Risk-Aware Travel Path Planning Algorithm Based on Reinforcement Learning during COVID-19

The outbreak of COVID-19 brought great inconvenience to people's daily travel. In order to provide people with a path planning scheme that takes into account both safety and travel distance, a risk aversion path planning model in urban traffic scenarios was established through reinforcement learning. We have designed a state and action space of agents in a 'point-to-point';way. Moreover, we have extracted the road network model and impedance matrix through SUMO simulation, and have designed a Restricted Reinforcement Learning-Artificial Potential Field (RRL-APF) algorithm, which can optimize the Q-table initialization operation before the agent learning and the action selection strategy during learning. The greedy coefficient is dynamically adjusted through the improved greedy strategy. Finally, according to different scenarios, our algorithm is verified by the road network model and epidemic historical data in the surrounding areas of Xinfadi, Beijing, China, and comparisons are made with common Q-Learning, the Sarsa algorithm and the artificial potential field-based reinforcement learning (RLAFP) algorithm. The results indicate that our algorithm improves convergence speed by 35% on average and the travel distance is reduced by 4.3% on average, while avoiding risk areas, compared with the other three algorithms.

Life-Cycle Spatial Strategy for Multidimensional Health-Oriented Medical Care Community—From the Perspective of Sustainable Marketing

The aging population and the increasing number of sub-healthy people in all age groups in China have brought huge opportunities for related industries. From the perspective of marketing and consumer psychology, there is a great demand for health care properties, especially those that provide long-term medical care. Against this situation, almost all the leading real estate companies have entered this field and tried to occupy more market shares through different products and brand marketing sustainably. In this context, it is urgent to explore a comprehensive community model combining medical and nursing care that covers all stages of life, so as to promote the health of diverse populations. In China, existing research on the growth of medical care communities for sustainable needs started relatively late, and insufficient attention has been paid to the supply–demand linkage among psychological demand, health behavior, spatial bearing, and service supply. Taking Wuzhishan city for example, we deduce the Medical-Care Maslow’s Hierarchy of Needs System according to classical theories. Based on motivation theory and marketing strategy, a theoretical model of Health demand-behavior-facilities and Spatial Interaction (HBSI) mediated by healthy behavior is constructed. Then, expert group decision making processes and the Fuzzy Delphi Method (DFM) were used to screen 67 spatial impact factors of 14 categories in five dimensions, including life safety, physical health, mental health, social adaptation and resilience recovery, which fit users’ multi-dimensional health needs. Finally, to provide a spatial strategy reference for the construction of sustainable and adaptive medical caring communities, spatial planning strategies and guidelines are offered based on correlation analysis, so as to fit the changeable market pattern, meet the psychological expectations and life-cycle caring needs of consumers.

Genetic mechanisms of critical illness in Covid-19 (preprint)

The subset of patients who develop critical illness in Covid-19 have extensive inflammation affecting the lungs and are strikingly different from other patients: immunosuppressive therapy benefits critically-ill patients, but may harm some non-critical cases. Since susceptibility to life-threatening infections and immune-mediated diseases are both strongly heritable traits, we reasoned that host genetic variation may identify mechanistic targets for therapeutic development in Covid-19. GenOMICC (Genetics Of Mortality In Critical Care, genomicc.org) is a global collaborative study to understand the genetic basis of critical illness. Here we report the results of a genome-wide association study (GWAS) in 2790 critically-ill Covid-19 patients from 208 UK intensive care units (ICUs), representing >95% of all ICU beds. Random controls were drawn from three distinct UK population studies. We identify and replicate several novel genome-wide significant associations including variants chr19p13.3 (rs2109069, P = 3.98 x 10-12), within the gene encoding dipeptidyl peptidase 9 (DPP9), and at chr21q22.1 (rs2236757, P = 4.99 x 10-8) in the interferon receptor IFNAR2. Consistent with our focus on extreme disease in younger patients with less comorbidity, we detect a stronger signal at the known 3p21.31 locus than previous studies (rs73064425, P = 1.2 x 10-27). We identify potential targets for repurposing of existing licensed medications. Using Mendelian randomisation we found evidence in support of a causal link from low expression of IFNAR2, and high expression of TYK2, to life-threatening disease. Transcriptome-wide association in lung tissue revealed that high expression of the monocyte/macrophage chemotactic receptor CCR2 is associated with severe Covid-19. We detected genome-wide significant gene-level associations for genes with central roles in viral restriction (OAS1, OAS2, OAS3). These results identify specific loci associated with life-threatening disease, and potential targets for host-directed therapies. Randomised clinical trials will be necessary before any change to clinical practice.