Connect with us
  • Elysium

Neuro rehab technology

The future of stroke: AI-guided screening

“We believe that atrial fibrillation screening has great potential, but currently the yield is too low and the cost is too high to make widespread screening a reality”



A new study is exploring AI-guided screening using electrocardiograms (ECGs) data in order to detect a hidden risk factor for stroke.

Researchers used AI in order to evaluate patients’ ECGs in a targeted strategy to screen for atrial fibrillation, which is a common heart rhythm disorder.

Atrial fibrillation is an irregular heartbeat that can cause blood clots with the potential to travel to the brain and cause a stroke, however, it is largely under diagnosed.

In this digitally-enabled, decentralised study, AI was able to identify new cases of atrial fibrillation that would have gone previously undetected during routine care at clinics.

Previous research had already developed an AI algorithm to identify patients with a high likelihood of previously unknown atrial fibrillation. 

Dr Peter Noseworthy, lead author of the study says: “We believe that atrial fibrillation screening has great potential, but currently the yield is too low and the cost is too high to make widespread screening a reality. 

“This study demonstrates that an AI-ECG algorithm can help target screening to patients who are most likely to benefit.”

How the study worked

The study group involved 1,003 patients for continuous monitoring and used another 1,003 patients from usual care as real-world controls.

The findings revealed that AI can indeed identify a subgroup of high-risk patients who would benefit from further intensive heart monitoring in order to detect atrial fibrillation, therefore supporting an AI-guided targeted screening strategy.

ECG’s are used for a wide variety of diagnostics, however, due to atrial fibrillation occurring in short bursts, the chances of catching an episode on a single 10-second ECG tracing is low.

Patients can undergo continuous or intermittent cardiac monitoring methods that have a higher rate of detection, though they are resource-intensive and expensive.

This is where the AI-guided ECG can come in to play.

Thanks to the AI algorithm, patients who display a normal rhythm on the day of the ECG, the algorithm can show if they may have an increased risk of undetected episodes of atrial fibrillation at other times. 

Those patients can then undergo additional monitoring to confirm the diagnosis.

Senior author of the study, Dr Xiaoxi Yao says: “Traditional screening programs select patients based on age (65 or older) or the presence of conditions such as high blood pressure. 

“These approaches make sense because advanced age is one of the most important risk factors for atrial fibrillation. 

“However, it is not feasible to repeatedly conduct intensive heart monitoring in more than 50 million older adults across the country.

“The study shows that an AI algorithm can select a subgroup of older adults who might benefit more from intensive monitoring. 

“If this new strategy is broadly implemented, it could reduce undiagnosed atrial fibrillation, and prevent stroke and death in millions of patients across the globe.”

What is next?

Next for the research team, is a multi centre hybrid trial which focuses on the effectiveness of implementing the AI-ECG workflow in diverse clinical settings and patient populations.

Dr Noseworthy says: “We hope that this approach will be particularly valuable in resource-constrained environments where the rate of undetected atrial fibrillation may be particularly high, and resources to detect it may be limited. 

“However, more work is needed to overcome barriers to implementation, and further studies must evaluate targeted screening strategies in these environments.

“Our ultimate goal is to prevent strokes. I believe the current study has brought us one step closer.”