1.Effect of timing it right family support program on patients′ uncertainty in illness and relatives care ability of acute myocardial infarction patients with percutaneous transluminal coronary intervention treatment
Zhenchao WU ; Cui ZHANG ; Ningning ZHOU
Chinese Journal of Practical Nursing 2020;36(33):2571-2579
Objective:To investigate the effect of timing it right family support program-based care on patients′ uncertainty in illness and relatives care ability of acute myocardial infarction patients with percutaneous transluminal coronary intervention treatment, and to provide reference for family continuous care of such patients.Methods:A total of 88 patients and relatives admitted to the department of cardiology in Hebei People′s Hospital from March 2018 to May 2019 were randomly divided into intervention group (44 cases) and control group (44 cases). The control group received routine care, while the intervention group received timing it right family support program based on the routine care. Two groups were given follow-up for 6 months, the patients′ uncertainty in illness and relatives care burden and care ability were compared between two groups.Results:3 months, 6 months after discharge, the ambiguity, unpredictability and total uncertainty in illness scores were significantly decreased in the intervention group compared to the control group [(17.89±3.67), (14.56±3.15), (11.82±1.68), (10.31±1.62), (43.21±4.71), (38.31±4.19) vs. (19.83±3.43), (16.85±2.56), (13.29±2.37), (11.90±2.26), (47.34±5.58), (42.24±3.89)], the differences were statically significant ( t value was 2.435-4.351, P<0.05). At discharge and 3 months, 6 months after discharge, the scores of sociability burden were significantly decreased in the intervention group compared to the control group [(4.49±0.99), (3.59±0.79), (2.92±0.35) vs. (5.14±1.22), (3.98±0.82), (3.61±0.67)]; 3 months and 6 months after discharge, the scores of time-depending burden and total burden scores were significantly decreased in the intervention group compared to the control group [(12.79±2.50), (10.51±3.08), (37.31±4.22), (31.72±3.39) vs. (14.61±2.86), (13.32±3.09), (40.34±3.97), (36.19±3.27)]; 6 months after discharge, the scores of development-limited burden were significantly decreased in the intervention group compared to the control group [(7.36±1.11) vs. (8.07±1.31)], the differences were statically significant ( t value was 2.146-6.020, P<0.05). At discharge and 3 months, 6 months after discharge, the scores of learning to cope with new role, providing care according to care-receiver`s needs, managing own emotional needs, appraising supportive resources balancing care-giving needs and own needs and total care ability scores were significantly decreased in the intervention group compared to the control group, the differences were statically significant ( t value was 4.957-25.242, P<0.01). Conclusion:Timing it right family support program can alleviate patients′ uncertainty in illness and improve relatives care abilily of acute myocardial infarction patients with percutaneous transluminal coronary intervention treatment.
2.MF2ResU-Net: a multi-feature fusion deep learning architecture for retinal blood vessel segmentation
Zhenchao CUI ; Shujie SONG ; Jing QI
Digital Chinese Medicine 2022;5(4):406-418
Objective:
For computer-aided Chinese medical diagnosis and aiming at the problem of insufficient segmentation, a novel multi-level method based on the multi-scale fusion residual neural network (MF2ResU-Net) model is proposed.
Methods:
To obtain refined features of retinal blood vessels, three cascade connected U-Net networks are employed. To deal with the problem of difference between the parts of encoder and decoder, in MF2ResU-Net, shortcut connections are used to combine the encoder and decoder layers in the blocks. To refine the feature of segmentation, atrous spatial pyramid pooling (ASPP) is embedded to achieve multi-scale features for the final segmentation networks.
Results:
The MF2ResU-Net was superior to the existing methods on the criteria of sensitivity (Sen), specificity (Spe), accuracy (ACC), and area under curve (AUC), the values of which are 0.8013 and 0.8102, 0.9842 and 0.9809, 0.9700 and 0.9776, and 0.9797 and 0.9837, respectively for DRIVE and CHASE DB1. The results of experiments demonstrated the effectiveness and robustness of the model in the segmentation of complex curvature and small blood vessels.
Conclusion
Based on residual connections and multi-feature fusion, the proposed method can obtain accurate segmentation of retinal blood vessels by refining the segmentation features, which can provide another diagnosis method for computer-aided Chinese medical diagnosis.