Content of the article
Scientists may have found a way to identify who is susceptible to long COVID, thanks to machine learning and artificial intelligence.
Using machine learning, the researchers sifted through hundreds of characteristics to predict who might develop long COVID.
Scientists may have found a way to identify who is susceptible to long COVID, thanks to machine learning and artificial intelligence.
COVID long, or post-COVID-19 condition, is estimated to affect one in ten patients who have already contracted the virus. The most common symptoms are fatigue, memory problems, trouble sleeping, shortness of breath, anxiety and depression in the weeks and months following an illness, according to the government of canadaand may be severe enough to impact the patient’s ability to work.
Now, scientists from the University of North Carolinasay they trained three machine learning models to identify the most important characteristics and risk factors for long COVID and identify a cohort of potential long COVID patients.
“These findings are a testament to the powerful impact of real-world clinical data…to help better understand and find solutions to important public health issues such as long COVID,” said Joni Rutter, acting chair of NCATS.
Researchers used machine learning to identify common characteristics of COVID-19 patients who later presented to long-term clinics.
“Characterizing, diagnosing, treating and caring for patients with long-term COVID has proven to be a challenge due to the list of characteristic symptoms continuously changing over time,” said study first author Emily Pfaff. in a press release. statement. “We needed to gain a better understanding of the complexities of long COVID, and for that it made sense to leverage modern data analytics tools and a unique big data resource like N3C, where many features of long COVID are represented.
Patient data such as demographics, healthcare visits, medical conditions, and prescription drug orders of patients before and after contracting COVID-19 were collected from the National COVID Cohort Collaborative (N3C ). The N3C is a database containing information on more than 13 million Americans from 72 regions of 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 had been identified as having long 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 visited a healthcare site with a long COVID treatment center (indicating they had access to COVID long care). follow up to see who from this second list attended a lengthy COVID clinic.
The most important characteristics of long-term participants in the COVID clinic were: shortness of breath, difficulty breathing, pre-existing diabetes or chronic kidney disease. To be on or to have taken Albuterol (a respiratory medicine, eg for asthma), metoprolol (medicine for angina pectoris and high blood pressure) and/or melatonin were also common patient characteristics. Having the COVID vaccine or taking dexamethasone seemed to influence against needing treatment for long COVID.
The researchers noted that their data disproportionately represents patients who are more likely to use (and possibly trust) healthcare clinics, hospitalized patients, as well as those with more initial symptoms. serious.
The N3C team plans to continue refining the AI learning process with more data, which means more people will be identified as potentially long-lasting COVID patients.
Additional types of long COVID, which affect some people differently, will also be explored, along with potential treatment options.
“Depending on where the research leads, we may find that patients with different presentations of long COVID are different enough to warrant entirely different treatments,” Pfaff said. “It is therefore important for us to determine whether long COVID is a disease, or a constellation of related conditions that are also linked to having had acute COVID-19.”
The study was sponsored by the National Center for Advancing Translational Sciences, an organization that turns scientific breakthroughs and discoveries into new treatments or cures.
The researchers add that through their efforts to quickly identify large swaths of patients using AI, better research methods will soon be available to study more COVID patients and more treatment options.
Chris Arnold is a Toronto-based writer.
Thank you for your support. If you liked this story, send it to a friend. Every share counts.