This Artificial Intelligence predicts if an infected person will die from Covid-19

Published by: MRT

Published on:

Esta Inteligencia Artificial predice si un infectado morirá por Covid-19

In March 2020 the nightmare began (in the West). And as of June 2021, it’s not over yet. We have been living with a historic pandemic at a global level for more than a year, and although vaccines are already making us see the light at the end of the tunnel ever closer, the daily data continues to reflect that every day people continue to be infected with Covid-19. And what’s worse: he keeps dying from the damn bug.

For this reason, and given that we are going to live with Covid-19 for a long time even if it does not hit as hard as it did in its ‘debut’, the tools to identify it quickly are necessary. And if they can also identify if the infected subject has a greater risk of perishing, even better. This is what one specifically does, an Artificial Intelligence capable of tracking the ‘signature’ of the Coronavirus in a person’s body.

The AI ​​that detects Covid-19

A new artificial intelligence (AI) technology to detect increased blood vessel inflammation can calculate a person’s risk of death from Covid-19 and Covid-19 variants. Technology could be used to tailor their treatment and give them the best chance of recovery, depending on a new investigation sponsored by the University of Oxford and presented today at the British Cardiovascular Society conference.

Severe cases of Covid-19 have been associated with a “cytokine storm”, in which the virus’s “spike” protein triggers the immune system to kick in and produce a wave of harmful molecules called cytokines. The Covid-19 “signature” detects the red flags. Now, using routine chest CT scans, researchers have developed a Covid-19 “signature” using machine learning.

Variants of the coronavirus

This “signature” detects biological signals in the fat surrounding the blood vessels of the chest to measure the level of vascular inflammation caused by cytokines in people infected with the virus. The team applied the Covid-19 signature to chest CT scans of 435 people admitted to Oxford, Leicester and Bath hospitals, and compared the degree of inflammation and risk of death in people with and without Covid-19.

In the case of patients admitted to the hospital, the level of inflammation of the blood vessels caused by cytokines was much higher in those with Covid-19, and even higher in patients infected with variant B.1.1.7 or “alpha”, first identified in the UK.

Vascular inflammation, the key

Patients with a high level of vascular inflammation were up to eight times more likely to die in hospital, and they were the ones that responded best to the anti-inflammatory drug Dexamethasone. Covid-19 patients with elevated vascular inflammation treated with Dexamethasone had 6 times lower risk of dying than Covid-19 patients who were not given the drug.

By using this tool to obtain an inflammation score, Covid-19 patients who had a lot of inflammation in their blood vessels, and therefore an increased risk of death, could potentially receive anti-inflammatory drugs to reduce their risk and help their recovery. long term. Currently, clinical trials are studying the efficacy of this approach.

Track post-Covid 19 effects

Now, researchers will continue to watch the impact of coronavirus variants as they emerge. They claim that their technology may have immense potential to easily track the long-term cardiovascular effects of Covid-19 and respond quickly to future viruses.

Professor Charalambos Antoniades, Professor of Cardiovascular Medicine and Principal Clinical Investigator at the BHF in the Radcliffe Department of Medicine at the University of Oxford, argues that “By simply adding one more step to the routine care of people admitted to hospital with Covid-19 already undergoing a CT scan, we can now detect patients at high risk for life-threatening complications and we could tailor his treatment to aid long-term recovery. “

“But the benefits don’t stop there. We know that this exaggerated immune response to the virus can also cause abnormal blood clotting, so we are developing this AI platform to specifically identify Covid-19 patients who are at higher risk of future heart attack or stroke. We can also easily pivot our platform to develop a new scanning ‘signature’ to better understand future viruses and diseases taking over our population. “


Disclaimer: This article is generated from the feed and not edited by our team.