Based on the reports by doctors in Italy on limiting ventilators for Coronavirus patients, and overburdened hospitals spread throughout Europe, data scientists have put efforts to build a mathematical model that will help hospitals forecast what they might face in the coming days or weeks basis the number of COVID-19 cases in their respective areas.
The model primarily offered to administrators at the University of Pennsylvania hospitals illustrates how they could increase capacity within weeks.
Penn data scientist Corey Chivers said, “The intention is to see what the capacity requirements for hospitalization, intensive care, and ventilators might be,” he added, “The more we can get a handle on whether capacity is too low for what an area can expect, the more a hospital system can take steps” to address that shortfall.
Factoring in the risk that COVID-19 will overburden hospitals in the US, just like Wuhan in China, and then northern Italy, the states are taking preventive measures by canceling a variety of public events to work on social distancing measures so that COVID-19 cases do not flood hospitals like a viral tsunami.
Hospitals are doing their bit by rescheduling regular checkups of cancer patients (not treatments), postponing surgeries that can wait, to give doctors and nurses more room to pay more attention to handle COVID-19 cases.
CHIME (Covid-19 Hospital Impact Model for Epidemics) built by Penn’s Chivers and others in “predictive healthcare,” is essentially an epidemiological tool for infectious diseases spread called a SIR model.
So basically, it works on the number of susceptible (S) people in an area (in case of Coronavirus, it is everyone, since no one is immune to the new coronavirus that is responsible for it). Next comes the number of infected people (I), and the last element here is the number of people recovered (R).
The model here makes use of current estimates, the duration of the infection (14 days), next considers the number of new cases caused by an infected person (known as effective reproduction number which is about 2.5) and the number of COVID-19 patients that need to be hospitalized, and then comes the percentage of patients that need ICU or ventilator and the period of stay of these three.
Taking all these factors into consideration, the CHIME model can help hospitals forecast what they need to be ready for in times of the COVID-19 pandemic.