MATERIALS AND METHODS: A search for relevant studies published in the last five years was conducted using the databases of Google Scholar, IEEE Xplore, PubMed, Scopus, Springer Link and Web of Science.
RESULTS: Of the 4959 records identified, a total of 29 studies met the inclusion criteria. The findings were reviewed in three areas: social interaction of older adults supported by user interface, the digital technologies used in the user interface, and the effects of user interfaces on the social interactions of older adults.
CONCLUSIONS: Future research should develop digital technologies and service models to enhance the quality of life of older adults. Long-term solutions to promote social interaction in older adults require more user interface support. Community connection-based user interfaces can support existing social relationships and develop new social circles for older adults.
METHOD: This study proposed a single-scale multi-input convolutional neural network (SSMICNN) method to classify ERP signals between aMCI patients with T2DM and the control group. Firstly, the 18-electrode ERP signal on alpha, beta, and theta frequency bands was extracted by using the fast Fourier transform, and then the mean, sum of squares, and absolute value feature of each frequency band were calculated. Finally, these three features are converted into multispectral images respectively and used as the input of the SSMICNN network to realize the classification task.
RESULTS: The results show that the SSMICNN can fuse MSI formed by different features, SSMICNN enriches the feature quantity of the neural network input layer and has excellent robustness, and the errors of SSMICNN can be simultaneously transmitted to the three convolution channels in the back-propagation phase. Comparison with Existing Method(s): SSMICNN could more effectively identify ERP signals from aMCI with T2DM from the control group compared to existing classification methods, including convolution neural network, support vector machine, and logistic regression.
CONCLUSIONS: The combination of SSMICNN and MSI can be used as an effective biological marker to distinguish aMCI patients with T2DM from the control group.
CASE SUMMARY: Two special COVID-19 cases-one full-term pregnant woman and one elderly (72-year-old) man-were treated by veno-venous (VV)-ECMO in the Second People's Hospital of Zhongshan, Zhongshan City, Guangdong Province, China. Both patients had developed refractory hypoxemia shortly after hospital admission, despite conventional support, and were therefore managed by VV-ECMO. Although both experienced multiple ECMO-related complications on top of the COVID-19 disease, their conditions improved gradually. Both patients were weaned successfully from the ECMO therapy. At the time of writing of this report, the woman has recovered completely and been discharged from hospital to home; the man remains on mechanical ventilation, due to respiratory muscle weakness and suspected lung fibrosis. As ECMO itself is associated with various complications, it is very important to understand and treat these complications to achieve optimal outcome.
CONCLUSION: VV-ECMO can provide sufficient gas exchange for COVID-19 patients with acute respiratory distress syndrome. However, it is crucial to understand and treat ECMO-related complications.