Scientists are using AI to predict which coronavirus patients need ventilators

Navin Bondade 0 Comments Artificial Intelligence, Data Science, Deep Learning, Machine Learning

The number of COVID-19 patients is increasing exponentially & hospitals are facing heavy load in managing them and the resources available to treat the patients. A ventilator is an important resource to fight against COVID-19 but many countries are lacking them, Afghanistan has only 12 ventilators in their whole country.

In order to manage the ventilators efficiently, computer scientists from the University of Copenhagen are using AI to calculate which coronavirus patients need ventilators and intensive care.

Somewhere between 10% and 25% of patients sick with COVID-19 eventually require assistance to breathe. Roughly 5% of patients will develop acute respiratory distress syndrome, at which point only a mechanical ventilator can drive oxygen into their lungs and push fluid out.

Recognizing the difference between those whose survival depends on access to a ventilator and those who can recover with less aggressive breathing assistance has become a vital skill for doctors.

Similar to a doctor the new AI system will help to identify the symptoms that seriously ill patients have in common. Hospitals could use the insights provided by the AI system to work how many patients will need a ventilator at specific times in the future, and plan their resources accordingly.

“We are aware of certain things that increase risks, such as age, smoking, asthma and heart problems, but there are other factors involved,” said Espen Solem, the chief physician of Denmark’s Bispebjerg.

“After all, we hear about young people who end up on ventilators and older people who do well without understanding why. So let’s get the computer to find patterns that we aren’t able to see ourselves.”

This new initiative is being conducted in a collaboration with Rigshospitalet and Bispebjerg Hospital.

“With these AI models, hospitals will be able to know – for example – that 40 percent of their 300 hospitalized patients will probably require a ventilator within one week. This allows them to plan and deploy their resources in the best possible way,” said Mads Nielsen from the University of Copenhagen in Denmark.

Algorithms will harvest vast amounts of data from multiple sources. First, they will find patterns in data from Danish coronavirus patients who have been through the system up until now.

In doing so, doctors hope to identify shared traits among the most severely affected patients. This may turn out to be the number of white blood cells, the use of certain pharmaceuticals or something else.

These patterns will be compared with information from newly hospitalized patients. The data consists of X-rays, tests and measurements taken of patients at the time of their admittance to the hospital, along with their electronic health records.

“All data will go to a supercomputer where, within minutes, our model calculates how likely a specific patient is to require a ventilator, & how many days will go by before such a need arises. That’s our goal,” says Mads Nielsen.

Although the models will not be used as a basis for treating individual patients, they will be used as a planning tool that can still make a big difference for hospital staff. According to Espen Solem:

“It will be a great help if we know from the outset whether an individual patient is someone who we need to pay extra attention to, and reserve capacity for. Danish hospitals are still able to keep up, but the situation could change.”

“We hope that our models will be able to be used during this initial wave of coronavirus infections, otherwise, they will be beneficial during the second wave that we anticipate in autumn,” Nielsen noted.

Source: University of Copenhagen