Researchers have developed an artificial intelligence (AI) model that can diagnose SARS-CoV-2 (COVID-19) with comparable efficacy as a professional radiologist, while preserving the privacy of patient data. The findings were published in journal Nature Machine Intelligence.
The technique, developed by researchers from the University of Cambridge and the Huazhong University of Science and Technology, utilized a method called federated learning to develop their model.
Since the beginning of the COVID pandemic, AI researchers have strived to construct models that could diagnose the disease. However, many of these models were built using low-quality data, as highlighted by the researchers. “AI has a lot of limitations when it comes to COVID-19 diagnosis, and we need to carefully screen and curate the data so that we end up with a model that works and is trustworthy,” said co-first author Hanchen Wang from Cambridge’s Department of Engineering via a press release. “Where earlier models have relied on arbitrary open-sourced data, we worked with a large team of radiologists from the NHS and Wuhan Tongji Hospital Group to select the data, so that we were starting from a strong position.”
Here’s a social distancing strategy that really worked in the early days of the pandemic: New research shows that providing hotel rooms to homeless people at high risk for severe COVID-19 significantly lowered their chance of infection.
In early April 2020, the city of Chicago made 200 rooms at a hotel available to homeless people in shelters who were considered at high risk because they were: at least 60; at least 55 with any underlying health condition; or younger than 55 years with HIV/AIDS or any other health condition known to substantially increase COVID-19 risk.
The participants also received extensive health and social support services, and could stay as long as desired during the five months that the rooms were available.
“We saw that people in this intervention were 2.5 times less likely to contract the virus compared to rates among people experiencing homelessness in shelters across the city,” said study co-author Dr. Elizabeth Tung. She is an assistant professor of medicine at University of Chicago Medicine.
Patients who develop acute kidney injury (AKI) during SARS-CoV-2 infection face increased risk of morbidity and mortality. AKI can occur at any stage of infection with COVID-19; clinical judgment and awareness of AKI risk factors in combination with early detection and diagnosis are key in preventing short- and long-term complications in patients with AKI related to COVID-19.
The ability of two-dose COVID-19 vaccines to protect against symptomatic infection by the Omicron variant falls significantly short, but a booster shot provides considerable protection, according to the first real-world study of how effective vaccines are against the rapidly spreading new form of the coronavirus.
Four months after their second dose of the Pfizer-BioNTech vaccine, people had only about 35% protection against symptomatic infection by Omicron, which is significantly lower than against the Delta variant, British government scientists said.