November 21, 2022 – Artificial intelligence It can improve diagnosis and treatment for patients, but first it must make AI-enabled clinical tools readily available and usable.
New search from Mayo Clinic found that clinicians who heavily adopted an AI-enabled clinical decision support tool were twice as likely to diagnose left ventricular depression ejection fraction As low users of the tool. The study published in Mayo Clinic procedures, found a large variance in the rate of adoption of AI recommendations. Doctors with high adoption tended to be less experienced in dealing with patients with complex health problems, but age, gender, years of experience, and number of patients cared for were not important factors.
“It was amazing to see the huge difference in the diagnosis rate between high adopters and low adopters,” he says. David Rushlow, MDMayo Clinic physician and chair Family medicine at Mayo Clinic in the Midwest. “The tool is very useful, but we didn’t expect to see a complete doubling of the diagnosis rate for low ejection fracture compared to low adopters.”
The ejection fraction measures the percentage of blood that leaves the heart each time it contracts. Low ejection fraction can be caused by a weakening of the heart muscle, such as cardiomyopathy, as well as heart valve problems, uncontrolled high blood pressure, or damage from a heart attack.
Early diagnosis and treatment of patients with low ejection fraction is critical to reduce the risk of symptomatic heart failure, hospitalization and mortality. “AI decision-support tools have the potential to be very effective in helping to diagnose serious health conditions before typical clinical symptoms appear, and may outpace traditional diagnostic methods,” says Dr. Ruchlow.
Physicians at 48 Mayo Clinic primary care practices in Minnesota and Wisconsin participated in the randomized controlled trial, which included 358 physicians, nurse practitioners, and physician assistants, of whom 165 were randomized to the AI arm and included in the current adoption analysis. The AI algorithm was run on 22,641 patients with the disease Electrocardiography (ECG) performed between August 5, 2019, and March 31, 2020. Clinicians randomized to the intervention group had access to a screening report, which showed an AI-ECG scan as positive or negative; Physicians who were randomized to usual care did not have access.
When the report was negative, further testing was not recommended, but when it was positive, the recommendation was to ‘consider a request for a Echocardiogram“Physicians also received an email alert when an AI-ECG scan was positive, indicating that patients had a high probability of a previously unrecognized low ejection fraction.
“The clinicians most likely to follow AI’s decision-assistance recommendations were the least experienced in dealing with complex patients,” says Dr. Ruchlow. “This illustrates the importance of AI systems that seamlessly integrate into clinicians’ workflows. Due to the technical nature of AI in healthcare, it is often initiated and developed in academic specialty practices. To maximize the benefits of AI, more collaboration is needed between specialty practices and care primary”.
Mayo Clinic holds a patent for AI technology and may receive financial benefits from it, but will not benefit financially from its use in patient care at Mayo Clinic. Co-authors Isaac Attia, Dr.And the Paul Friedman, MDAnd the Francisco Lopez Jimenez, MDYou may also receive financial benefits from this Agreement. The remaining co-authors reported no competing interests.
The study was supported in part by the Mayo Clinic Robert D. and Patricia E. Kern Center for the Sciences of Health Care Delivery.
for more information: https://www.mayoclinic.org/