Your browser doesn't support javascript.
loading
Montrer: 20 | 50 | 100
Résultats 1 - 7 de 7
Filtrer
Plus de filtres








Gamme d'année
1.
Article de Chinois | WPRIM | ID: wpr-993643

RÉSUMÉ

Objective:To explore indicators related to visceral fat index by constructing a random forest model.Methods:In this cross-sectional study, the laboratory measures and body composition analysis records of 617 hospital employees (in-service and retired) who underwent physical examination in Heilongjiang Provincial Hospital Health Management Center from March to September 2021 were selected. The subjects were divided into a training set ( n=411) and a test set ( n=206) with the ratio of 2∶1. A total of 110 predictors were included in the model. The model was constructed with the training set and was evaluated with the test set. The optimal number of nodes and decision trees were selected to evaluate the prediction performance of the optimal model. And the top 10 relatively important factors were selected for further investigation. The 617 participants were further divided in to groups according to the visceral fat index: the normal or high visceral fat index group, and the differences of the top 10 relatively important factors were further compared between the two groups. Results:The optimal number of nodes of the final random forest model was 39 and the number of decision trees was 300. The accuracy, precision, sensitivity and specificity of the model was 83.3%, 73.9%, 89.4% and 78.7%, respectively. The area under the receiver operating characteristic curve and 95% confidence interval of the model was 0.881 (0.832-0.931). The top 10 relatively important factors in the model were body mass index, gender, age, serum uric acid, red blood cell count, monocyte cell count, C-peptide, carcinoembryonic antigen, glycosylated hemoglobin and glutamyl transpeptidase. There were significant differences in the up-mentioned 10 indicators between the subjects with normal and high visceral fat index (all P<0.05). Conclusions:The random forest model built in this study has good performance in predicting visceral fat index, and visceral fat is related with changes in liver function, pancreas function and immune function.

2.
Article de Anglais | WPRIM | ID: wpr-898831

RÉSUMÉ

Purpose@#To generate the under-sampling pattern using a self-supervised learning framework based on a graph convolutional network. @*Materials and Methods@#We first decoded the k-space data into the graph and put it into the network. After the processing of graph convolution layers and graph pooling layers, the network generated the under-sampling pattern for MR reconstruction.We trained the network on the simulated brain dataset enabled by the selfsupervised learning strategy. We did simulation along with the in vivo brain and liver experiments under different noise levels and accelerating factors to compare the performance between the proposed method and traditional methods using the PSNR and SSIM index. @*Results@#The simulation experiments showed that the proposed method can achieve the best performance with low accelerating factors (2 and 3) at all noise levels and in high accelerating factors (4 and 5) at high noise levels (50 and 70 dB). In in vivo experiments, the proposed method attained the highest PSNR and SSIM in the brain dataset as well as in the liver dataset after fine tuning on a small liver dataset. @*Conclusion@#The self-supervised learning framework based on a graph convolutional network was able to design the under-sampling mask for MR reconstruction. The superior performance in the simulation and in vivo experiments demonstrated the feasibility and flexibility of the proposed method and its potential in clinical use.

3.
Article de Anglais | WPRIM | ID: wpr-891127

RÉSUMÉ

Purpose@#To generate the under-sampling pattern using a self-supervised learning framework based on a graph convolutional network. @*Materials and Methods@#We first decoded the k-space data into the graph and put it into the network. After the processing of graph convolution layers and graph pooling layers, the network generated the under-sampling pattern for MR reconstruction.We trained the network on the simulated brain dataset enabled by the selfsupervised learning strategy. We did simulation along with the in vivo brain and liver experiments under different noise levels and accelerating factors to compare the performance between the proposed method and traditional methods using the PSNR and SSIM index. @*Results@#The simulation experiments showed that the proposed method can achieve the best performance with low accelerating factors (2 and 3) at all noise levels and in high accelerating factors (4 and 5) at high noise levels (50 and 70 dB). In in vivo experiments, the proposed method attained the highest PSNR and SSIM in the brain dataset as well as in the liver dataset after fine tuning on a small liver dataset. @*Conclusion@#The self-supervised learning framework based on a graph convolutional network was able to design the under-sampling mask for MR reconstruction. The superior performance in the simulation and in vivo experiments demonstrated the feasibility and flexibility of the proposed method and its potential in clinical use.

