AI-guided screening uses electrocardiogram data to detect stroke

researchers from Mayo Clinic used artificial intelligence to evaluate patient electrocardiograms in a targeted strategy to examine atrial fibrillation, a common heart rhythm disorder. Atrial fibrillation is an irregular heartbeat that can cause blood clots to form that can travel to the brain and cause a AVC, however, it is highly underdiagnosed. In the decentralized, digitally enabled study, artificial intelligence identified new cases of atrial fibrillation that would not have attracted clinical attention during routine care.

One search A previous study had already developed an artificial intelligence algorithm to identify patients with a high probability of previously unknown atrial fibrillation. The algorithm for detecting atrial fibrillation in the normal sinus rhythm of an electrocardiogram is licensed by Anumana artificial intelligence-driven health technology company, by nference and the Mayo Clinic.

“We are convinced that atrial fibrillation tests have great potential, but the throughput is too low and the cost is too high today to make widespread screening a reality,” says Peter Noseworthy, cardiac electrophysiologist at the Mayo Clinic. and lead author of the study. “This study demonstrates that an artificial intelligence algorithm for electrocardiography can help target triage to patients most likely to benefit.”

The study enrolled 1003 patients for continuous monitoring and used another 1003 routine care patients as real-world controls. The findings were published in The Lancet and demonstrated that artificial intelligence can indeed identify a subgroup of high-risk patients who would benefit most from intensive heart monitoring to detect atrial fibrillation, supporting an AI-guided and targeted screening strategy. .

ECGs are commonly performed to obtain a variety of diagnoses, but because atrial fibrillation can be transient, the chance of detecting an episode in a single 10-second ECG is low. Patients can undergo continuous or intermittent cardiac monitoring approaches that have higher detection rates, but are resource intensive to use in all people and can be difficult and expensive for patients.

Read also  Westerwald sausage hike: Thousands on a culinary journey around Rotenhain - Westerwald newspaper

This is where the artificial intelligence-driven electrocardiogram can come in handy. The artificial intelligence algorithm can identify patients who, even though they have a normal rhythm on the day of the electrocardiogram, may have an increased risk of episodes of underdetected atrial fibrillation at other times. These patients may undergo additional monitoring to confirm the diagnosis.

“Traditional screening programs select patients according to age (65 years and older) or the presence of conditions such as high blood pressure. These approaches are reasonable, as advanced age is one of the most important risk factors for atrial fibrillation. However, it is not feasible to repeatedly conduct intensive cardiac monitoring in more than 50 million older adults across the country,” said Xiaoxi Yao, Ph.D., health outcomes researcher at the Department of Cardiovascular Medicine and Center for Provisional Science. of Health Services Robert D. Kern and Patricia E. Kern of the Mayo Clinic. Yao is the study’s senior author.

“The study demonstrates that the artificial intelligence algorithm can select a subset of older adults who could benefit most from intensive monitoring. If the new strategy is widely used, it could reduce underdiagnosed atrial fibrillation, prevent strokes and the deaths of millions of patients around the world,” says Yao.

The next step in this research will be a multicenter hybrid study focusing on the effectiveness of implementing the artificial intelligence-electrocardiogram workflow in diverse clinical settings and patient populations.

“We expect this approach to be particularly valuable in resource-constrained settings where the rate of underdetected atrial fibrillation may be particularly high and resources for detection may be limited. However, more work will be needed to overcome implementation barriers, and additional studies should evaluate targeted screening strategies in these settings,” states Noseworthy.

Read also  symptoms, causes and treatment!

“Now that we have demonstrated that AI-guided atrial fibrillation screening is possible, we will also need to demonstrate that patients with atrial fibrillation detected in screening benefit from treatment to prevent strokes,” says Noseworthy. “Our ultimate goal is to prevent strokes. I am convinced that the current study brought us closer to that.”