Using machine learning, the researchers sifted through hundreds of traits to predict who might develop a long COVID.

content of the article

Scientists may have found a way to determine who is vulnerable to long-COVID, thanks to machine learning and artificial intelligence.

advertising 2

content of the article

Long COVID, or post-COVID-19 condition, is estimated to affect one in ten patients previously infected with the virus. The most common symptoms include exhaustion, memory problems, trouble sleeping, shortness of breath, anxiety and depression in the weeks and months following an illness the government of Canadaand can be severe enough to affect a patient’s ability to work.

Now, Scientists at the University of North Carolinasay they trained three machine learning models to identify key features and risk factors for long COVID and to identify a cohort of potential long COVID patients.

“These results speak to the powerful impact of real-world clinical data…to help better understand and find solutions to major public health problems like COVID-19,” said Joni Rutter, acting chair of NCATS.

advertising 3

content of the article

Shortness of breath, difficulty breathing, pre-existing diabetes, chronic kidney disease are common features of patients with long-term COVID-19 illness

Researchers used machine learning to identify the common characteristics of COVID-19 patients who later presented to clinics with long-standing COVID-19 illness.

“Characterizing, diagnosing, treating, and managing patients with long-term COVID-19 illness has proven challenging as the list of hallmark symptoms continues to evolve over time,” said Emily Pfaff, first author of the study, in a Explanation. “We needed to better understand the complexities of long-COVID, and for that it made sense to use modern data analysis tools and a unique big data resource like N3C, which presents many characteristics of long-COVID.”

advertising 4

content of the article

Patient data such as demographics, doctor visits, medical conditions, and prescription drug orders from patients before and after contracting COVID-19 were collected by the National COVID Cohort Collaborative (N3C). The N3C is a database of information on more than 13 million Americans from 72 territories in the United States, nearly 5 million of whom have tested positive for COVID-19 since the pandemic began in March 2020.

From the N3C results, the researchers compiled a list of nearly 600 patients who were found to have long had COVID. The models were then tested on a cohort of 97,995 adults who had COVID-19 at least 90 days previously and who had attended a healthcare facility with a long-term COVID-19 treatment center (indicating that they had access to long-term COVID-19 care had). Researchers tracked to see who from this second list attended a long COVID clinic.

advertising 5

content of the article

The key characteristics of long-term COVID clinicians were: shortness of breath, difficulty breathing, pre-existing diabetes or chronic kidney disease. To be or have been on Alberol (a breathing drug for e.g. asthma), metoprolol (a drug for angina and high blood pressure) and/or melatonin were also common characteristics of the patients. The COVID vaccination or taking dexamethasone appeared to have an impact on the need for treatment in long COVID.

The researchers found that their data disproportionately represented those patients who were more likely to seek out (and perhaps trust) health clinics, inpatients, and those who had more severe initial symptoms.

advertising 6

content of the article

Further work on the computer models is required

The team at N3C plans to continue refining the AI ​​learning process with more data, meaning more people will later be identified as potentially long-term COVID patients.

Other types of long COVID, different effects on specific individuals, and potential treatment options are also being explored.

“Depending on where the research goes, we may find that patients with different presentations of long COVID are different enough to warrant wildly different treatments,” Pfaff said. “It is therefore important for us to determine whether Long COVID is a disease or a constellation of related diseases that are also associated with acute COVID-19 disease.”

The study was sponsored by the National Center for Advancing Translational Sciences, an organization that converts scientific breakthroughs and discoveries into new treatments or cures.

advertising 7

content of the article

The researchers add that thanks to their efforts to quickly identify large patient populations using AI, better research methods will soon be available to study more COVID patients and more treatment options.

Chris Arnold is a Toronto-based author.

Thank you for your support. If you liked this story, please send it to a friend. Every share counts.

Leave a Reply

Your email address will not be published. Required fields are marked *