4.
Article de Chinois | WPRIM | ID: wpr-862143

RÉSUMÉ

Objective To explore the feasibility of low dose Gemstone Spectrum CT in guiding percutaneous lung puncture biopsy. Methods Totally 80 patients underwent Gemstone Spectrum CT-guided lung puncture biopsy were enrolled. Conventional dose and low-dose CT (noise index [NI]=20, 24, 28) scanning in turn were performed on the progress of biopsy location. The quality of CT image, CT volume dose index (CTDIvol), dose length product (DLP) and effective dose (ED) were compared between conventional dose and low dose CT images. Results Both conventional dose and low dose CT images clearly showed the location relationship between puncture needle and lesion and met the need of puncture. There was no statistical significance of CT image quality among low dose CT images of NI=20, 24, 28 and conventional dose CT images (P=0.08). Meanwhile, significant differences of CTDIvol, DLP and ED were found among low doses CT images of NI=20, 24, 28 and conventional dose CT images (all P<0.01). With the increasing of NI, CTDIvol, DLP and ED decreased gradually (all P<0.05). Conclusion Low-dose scanning scheme of Gemstone Spectrum CT could meet the need of percutaneous lung puncture biopsy and reduce the radiation dose.

5.
Article de Chinois | WPRIM | ID: wpr-468199

RÉSUMÉ

Objective To analyze the adverse reactions of hysterosalpingography and prevention measures. Methods Totally 6 352 patients who underwent hysterosalpingography in our hospital between January 2006 and December 2013 were analyzed. Results Totally 836 cases had adverse reactions of different degrees including 312 cases of drug reactions and 626 cases of non?drug reactions. The adverse drug reactions were mainly hy?pogastralgia,laryngopharyngeal malaise,irritating cough,nausea,vomiting,shortness of breath,flush of the face,and pruritus. The non?drug reac?tions were mainly hypogastralgia,nausea,vomiting,pallor,speeding up of heart?beat,decreased blood pressure,dizziness,and blur version. Con?clusion Among patients who were negative for iodine anaphylactic test,there were still some who had adverse reactions of different degrees during HSG. Targeting at different conditions of reactions,corresponding prevention measures should be adopted to ensure the smooth progress of hysterosal?pingography.

6.
The Journal of Practical Medicine ; (24): 3720-3722, 2014.
Article de Chinois | WPRIM | ID: wpr-461730

RÉSUMÉ

Objective To investigate the sedative effects and the adverse reactions in the elderly patients received different speed of dexmedetomidine (Dex) intravenous infusion. Methods Eighty elderly cases were randomly divided into four groups. Group D0 was the control group, while the group D1, D2 and D3 were the trial groups. The heart rates, blood pressure, SpO2, Ramsay sedation score and Narcotrend value were recorded. Results The sedation onset time of the D2, D3 group was faster than those in the D0 and D1 groups (P 0.05). Conclusion Intravenous infusion of Dex by doses of 0.75 ~ 1.0 μg/(kg·h) during hip surgery in the elderly patients under spinal anesthesia could lead to a safe and effective sedation.

7.
Article de Chinois | WPRIM | ID: wpr-430397

RÉSUMÉ

Objective To analyze the management and outcomes of patients with ST-segment elevation myocardial infarction (STEMI) in Liaoning province.Methods The data were collected from a prospective and multicenter registry study including 8 tertiary hospitals and 12 secondary hospitals in Liaoning province.Total 1429 patients with acute STEMI admitted to hospitals from June 2009 to June 2010 were included in the study.A unified follow-up questionnaire was applied on patient discharged.Results The average age of patients was (63 ± 13)years.37.4% of patients recognized the disease as heart disease and 39.7% were transported by emergency ambulance with a median symptom-to-door time of 150 min.52.9% patients underwent emergency reperfusion therapy,including fibrinolytic therapy (24.4%) and primary percutaneous coronary intervention (PCI,28.1%).The in-hospital treatment included aspirin (99.6%),clopidogrel (81.9%),statins (90.1%),low molecular weight heparin (89.5%),β-blocker (66.0%),angiotensin converting enzyme inhibitor (ACEI)/ angiotensin receptor blocker (ARB)(66.6%).The in-hospital mortality was 10.7% ; the mortality in females was higher than that in males (18.3% vs.7.9%,P < 0.01) and the mortality in older patients (≥ 65 years) was higher than that in younger patients (<65 years)(17.0% vs.5.2%,P <0.01).The follow-up treatment included:aspirin (81.1%),clopidogrel (45.0%),statins (61.0%),β-blocker (48.3%),ACEI/ARB (42.4%).The follow-up mortality was 5.0% after hospital discharge.Conclusions Longer pre-hospital delay is commonly seen in STEMI patients.There is still certain gap of emergency reperfusion therapy and the evidence-based medication with related clinical guidelines of STEMI management in Liaoning.

SÉLECTION CITATIONS
DÉTAIL DE RECHERCHE