Researchers at the University of Minnesota, working with Epic, say they’ve validated an artificial intelligence algorithm that can assess chest X-rays for potential cases of COVID-19.
The tool, which was also developed in collaboration with M Health Fairview and already deployed at its 12 hospitals, will be made available through Epic to other providers.
WHY IT MATTERS
The new algorithm is able to evaluate X-rays as soon as the image is taken, say University of Minnesota Medical School researchers. In just seconds, the tool looks for patterns associated with COVID-19. If it recognizes them, the clinicians can see within the Epic system that the patient likely has the virus, they said.
To develop the algorithm, a team of U of M experts led by Ju Sun, assistant professor at the U of M College of Science and Engineering, analyzed de-identified chest X-rays that had been taken at M Health Fairview since January.
To train the AI to diagnose COVID-19 specifically, the researchers used 100,000 X-rays of patients who did not have the virus and 18,000 X-rays of patients who did.
Once the algorithm was validated, Dr. Genevieve Melton-Meaux, chief analytics and care innovation officer for M Health Fairview, worked with Epic and her Fairview colleagues to build an infrastructure around it, integrating with the electronic health record software to enable easier access for care teams.
U of M and Fairview teams will now make the AI tool available for free in the Epic App Orchard.
Drew McCombs, an Epic developer who worked closely with the U of M and Fairview, says customers can install the algorithm via Epic’s Cognitive Computing platform and begin end-user training in as few as 10 days.
“Our Cognitive Computing platform quickly pulls the X-ray, runs the algorithm, and shows the resulting prediction directly in Epic software that doctors, nurses, and support staff use every day — speeding up treatment and helping protect staff. The algorithm is available to healthcare organizations around the world that use Epic.”
THE LARGER TREND
There have been many AI and machine learning innovations developed in recent months for the fight against COVID-19, especially around imaging and diagnostics.
For instance, researchers from Mount Sinai Health System in New York showed this summer how they trained AI with imaging and clinical data to rapidly detect COVID-19 in patients.
They demonstrated how algorithms, in conjunction with chest CT scans and patient history, could more quickly diagnose patients and improve detection of patients who presented with normal CT scans.
“We were able to show that the AI model was as accurate as an experienced radiologist in diagnosing the disease, and even better in some cases where there was no clear sign of lung disease on CT,” said Dr. Zahi Fayad, director of the BioMedical Engineering and Imaging Institute at the Icahn School of Medicine at Mount Sinai, in a statement.
Just this week, researchers at University of Central Florida showed how algorithms could learn to classify COVID-19 pneumonia with as much as 90% accuracy, and distinguish cases from those caused by influenza.
But in the bigger picture, AI’s track record for sifting through COVID-19 data has been less than perfect so far. Many observers feel that, in the early days of the pandemic, at least, AI fell short in slowing its spread, with a shortage of good data to fuel new models leading to “anti-constructive” insights.
Other research, such as a recent article in the Journal of the American Medical Informatics Association, has shown how dissemination of “under-developed and potentially biased models” may worsen COVID-19 health disparities for people of color.
ON THE RECORD
“This may help patients get treated sooner and prevent unintentional exposure to COVID-19 for staff and other patients in the emergency department,” said Dr. Christopher Tignanelli, assistant professor of surgery at the University of Minnesota Medical School and co-lead on the U of M, Fairview and Epic algorithm project, in a statement.
“This can supplement nasopharyngeal swabs and diagnostic testing, which currently face supply chain issues and slow turnaround times across the country,” he said.
“Using this tool gives us the ability to reduce the spread of COVID-19 and save lives, so sharing it with other health systems makes a lot of sense,” added Melton-Meaux in statement. “Especially in regions with high infection rates or potentially less access to testing, the fight against COVID-19 requires all of us to work together.”
Twitter: @MikeMiliardHITN
Email the writer: [email protected]
Source: Read Full Article