One Coronavirus Detection Algorithm to Rule Them All

Published on October 21, 2020
Coronavirus
Image Credit: [Pixabay/ernestoeslava]

Cases of the coronavirus are surging again in parts of the United States, just in time for flu season. So, AI developers are about to face quite a test. Are they going to be able to assist physicians tell the difference between COVID 19 and the flu. They are both respiratory illnesses, and they have similar symptoms. Also, will machine learning be able to predict which patients are at most risk to become critically ill?

Many Algorithms in The Race

There are several machine learning algorithms that are hoping to do just that. They plan to do so by pouring over the mounds of data taken from symptomatic patients by analyzing chest CT scans and X-rays. AI will become more and more important in determining how much to treat a patient. Also, it can help figure out which patients are most likely to end up in the ICU. This, in turn, will help predict how many ventilators and beds are needed for a given facility. It will also help determine how much other life supporting equipment is required.

That’s on the forefront of everyone’s mind right now. Although both viruses are similarly managed, they are not the same entity, and patients will need different things.

Anna Yaffee – ER Doctor at Emory University

Studies have shown that machine learning systems have been able to detect patterns that define coronavirus at an increasing pace. It’s also already been able to identify which patients are most likely to require a ventilator and other advanced care.

Flu Season is Upon Us

However, those systems weren’t developed in the middle of flu season. It still remains to be seen how a machine learning algorithm will perform under more intricate clinical conditions. There will be a lot of patients that have several different illnesses that will have similar symptoms.

Imaging-based products are going to have a harder time spreading and being implemented without either integration into the electronic health record or some company licensing the technology out to universities directly.

Karandeep Singh – University of Michigan physician

Singh went on to say that machine learning-based imaging-analysis systems have shown their most potential in the identification of the impact of coronavirus on the lungs. It’s also been instrumental in helping doctors get an understanding of the progression of the disease, and how best to treat patients. Researchers in China just published a paper in the scientific journal ‘Nature’. It described an AI that was able to tell the difference between the coronavirus, the flu, and non-viral pneumonia. It was 98% accurate.

Enjoyed this video?
"No Thanks. Please Close This Box!"