Guevara Cesar, Penas Matilde Santos
Centre of Mechatronics and Interactive Systems (MIST)Universidad Tecnológica Indoamérica Quito 170301 Ecuador.
Institute of Knowledge Technology, Complutense University of Madrid 28040 Madrid Spain.
IEEE Access. 2020 Nov 5;8:201925-201936. doi: 10.1109/ACCESS.2020.3036347. eCollection 2020.
In this study, the Intelligent Infectious Diseases Algorithm (IIDA) has been developed to locate the sources of infection and survival rate of coronavirus disease 2019 (COVID-19), in order to propose health care routes for population affected by COVID-19. The main goal of this computational algorithm is to reduce the spread of the virus and decrease the number of infected people. To do so, health care routes are generated according to the priority of certain population groups. The algorithm was applied to New York state data. Based on infection rates and reported deaths, hot spots were determined by applying the kernel density estimation (KDE) to the groups that have been previously obtained using a clustering algorithm together with the elbow method. For each cluster, the survival rate -the key information to prioritize medical care- was determined using the proportional hazards model. Finally, ant colony optimization (ACO) and the traveling salesman problem (TSP) optimization algorithms were applied to identify the optimal route to the closest hospital. The results obtained efficiently covered the points with the highest concentration of COVID-19 cases. In this way, its spread can be prevented and health resources optimized.
在本研究中，开发了智能传染病算法（IIDA）来确定2019冠状病毒病（COVID-19）的感染源和存活率，以便为受COVID-19影响的人群提出医疗保健路线。这种计算算法的主要目标是减少病毒传播并减少感染人数。为此，根据特定人群组的优先级生成医疗保健路线。该算法应用于纽约州的数据。基于感染率和报告的死亡人数，通过对先前使用聚类算法和肘部方法获得的组应用核密度估计（KDE）来确定热点地区。对于每个聚类，使用比例风险模型确定存活率——这是确定医疗护理优先级的关键信息。最后，应用蚁群优化（ACO）和旅行商问题（TSP）优化算法来确定前往最近医院的最佳路线。获得的结果有效地覆盖了COVID-19病例浓度最高的点。通过这种方式，可以防止其传播并优化卫生资源。
