A University of Central Florida researcher is part of a new study showing that artificial intelligence can be nearly as accurate as a physician in diagnosing COVID-19 in the lungs.
The study, recently published in Nature Communications, shows the new technique can also overcome some of the challenges of current testing.
Researchers demonstrated that an AI algorithm could be trained to classify COVID-19 pneumonia in computed tomography (CT) scans with up to 90 percent accuracy, as well as correctly identify positive cases 84 percent of the time and negative cases 93 percent of the time.
CT scans offer a deeper insight into COVID-19 diagnosis and progression as compared to the often-used reverse transcription-polymerase chain reaction, or RT-PCR, tests. These tests have high false negative rates, delays in processing and other challenges.
Another benefit to CT scans is that they can detect COVID-19 in people without symptoms, in those who have
MONTREAL — Quebec is getting ready to introduce the federal government’s COVID-19 contact tracing application in the coming days as infections in the province remain on the rise.
Premier Francois Legault told reporters Tuesday in Quebec City the app will be deployed after officials concluded it would take too long to introduce the made-in-Quebec application they had hoped for.
Quebec reported 799 new COVID-19 cases and seven more deaths linked to the novel coronavirus on Tuesday, along with a spike in hospitalizations.
The province has had problems with contact tracing, with health officials in Montreal reporting difficulties tracking down people who were potentially exposed.
Health Minister Christian Dube said Quebec officials looked more closely at the smartphone application during a meeting with Ontario counterparts 10 days ago. While Ontario isn’t fully satisfied, Dube said he hopes Quebecers will use it in large numbers.
People infected by the novel coronavirus can have symptoms that range from mild to deadly. Now, two new analyses suggest that some life-threatening cases can be traced to weak spots in patients’ immune systems.
At least 3.5 percent of study patients with severe COVID-19, the disease caused by the novel coronavirus, have mutations in genes involved in antiviral defense. And at least 10 percent of patients with severe disease create “auto-antibodies” that attack the immune system, instead of fighting the virus. The results, reported in two papers in the journal Science on September 24, 2020, identify some root causes of life-threatening COVID-19, says study leader Jean-Laurent Casanova, a Howard Hughes Medical Institute Investigator at The Rockefeller University.
Seeing these harmful antibodies in so many patients — 101 out of 987 — was “a stunning observation,” he says. “These two papers provide the first explanation for why COVID-19 can be so
The U.S. Centers for Disease Control and Prevention issued and later removed updated guidance on its website to address growing evidence of limited airborne transmission of the virus that caused COVID-19.
It’s already known that the novel coronavirus is most commonly transmitted “through respiratory droplets or small particles, such as those in aerosols, produced when an infected person coughs, sneezes, sings, talks, or breathes.”
On Friday, the CDC also included that “There is growing evidence that droplets and airborne particles can remain suspended in the air and be breathed in by others, and travel distances beyond 6 feet (for example, during choir practice, in restaurants, or in fitness classes),” noting that “In general, indoor environments without good ventilation increase this risk.”