The epidemic of coronavirus-disease-2019 (COVID-19) started in Italy with the first official diagnosis on 21 February 2020; hence, it is now known how many cases were already present in earlier days and weeks, thus limiting the possibilities of conducting any retrospective analysis. We hypothesized that an unbiased representation of COVID-19 diffusion in these early phases could be inferred by the georeferenced calls to the emergency number relevant to respiratory problems and by the following emergency medical services (EMS) interventions. Accordingly, the aim of this study was to identify the beginning of anomalous trends (change in the data morphology) in emergency calls and EMS ambulances dispatches and reconstruct COVID-19 spatiotemporal evolution on the territory of Lombardy region. Accordingly, a signal processing method, previously used to find morphological features on the electrocardiographic signal, was applied on a time series representative of territorial clusters of about 100,000 citizens. Both emergency calls and age- and gender-weighted ambulance dispatches resulted strongly correlated to COVID-19 casualties on a provincial level, and the identified local starting days anticipated the official diagnoses and casualties, thus demonstrating how these parameters could be effectively used as early indicators for the spatiotemporal evolution of the epidemic on a certain territory.
The pandemic of COVID-19 has posed unprecedented threats to healthcare systems worldwide. Great efforts were spent to fight the emergency, with the widespread use of cutting-edge technologies, especially big data analytics and AI. In this context, the present study proposes a novel combination of geographical filtering and machine learning (ML) for the development and optimization of a COVID-19 early alert system based on Emergency Medical Services (EMS) data, for the anticipated identification of outbreaks with very high granularity, up to single municipalities. The model, implemented for the region of Lombardy, Italy, showed robust performance, with an overall 80% accuracy in identifying the active spread of the disease. The further post-processing of the output was implemented to classify the territory into five risk classes, resulting in effectively anticipating the demand for interventions by EMS. This model shows state-of-art potentiality for future applications in the early detection of the burden of the impact of COVID-19, or other similar epidemics, on the healthcare system.
<p><strong>Abstract.</strong> To address the study of the deployment of publicly accessible Automated External Defibrillators (AED), Geomatics allows computing their limited area of effectiveness (i.e. ‘catchment area’, CA), traditionally set as circular surfaces with a 100m-radius. Exploiting open geospatial data related to roads network, also ‘realistic’ CAs, based on the effective walking distance, can be computed. Aim of this study (performed on the territory of Lombardy, Italy, total surface 23,863.65 km<sup>2</sup>, with open source software as QGIS, PostGIS, pgRouting) was to compare the two approaches, and to evaluate if the territory analysis could support case-by-case decision-making about the preferable mapping technique.</p><p>Setting a limit of 200&thinsp;m, realistic CAs were computed for 7702 known AEDs on the territory (at 28/02/2018). The mean area obtained resulted close to that of the traditional 100m-radius circular area (33,665m<sup>2</sup> against 31,415m<sup>2</sup>), but the spatial coverage of 45043 OHCAs - Out-of-Hospital Cardiac Arrests (Lombardy, 1/1/2015 to 31/12/2018) is very different considering realistic or circular areas (15.35% vs 9.43%). The distribution of the mapping error (realistic-CA – circular-CA) and the computation failures of realistic areas were studied and correlated with the characteristics of the surrounding territory considering attributes related to streets, buildings, and land-use, computing linear correlation coefficients and performing Mann-Whitney U-tests. Results suggest that realistic CAs are not always correctly computable and circular areas are preferable when AEDs are far from the streets in less urbanized and more uniform territories. An automatized decision-making about the best case-by-case mapping technique is therefore feasible with open data and open source software.</p>
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.