Generating High-Granularity COVID-19 Territorial Early Alerts Using Emergency Medical Services and Machine Learning.

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.

Business Intelligence applied to Emergency Medical Services in the Lombardy region during SARS-CoV-2 epidemic.

BACKGROUND AND AIM OF THE WORK: On the 21st of February, the first patient was tested positive for SARS-CoV-2 at Codogno hospital in the Lombardy region. From that date, the Regional Emergency Medical Services (EMS) Trust (AREU) of the Lombardy region decided to apply Business Intelligence (BI) to the management of EMS during the epidemic. The aim of the study is to assess in this context the impact of BI on EMS management outcomes. METHODS: Since the beginning of the COVID-19 outbreak, AREU is using BI daily to track the number of first aid requests received from 112. BI analyses the number of requests that have been classified as respiratory and/or infectious episodes during the telephone dispatch interview. Moreover, BI allows identifying the numerical trend of episodes in each municipality (increasing, stable, decreasing). RESULTS: AREU decides to reallocate in the territory the resources based on real-time data recorded and elaborated by BI. Indeed, based on that data, the numbers of vehicles and personnel have been implemented in the municipalities that registered more episodes and where the clusters are supposed to be. BI has been of paramount importance in taking timely decisions on the management of EMS during COVID-19 outbreak.  Conclusions: Even if there is little evidence-based literature focused on BI impact within the health care, this study suggests that BI can be usefully applied to promptly identify clusters and patterns of the SARS-CoV-2 epidemic and, consequently, make informed decisions that can improve the EMS management response to the outbreak.