditional statistical algorithms for predicting septic shock. Physicians can better understand the reliability of the predictive model by Shapley additive explanations value analysis.
Humans ; Shock, Septic/blood* ; Machine Learning ; Male ; Female ; Retrospective Studies ; Middle Aged ; Aged ; Sepsis/complications* ; ROC Curve ; Cohort Studies ; Adult ; Intensive Care Units ; Algorithms ; Blood Coagulation ; Critical Illness

OBJECTIVE: This study aimed to explore the association between body mass index (BMI) and mortality based on the 10-year population-based multicenter prospective study. METHODS: A general population-based multicenter prospective study was conducted at four sites in rural China between 2013 and 2023. Multivariate Cox proportional hazards models and restricted cubic spline analyses were used to assess the association between BMI and mortality. Stratified analyses were performed based on the individual characteristics of the participants. RESULTS: Overall, 19,107 participants with a sum of 163,095 person-years were included and 1,910 participants died. The underweight (< 18.5 kg/m ²) presented an increase in all-cause mortality (adjusted hazards ratio [ aHR] = 2.00, 95% confidence interval [ CI]: 1.66-2.41), while overweight (≥ 24.0 to < 28.0 kg/m ²) and obesity (≥ 28.0 kg/m ²) presented a decrease with an aHR of 0.61 (95% CI: 0.52-0.73) and 0.51 (95% CI: 0.37-0.70), respectively. Overweight ( aHR = 0.76, 95% CI: 0.67-0.86) and mild obesity ( aHR = 0.72, 95% CI: 0.59-0.87) had a positive impact on mortality in people older than 60 years. All-cause mortality decreased rapidly until reaching a BMI of 25.7 kg/m ² ( aHR = 0.95, 95% CI: 0.92-0.98) and increased slightly above that value, indicating a U-shaped association. The beneficial impact of being overweight on mortality was robust in most subgroups and sensitivity analyses. CONCLUSION This study provides additional evidence that overweight and mild obesity may be inversely related to the risk of death in individuals older than 60 years. Therefore, it is essential to consider age differences when formulating health and weight management strategies.
Humans ; Body Mass Index ; China/epidemiology* ; Male ; Female ; Middle Aged ; Prospective Studies ; Rural Population/statistics & numerical data* ; Aged ; Follow-Up Studies ; Adult ; Mortality ; Cause of Death ; Obesity/mortality* ; Overweight/mortality*

Objective:To investigate the effect of CD8+CD28-T cells on acute graft-versus-host disease(aGVHD)after haploidentical hematopoietic stem cell transplantation(haplo-HSCT).Methods:The relationship between absolute count of CD8+CD28-T cells and aGVHD in 60 patients with malignant hematological diseases was retrospectively analyzed after haplo-HSCT,and the differences in the incidence rate of chronic graft-versus host disease(cGVHD),infection and prognosis between different CD8+CD28-T absolute cells count groups were compared.Results:aGVHD occurred in 40 of 60 patients after haplo-HSCT,with an incidence rate of 66.67％.The median occurrence time of aGVHD was 32.5(20-100)days.At 30 days after the transplantation,the absolute count of CD8+CD28-T cells of aGVHD group was significantly lower than that of non-aGVHD group(P=0.03).Thus the absolute count of CD8+CD28-T cells at 30 days after transplantation can be used to predict the occurrence of aGVHD to some extent.At 30 days after transplantation,the incidence rate of aGVHD in the low cell count group(CD8+CD28-T cells absolute count＜0.06/μl)was significantly higher than that in the high cell count group(CD8+CD28-T cells absolute count ≥0.06/μl,P=0.011).Multivariate Cox regression analysis further confirmed that the absolute count of CD8+CD28-T cells at 30 days after transplantation was an independent risk factor for aGVHD,and the risk of aGVHD in the low cell count group was 2.222 times higher than that in the high cell count group(P=0.015).The incidence of cGVHD,fungal infection,EBV infection and CMV infection were not significantly different between the two groups with different CD8+CD28-T cells absolute count.The overall survival,non-recurrent mortality and relapse rates were not significantly different between different CD8+CD28-T cells absolute count groups.Conclusion:Patients with delayed CD8+CD28-T cells reconstitution after haplo-HSCT are more likely to develop aGVHD,and the absolute count of CD8+CD28-T cells can be used to predict the incidence of aGVHD to some extent.The absolute count of CD8+CD28-T cells after haplo-HSCT was not associated with cGVHD,fungal infection,EBV infection,and CMV infection,and was also not significantly associated with the prognosis after transplantation.

Aim To preliminarily evaluate the effects of hypobaric hypoxia on organism damage in rats with post-traumatic stress disorder(PTSD),with a view to laying a foundation for drug research in plateau PTSD.Methods The rats were randomly divided into four groups,namely,the control(Control)group,the sin-gle-prolonged stress(SPS)group,the hypobaric hy-poxia(HH)group and the single-prolonged stress combined with hypobaric hypoxia(SPS+HH)group.The PTSD model was firstly constructed using the SPS method for rats in the SPS and SPS+HH groups.On the second day,rats in the HH group and SPS+HH group were placed in a low-pressure hypoxia chamber at a simulated altitude of 6000 m for 14 days.General condition,behavior,blood tests,and histomorphology were examined in order to evaluate the damage caused by low pressure hypoxia in PTSD rats.Results The body mass of rats in the SPS+HH group was signifi-cantly reduced;the feces were partly hard and lumpy,and some of them were seen to have high viscosity.Anxiety-like and depression-like behaviors were ob-served in all groups except in the control group,in which hypobaric hypoxia aggravated the behavioral ab-normalities in SPS rats.Rats in both the SPS and SPS+HH groups had coagulation dysfunction and abnor-mally increased blood viscosity,which was significantly abnormal in the SPS+HH group;erythrocytes,hemo-globin,and erythrocyte specific volume in whole blood of rats in the SPS+HH group were significantly in-creased compared with those of rats in the SPS group;and serum TP,LDH and GLU levels were abnormal in rats in the SPS+HH group.Dilated and congested blood vessels were seen in hippocampal tissue,conges-ted central veins were seen in hepatic tissue,and dilat-ed and congested liver sinusoids with mild granuloma-tous degeneration of hepatocytes were seen in rats of the SPS+HH group.Conclusion Hypobaric hypoxia exacerbates depression-like and anxiety-like behaviors in PTSD rats,as well as hematological indices and his-tomorphometric abnormalities in PTSD rats.