Objective To develop a neural network-based deep learning model for predicting postoperative recurrence in thyroid tumor patients and validate the model with external datasets for providing clinicians with a reliable decision support tool.Methods An artificial neural network structure was adopted in the study,with thyroid tumor data from the SEER database serving as the training set.External validation was conducted with open-source data from the University of California,Irvine(UCIrvine),and the data from 100 patients at a general tertiary hospital in Hunan province.The model's accuracy and reliability in predicting recurrence were evaluated through multiple performance metrics.Results Experimental results showed that the model outperformed Logistic model in recurrence prediction,with accuracy,recall rate,precision and F1 score reaching 0.915 3,0.981 8,0.921 1 and 0.947 4 in internal validation.Moreover,the model achieved accuracies,recall rates,precisions,F1 scores and ROC_AUC values of 0.832 9,0.945 5,0.841 4,0.890 4 and 0.78 on the UCIrvine validation set,while 0.870 0,0.880 0,0.862 7,0.871 3 and 0.80 on the local validation set.Conclusion This neural network-based predictive model exhibits excellent performance in thyroid tumor recurrence prediction,providing clinicians with a valuable decision support tool that can help optimize postoperative treatment plans and improve patient prognosis management.

Objective To explore the mechanism through which dexmedetomidine(Dex)alleviates doxorubicin(Adr)-induced myo-cardial injury via regulating nuclear factor κB(NF-κB)expression.Methods Sprague-Dawley rats were divided into control,Adr,and Adr+Dex groups.Theirs hearts were harvested for hematoxylin and eosin(HE)staining,immunohistochemical staining,real-time polymerase chain reaction(PCR),and Western blotting anlyses.The rat primary cardiomyocytes,breast cancer cell line MDA-MB-23,lung cancer cell line H226,gastric cancer cell line AGS,and bladder cancer cell line 5637 were cultured and divided into control,Adr,Adr+Dex,Dex,and Adr+Dex+NF-κBi groups.CCK-8 and immunofluorescence staining were performed to detect the reactive oxygen species(ROS)contents.Results The myocardial arrangement of the rats in the Adr group was disordered,myocardial cell activity was lower,the mitochondrial membrane potential was lower,ROS production was higher,and NF-κB mRNA and protein contents were sub-stantially lower than those in the control group.The cardiomyocyte morphology was improved,cell activity was higher,mitochondrial mem-brane potential was increased,ROS production decreased,and NF-κB expression significantly increased in the Adr+Dex group compared with those in the control group.The mitochondrial membrane potential in the Adr+Dex+NF-κBi group was lower,and ROS generation was increased compared with the control group.The activity of the tumor cells in the Adr group was lower,and no statistically significant diffe-rences were found compared with that in the Adr+Dex group.Conclusion Treatment with Dex may not affect the chemotherapeutic effects of Adr.Dex administration may increase the myocardial mitochondrial membrane potential and reduce ROS generation by regu-lating NF-κB levels,thereby reducing Adr-induced myocardial damage.

Objective To develop a three-dimensional(3D)deep neural network based preoperative classification model for coronary computed tomography angiography(CTA)in atrial fibrillation patients,and to explore the effects of transfer learning on the performance of medical image classification models,thereby providing preoperative decision support for catheter ablation to advance atrial fibrillation treatment toward precision and personalization.Methods Utilizing 3D ConvNet and 3D ResNet as backbone network,the three-dimensional classification features were extracted from coronary CTA sequences.The publicly available pre-trained weights were used for transfer learning.The model performance was evaluated through metrics such as confusion matrix,classification accuracy,and area under the curve(AUC).A comparative analysis was also conducted to evaluate the performance differences between the transfer learning model and the initialized training model.Results Transfer learning yielded significant performance improvements over the initialized training models,attaining AUC improvement of 9.1%-16.7%and accuracy enhancement of 6.2%-23.5%.Among all models,3D-ResNet18 model with MedicalNet pre-training weights performed the best,achieving an AUC of 0.77 and an accuracy of 0.71.Conclusion The proposed three-dimensional deep network enhanced by transfer learning can effectively identify atrial fibrillation patients requiring additional ablation besides pulmonary vein isolation through preoperative coronary CTA,which will assist clinicians in optimizing surgical strategies and improving treatment outcomes,thereby reducing long-term postoperative recurrence rates.

Objective To develop a neural network-based deep learning model for predicting postoperative recurrence in thyroid tumor patients and validate the model with external datasets for providing clinicians with a reliable decision support tool.Methods An artificial neural network structure was adopted in the study,with thyroid tumor data from the SEER database serving as the training set.External validation was conducted with open-source data from the University of California,Irvine(UCIrvine),and the data from 100 patients at a general tertiary hospital in Hunan province.The model's accuracy and reliability in predicting recurrence were evaluated through multiple performance metrics.Results Experimental results showed that the model outperformed Logistic model in recurrence prediction,with accuracy,recall rate,precision and F1 score reaching 0.915 3,0.981 8,0.921 1 and 0.947 4 in internal validation.Moreover,the model achieved accuracies,recall rates,precisions,F1 scores and ROC_AUC values of 0.832 9,0.945 5,0.841 4,0.890 4 and 0.78 on the UCIrvine validation set,while 0.870 0,0.880 0,0.862 7,0.871 3 and 0.80 on the local validation set.Conclusion This neural network-based predictive model exhibits excellent performance in thyroid tumor recurrence prediction,providing clinicians with a valuable decision support tool that can help optimize postoperative treatment plans and improve patient prognosis management.

