Samany Najmeh Neysani, Toomanian Ara, Maher Ali, Hanani Khatereh, Zali Ali Reza
Department of GIS & RS, Faculty of Geography, University of Tehran, Iran.
School of Management and Medical Education, Shahid Beheshti University of Medical Sciences, Tehran, Iran.
Land use policy. 2021 Oct;109:105725. doi: 10.1016/j.landusepol.2021.105725. Epub 2021 Aug 30.
Investigations on the spatial patterns of COVID-19 spreading indicate the possibility of the virus transmission by moving infected people in an urban area. Hospitals are the most susceptible locations due to the COVID-19 contaminations in metropolises. This paper aims to find the riskiest places surrounding the hospitals using an MLP-ANN. The main contribution is discovering the influence zone of COVID-19 treatment hospitals and the main spatial factors around them that increase the prevalence of COVID-19. The innovation of this paper is to find the most relevant spatial factors regarding the distance from central hospitals modeling the risk level of the study area. Therefore, eight hospitals with two service areas for each of them are computed with [0-500] and [500-1000] meters distance. Besides, five spatial factors have been considered, consist of the location of patients' financial transactions, the distance of streets from hospitals, the distance of highways from hospitals, the distance of the non-residential land use from the hospitals, and the hospital patient number. The implementation results revealed a meaningful relation between the distance from the hospitals and patient density. The RMSE and R measures are 0.00734 and 0.94635 for [0-500 m] while these quantities are 0.054088 and 0.902725 for [500-1000 m] respectively. These values indicate the role of distance to central hospitals for COVID-19 treatment. Moreover, a sensitivity analysis demonstrated that the number of patients' transactions and the distance of the non-residential land use from the hospitals are two dominant factors for virus propagation. The results help urban managers to begin preventative strategies to decrease the community incidence rate in high-risk places.
对新冠病毒传播空间模式的调查表明，在城市地区移动感染者存在病毒传播的可能性。由于大都市中新冠病毒的污染，医院是最易受影响的场所。本文旨在使用多层感知器人工神经网络（MLP-ANN）找出医院周边风险最高的地方。主要贡献在于发现新冠治疗医院的影响区域以及其周边增加新冠病毒传播率的主要空间因素。本文的创新之处在于，通过对研究区域的风险水平进行建模，找出与距中心医院距离最相关的空间因素。因此，计算了八家医院，每家医院有两个服务区，距离分别为[0 - 500]米和[500 - 1000]米。此外，还考虑了五个空间因素，包括患者金融交易地点、街道与医院的距离、高速公路与医院的距离、非居住用地与医院的距离以及医院患者数量。实施结果揭示了距医院距离与患者密度之间存在有意义的关系。对于[0 - 500米]，均方根误差（RMSE）和相关系数（R）分别为0.00734和0.94635，而对于[500 - 1000米]，这些值分别为0.054088和0.902725。这些值表明距中心医院的距离对新冠治疗的作用。此外，敏感性分析表明，患者交易数量和非居住用地与医院的距离是病毒传播的两个主要因素。研究结果有助于城市管理者启动预防策略，以降低高风险地区的社区发病率。
