RESUMEN
Objective:To conduct a predictive analysis of the safety risks in cardiac surgery intensive care unit(ICU)equipment,and to explore the application value of safety risk countermeasure strategies.Methods:The system failure modes and effects analysis(SFMEA)of cardiac surgery ICU equipment was carried out from the main system,subsystem and component levels,and the safety risk level was evaluated by using the triangular fuzzy soft set evaluation information fusion algorithm.The hierarchical management was carried out according to the priority order.A total of 89 medical equipment in clinical use in cardiac surgery ICU of the hospital were selected and divided into control group(79 units)and observation group(82 units,including 72 units in the control group and 10 newly added units)according to different management modes.The equipment in the control group adopted experiential management,the equipment in the observation group adopted predictive management.The system stability,equipment safety and clinical service satisfaction of the two groups were compared.Results:The failure ratio of operating components and functions,mechanical components and functions,electrical source circuits and functions,signal acquisition and processing,data output and storage in the observation group were(1.49±1.02)%,(1.91±1.37)%,(2.21±1.16)%,(0.97±0.67)%and(0.61±0.43)%,respectively,which were lower than those in the control group,the difference was statistically significant(t=3.119,t=3.705,t=4.713,t=3.871,t=4.306;P<0.05).The risk ratios of routine testing equipment,emergency treatment equipment,special treatment equipment and basic medical equipment in the observation group were 7.69%(1/13),10.53%(2/19),0.00%(0/8)and 11.90%(5/42),respectively,which were lower than those in the control group,,the difference was statistically significant(x2=4.887,x2=4.039,x2=5.333,x2=4.082;P<0.05).The satisfaction of hospital staff on clinical service quality of equipment in observation group was 94.59%,which was higher than that in control group,the difference was statistically significant(x2=5.731,P<0.05).Conclusion:The predictive analysis and response management strategies of equipment safety risk in cardiac surgery ICU based on triangular fuzzy soft set evaluation information fusion algorithm can improve the predictability of equipment safety risks in cardiac surgery ICU,enhance the stability of medical equipment system,improve the safety of clinical diagnosis and treatment of medical equipment,and improve the satisfaction of medical equipment management.
RESUMEN
Accurate segmentation of multiple gliomas from multimodal MRI is a prerequisite for many precision medical procedures. To effectively use the characteristics of glioma MRI and im-prove the segmentation accuracy, we proposes a multi-Dice loss function structure and used pre-experiments to select the good hyperparameters (i.e. data dimension, image fusion step, and the implementation of loss function) to construct a 3D full convolution DenseNet-based image feature learning network. This study included 274 segmented training sets of glioma MRI and 110 test sets without segmentation. After grayscale normalization of the image, the 3D image block was extracted as a network input, and the network output used the image block fusion method to obtain the final segmentation result. The proposed structure improved the accuracy of glioma segmentation compared to a general structure. In the on-line assessment of the open BraTS2015 data set, the Dice values for the entire tumor area, tumor core area, and enhanced tumor area were 0.85, 0.71, and 0.63, respectively.
RESUMEN
0.05);and there were significant diffe-rences between the final diagnosis and pre-hospitalized diagnosis in all patients with VE(?2=47.08 P