AI Recommendations Lead to More Diagnoses of Low LVEF Diagnoses

AI Recommendations Lead to More Diagnoses of Low LVEF Diagnoses

Spread the love

A team led by Dr. David Rushlow of the Mayo Clinic in Rochester, MN, compared the performance of a group of clinicians who had access to electrocardiogram (ECG) analysis of an AI algorithm and a group that had none. The researchers found that those who were alerted by the algorithm to high-risk low LVEF cases were more likely to order echocardiograms and were twice as likely to identify low LVEF patients.

They also found that clinicians with less complex patients are more likely to be high adopters of AI tools, and those who are more likely to follow AI tool recommendations were less experienced in AI tools. the treatment of complex patients.

“[Our findings underscore] the importance of clinician training and engagement, and AI systems that integrate seamlessly into the workflows of busy caregivers,” Rushlow and colleagues wrote.

Adoption of AI technology in healthcare remains low, with critics pointing out that AI studies mostly deal with small retrospective data sets. Moreover, few studies have explored the characteristics of high adopters compared to more hesitant clinicians, as well as the clinical outcomes related to these two approaches.

Rushlow et al wanted to do this for both groups in the case of a diagnosis of low LVEF. They defined adoption as the clinician ordering an echocardiogram — the gold standard imaging test for diagnosing low LVEF — within three months of receiving the AI-enabled EKG alert.

The study authors looked at data from a total of 165 clinicians and 11,573 patients. They found that among patients with positive AI EKGs, high adopters (n=41) were twice as likely to diagnose patients with low LVEF (33.9%) compared to low adopters (n=124) with an odds ratio of 1.62 (16.9%).

When analyzing the results of patients with AI-activated negative EKGs, the researchers found no difference in the rate of echocardiogram ordering between the high and low adoption groups. They wrote that this suggests that high adopters are not just indiscriminately ordering more echocardiogram tests.

“In fact, despite the doubling of diagnostic yield, the high adopter group only ordered 35% more echocardiograms in patients flagged by the AI ​​EKG,” they added.

They also found that high adopters were more often advanced practice providers, such as nurse practitioners and physician assistants, and tended to have less complex patients.

The authors noted that this study shows the power of collaboration between specialist practice and primary care. They called for greater collaboration between specialty practices and primary care to maximize the benefits of AI in healthcare.

Copyright © 2022

Leave a Comment

Your email address will not be published.