Objective To develop a three-dimensional(3D)deep neural network based preoperative classification model for coronary computed tomography angiography(CTA)in atrial fibrillation patients,and to explore the effects of transfer learning on the performance of medical image classification models,thereby providing preoperative decision support for catheter ablation to advance atrial fibrillation treatment toward precision and personalization.Methods Utilizing 3D ConvNet and 3D ResNet as backbone network,the three-dimensional classification features were extracted from coronary CTA sequences.The publicly available pre-trained weights were used for transfer learning.The model performance was evaluated through metrics such as confusion matrix,classification accuracy,and area under the curve(AUC).A comparative analysis was also conducted to evaluate the performance differences between the transfer learning model and the initialized training model.Results Transfer learning yielded significant performance improvements over the initialized training models,attaining AUC improvement of 9.1%-16.7%and accuracy enhancement of 6.2%-23.5%.Among all models,3D-ResNet18 model with MedicalNet pre-training weights performed the best,achieving an AUC of 0.77 and an accuracy of 0.71.Conclusion The proposed three-dimensional deep network enhanced by transfer learning can effectively identify atrial fibrillation patients requiring additional ablation besides pulmonary vein isolation through preoperative coronary CTA,which will assist clinicians in optimizing surgical strategies and improving treatment outcomes,thereby reducing long-term postoperative recurrence rates.

Objective To explore the mechanism through which dexmedetomidine(Dex)alleviates doxorubicin(Adr)-induced myo-cardial injury via regulating nuclear factor κB(NF-κB)expression.Methods Sprague-Dawley rats were divided into control,Adr,and Adr+Dex groups.Theirs hearts were harvested for hematoxylin and eosin(HE)staining,immunohistochemical staining,real-time polymerase chain reaction(PCR),and Western blotting anlyses.The rat primary cardiomyocytes,breast cancer cell line MDA-MB-23,lung cancer cell line H226,gastric cancer cell line AGS,and bladder cancer cell line 5637 were cultured and divided into control,Adr,Adr+Dex,Dex,and Adr+Dex+NF-κBi groups.CCK-8 and immunofluorescence staining were performed to detect the reactive oxygen species(ROS)contents.Results The myocardial arrangement of the rats in the Adr group was disordered,myocardial cell activity was lower,the mitochondrial membrane potential was lower,ROS production was higher,and NF-κB mRNA and protein contents were sub-stantially lower than those in the control group.The cardiomyocyte morphology was improved,cell activity was higher,mitochondrial mem-brane potential was increased,ROS production decreased,and NF-κB expression significantly increased in the Adr+Dex group compared with those in the control group.The mitochondrial membrane potential in the Adr+Dex+NF-κBi group was lower,and ROS generation was increased compared with the control group.The activity of the tumor cells in the Adr group was lower,and no statistically significant diffe-rences were found compared with that in the Adr+Dex group.Conclusion Treatment with Dex may not affect the chemotherapeutic effects of Adr.Dex administration may increase the myocardial mitochondrial membrane potential and reduce ROS generation by regu-lating NF-κB levels,thereby reducing Adr-induced myocardial damage.

OBJECTIVES: Reforming medical insurance payment methods is a key part of deepening the healthcare system reform. Understanding the influencing factors and underlying mechanisms of physicians' strategic behaviors under the diagnosis-related groups (DRG) payment system is crucial for reducing medical resource waste and improving the efficiency of health insurance fund utilization. METHODS: Based on the Theory of Planned Behavior, this study used grounded theory to construct a questionnaire encompassing belief, behavioral attitude, subjective norm, perceived behavioral control, behavioral intention, and behavior measurement items. Structural equation modeling was then used for empirical analysis. RESULTS: Physicians' behavioral intention had the most significant impact on their strategic behavior (β=0.606, P<0.001). Physician's attitude toward strategic behavior (β=-0.159, P<0.01), subjective norm (β=-0.093, P<0.05), and perceived behavioral control (β=-0.120, P<0.05) were major influencing factors of behavioral intention. Physicians' behavioral beliefs, normative beliefs, and control beliefs were significantly correlated with behavioral attitude (β=0.554, P<0.001), subjective norm (β=0.383, P<0.001), and perceived behavioral control (β=0.274, P<0.001), respectively. CONCLUSIONS Behavioral intention is the primary predictor driving physicians to engage in strategic behavior. Attitudes toward the behavior, subjective norms, and perceived behavioral control all significantly affect physicians' behavioral intentions.
Humans ; Physicians/psychology* ; Surveys and Questionnaires ; Attitude of Health Personnel ; Diagnosis-Related Groups/economics* ; Intention ; Female ; Male ; Adult

