Anno Sumiko

Introduction: Coronavirus disease (COVID-19) rapidly spread from Wuhan, China to other parts of China and other regions/countries around the world, resulting in a pandemic due to large populations moving through the massive transport hubs connecting all regions of China via railways and a major international airport. COVID-19 will remain a threat until safe and effective vaccines and antiviral drugs have been developed, distributed, and administered on a global scale. Thus, there is urgent need to establish effective implementation of preemptive non-pharmaceutical interventions for appropriate prevention and control strategies, and predicting future COVID-19 cases is required to monitor and control the issue. Methods This study attempts to utilize a three-layer graph convolutional network (GCN) model to predict future COVID-19 cases in 190 regions and countries using COVID-19 case data, commercial flight route data, and digital maps of public transportation in terms of transnational human mobility. We compared the performance of the proposed GCN model to a multilayer perceptron (MLP) model on a dataset of COVID-19 cases (excluding the graph representation). The prediction performance of the models was evaluated using the mean squared error. Results Our results demonstrate that the proposed GCN model can achieve better graph utilization and performance compared to the baseline in terms of both prediction accuracy and stability. Discussion The proposed GCN model is a useful means to predict COVID-19 cases at regional and national levels. Such predictions can be used to facilitate public health solutions in public health responses to the COVID-19 pandemic using deep learning and data pooling. In addition, the proposed GCN model may help public health policymakers in decision making in terms of epidemic prevention and control strategies.

Early warning systems (EWS) have been proposed as a measure for controlling and preventing dengue fever outbreaks in countries where this infection is endemic. A vaccine is not available and has yet to reach the market due to the economic burden of development, introduction and safety concerns. Understanding how dengue spreads and identifying the risk factors will facilitate the development of a dengue EWS, for which a climate-based model is still needed. An analysis was conducted to examine emerging spatiotemporal hotspots of dengue fever at the township level in Taiwan, associated with climatic factors obtained from remotely sensed data in order to identify the risk factors. Machinelearning was applied to support the search for factors with a spatiotemporal correlation with dengue fever outbreaks. Three dengue fever hotspot categories were found in southwest Taiwan and shown to be spatiotemporally associated with five kinds of sea surface temperatures. Machine-learning, based on the deep AlexNet model trained by transfer learning, yielded an accuracy of 100% on an 8-fold cross-validation test dataset of longitudetime sea surface temperature images.