Objective:To develop 2 prediction models for anti-tuberculosis drug-induced liver injury (ATB-DILI) based on convolutional neural network (CNN) and multiple logistic regression, and to evaluate and compare the performance of the 2 models.Methods:The clinical and laboratory test data of inpatients in the Third People′s Hospital of Zhenjiang, Jurong People's Hospital, and the Third People′s Hospital of Danyang from January 1, 2019 to October 31, 2022 were collected. According to whether ATB-DILI occurred, patients were divided into with and without ATB-DILI groups, and the clinical characteristics of the 2 groups were compared. The patients were randomly divided into training set and test set according to a ratio of 7∶3 by random number table method. Based on data in the training set, multiple logistic regression and CNN were used to develop ATB-DILI prediction models; based on data in the training and test sets, the accuracy of the 2 models in predicting ATB-DILI was verified. The receiver operating characteristic (ROC) curve was drawn, and the sensitivity, specificity, Youden index and area under the curve (AUC) of the 2 models were compared.Results:A total of 3 012 patients were included in the study, of which 294 (9.76%) were diagnosed with ATB-DILI; 2 108 patients were in the training set and 904 in the test set. The results of multiple logistic regression analysis showed that age, history of liver diseases, hypoalbuminemia, and no preventive use of liver protection drugs were independent risk factors for the occurrence of ATB-DILI. Based on these risk factors, multiple logistic regression model equations were constructed. The results of deep learning and analyzing the patient data of the training set by CNN showed that the top 5 risk factors that had the greatest impact on the occurrence of ATB-DILI were history of liver disease, age, no preventive use of liver protection drugs, hypoalbuminemia, and alcohol consumption. The CNN model was constructed according to the top 5 risk factors. The total accuracy in predicting the occurrence of ATB-DILI in the training and test sets using the multiple logistic regression model was 87.62% and 88.27%, respectively, and the total accuracy of using CNN model was 92.36% and 91.70%, respectively. The sensitivity, specificity, and AUC of the CNN model were all higher than those of the multiple logistic regression model, and the differences were statistically significant (all P<0.05). Conclusion:Both the multiple logistic regression model and CNN model have good predictive performance for the occurrence of ATB-DILI, and the prediction performance of CNN model is better, comparatively.

Objective:To develop 2 prediction models for anti-tuberculosis drug-induced liver injury (ATB-DILI) based on convolutional neural network (CNN) and multiple logistic regression, and to evaluate and compare the performance of the 2 models.Methods:The clinical and laboratory test data of inpatients in the Third People′s Hospital of Zhenjiang, Jurong People's Hospital, and the Third People′s Hospital of Danyang from January 1, 2019 to October 31, 2022 were collected. According to whether ATB-DILI occurred, patients were divided into with and without ATB-DILI groups, and the clinical characteristics of the 2 groups were compared. The patients were randomly divided into training set and test set according to a ratio of 7∶3 by random number table method. Based on data in the training set, multiple logistic regression and CNN were used to develop ATB-DILI prediction models; based on data in the training and test sets, the accuracy of the 2 models in predicting ATB-DILI was verified. The receiver operating characteristic (ROC) curve was drawn, and the sensitivity, specificity, Youden index and area under the curve (AUC) of the 2 models were compared.Results:A total of 3 012 patients were included in the study, of which 294 (9.76%) were diagnosed with ATB-DILI; 2 108 patients were in the training set and 904 in the test set. The results of multiple logistic regression analysis showed that age, history of liver diseases, hypoalbuminemia, and no preventive use of liver protection drugs were independent risk factors for the occurrence of ATB-DILI. Based on these risk factors, multiple logistic regression model equations were constructed. The results of deep learning and analyzing the patient data of the training set by CNN showed that the top 5 risk factors that had the greatest impact on the occurrence of ATB-DILI were history of liver disease, age, no preventive use of liver protection drugs, hypoalbuminemia, and alcohol consumption. The CNN model was constructed according to the top 5 risk factors. The total accuracy in predicting the occurrence of ATB-DILI in the training and test sets using the multiple logistic regression model was 87.62% and 88.27%, respectively, and the total accuracy of using CNN model was 92.36% and 91.70%, respectively. The sensitivity, specificity, and AUC of the CNN model were all higher than those of the multiple logistic regression model, and the differences were statistically significant (all P<0.05). Conclusion:Both the multiple logistic regression model and CNN model have good predictive performance for the occurrence of ATB-DILI, and the prediction performance of CNN model is better, comparatively.

OBJECTIVE: To investigate the change of fasting serum adiponectin in obstructive sleep apnea-hypopnea syndrome (OSAHS) patients. METHOD: Forty males with OSAHS and forty age-matched male normal controls were included in the study. Subjects in OSAHS group were divided into two sub-groups according to body mass index (BMI): obese OSAHS group (BMI > or =25, n=26) and non-obese group OSAHS (BMI <25, n=14). All subjects underwent an overnight sleep study. The serum adiponectin levels were measured by ELISA. RESULT: (1) Except for BMI,compared with control subjects, levels of fasting adiponectin level were significantly lower in OSAHS subjects (P < 0.05). (2) In obese OSAHS sub-group, serum adiponectin level was negatively correlated with BMI and AHI. However, serum adiponectin level was positively correlated with the minimum oxygen saturation. There were similar correlations between serum adiponectin level and sleep parameters in non-obese OSAHS sub-group. CONCLUSION Despite age and BMI, fasting adiponectin level was significantly lower in OSAHS patients than that in control subjects. And fasting adiponectin level was correlated with BMI, AHI and the minimum oxygen saturation. OSAHS is one of the main reasons of the decreased adiponectin.
Adiponectin ; blood ; Adult ; Case-Control Studies ; Humans ; Male ; Middle Aged ; Sleep Apnea, Obstructive ; blood ; Young Adult

Objective To investigate the apoptosis of poly morphonuclear neutrophil(PMN)and the reversion of recombinant human granulocyte colony-stimulating factor(G-CSF)in acute lung injury.Methods 30 guinea pigs were randomly divided into three groups:control group,oil acid group(OA group),OA+G-CSF group.Both OA group and OA+G-CSF group had intraveneos injection of oleic acid(0.12ml/kg)to induce acute lung injury.OA+G-CSF group had G-CSF 0.5μg/kg injection once a day for 2 days.Control group had injection of normal saline.All the 3 groups took BALF 2 hours later.PMNs were isolated by density gradient centrifugation.PMN apoptosis was detecded by Terminal deoxynucleotidy transferase-mediated dUTP biotin nick end labeling(TUNEL).Results PMN apoptosis of BALFs of OA group,OA+G-CSF group and control group were(2.5±1.080)%,(3.5±0.850)%and(6.4±1.505)%.The level of PMN apoptosis of BALF of OA group compared with OA+G-CSF group and control group were decreased markedly(P＜0.01 for each).Conclusion The apoptosis of PMN in acute lung injury is delayed,and persistent activation of PMN and release of toxic content is closely related to lung injury.G-CSF can reverse the level of apoptosis of PMN in acute lung injury.

By combining the teaching environment and taking the multimedia teaching system as the platform,we adopted the nimble utilization teaching method in physiology teaching process which fully aroused the students'enthusiasm in studies,and played the certain impetus role to students' quality enhancement.