OBJECTIVES: Clinical research plays a vital role in disease research and population health. The public is the main source of clinical research volunteers. Understanding the public's cognition of clinical research plays a decisive role in the development of clinical research. This study aims to understand the Chinese public's cognition for clinical research and the influencing factors. METHODS: The questionnaire based on Chinese-translated Public Awareness of Research for Therapeutic Advancements through Knowledge and Empowerment (PARTAKE) was used to investigate the public's cognition for clinical research. RESULTS: Of the 2 513 valid respondents, 91.84% had heard of "clinical research", 91.76% of the respondents believed that clinical research was beneficial to society, 65.90% were willing to participate in clinical research, 87.50% believed that confidentiality was a very important thing, 73.70% believed that their personal information had been protected when participating in clinical research, and, 46.40% did not know whether volunteers participating in clinical research could receive adequate compensation. Educational levels, employment status, and annual income impacted in public perceptions of willingness to participate in clinical research, especially in privacy protection, informed consent, whether clinical research is intended for society, compensation for clinical research, and safety of clinical research (all P<0.01). CONCLUSIONS The Chinese public's cognition level for clinical research is acceptable, but there is still a lot of room for improvement in privacy protection, informed consent, and compensation. By designing a reasonable knowledge training program for clinical research and using the multimedia, improving access to the relevant knowledge, more public will know about clinical research recruitment information, which is of great significance for the development of clinical research in China.
Humans ; China ; East Asian People ; Educational Status ; Surveys and Questionnaires ; Public Opinion ; Knowledge ; Biomedical Research

Adverse childhood experience (ACE) is potentially negative experience that occurs between 0 and 18 years old. The ACE adolescents have prominent mental health problems such as emotional regulation disorder, unstable interpersonal relationship, poor coping ability, and cognitive dysfunction. Until now, the factors affecting the mental health of ACE adolescents are not clear, but it is certain that the ecosystem in which ACE adolescents life affects their mental health. Specifically, the parent-child relationship, the school environment, the peer relationship in the micro-system, and the interaction between the parent-child relationship and other interpersonal relationship in the meso-system have been confirmed to be significantly related to the mental health of ACE adolescents. In the appearance system, the neighborhood cohesion, the level of family income, the educational level of parents and the different social and cultural background in the macro-system all have different degrees of impact on the development of ACE adolescents' psychological behaviors. In the diachronic system, the time and frequency of suffering from ACE have different effects on the mental health regarding the ACE adolescents.
Adolescent ; Adverse Childhood Experiences ; Child ; Child, Preschool ; Ecosystem ; Health Status ; Humans ; Infant ; Infant, Newborn ; Mental Health ; Parents

Objective:To explore the effect of network medication guidance on anticoagulation management of warfarin.Methods:The study was designed as the retrospective cohort study. Study subjects were selected from patients who underwent cardiac valve replacement during January 2018 and April 2019 in the Department of Cardiovascular Surgery of Xiangya Hospital, Central South University, and took oral warfarin for 3 months or more after operation. According to the mode of revisit, the patients were divided into 4 groups: 1-month post-operation network group (INR review results were uploaded online for more than 2 times within 1 month after operation), 1-month post-operation control group (INR was reviewed in Xiangya Hospital 1 month after the operation and INR data was recorded), 3-month post-operation network group (INR review results were uploaded online for more than 4 times within 3 months after operation), and 3-month post-operation control group (INR was reviewed in Xiangya Hospital 3 months after the operation and INR data was recorded). The gender and age distribution of patients in the network group and the control group, as well as INR and INR compliance rate at 1 or 3 months after operation were compared.Results:A total of 420 patients underwent cardiac valve replacement in Xiangya Hospital during the study period, and all of them were prescribed warfarin for anticoagulation. Among the 420 patients, 266 patients (63.3%) had network or Xiangya Hospital revisit records 1 month after operation, 71 of which were included in the 1-month post-operation network group and 178 of which in the 1-month post-operation control group; 132 (31.4%) patients had network or Xiangya Hospital revisit records 3 month after operation, 46 of which were included in the 3-month post-operation network group and 77 of which in the 3-month post-operation control group. Patients in the 1-month post-operation network group had lower age, higher INR compliance rate, and lower incidence of insufficient anticoagulation than those in the 1-month post-operation control group, and the differences were all statistically significant [(49±10) years vs. (53±11) years, P=0.009; 64.8%(46/71) vs. 45.5%(81/178), P=0.006; 21.1%(15/71) vs. 46.6%(83/178), P<0.001]. Patients in the 3-month post-operation network group had higher INR, higher INR compliance rate, and lower incidence of insufficient anticoagulation than those in the 3-month post-operation control group, and the differences were all statistically significant [(2.05±0.45) vs. (1.84±0.62), P=0.044; 67.4% (31/46) vs. 30.9% (30/97), P=0.002; 30.4% (14/46) vs. 54.5% (42/77), P=0.009]. Conclusions:Network medication guidance is helpful to improve the effect of warfarin anticoagulation management and improve the INR compliance rate of patients after cardiac valve replacement. The main manifestation of substandard anticoagulation is insufficient anticoagulation, which should be paid attention to.