Predicting Atrial Fibrillation with AI
Predict and detect an episode of Atrial Fibrillation (arrhythmia) with Artificial Intelligence (AI)
Atrial Fibrillation (AFib or AF) is an irregular or quivering heartbeat (arrhythmia) that can lead to stroke, blood clots, heart failure, and other heart-related complications. It is a pathology that affects 2% of the world population.
Normally, the heart contracts and relaxes to a regular beat. In atrial fibrillation, the upper chambers of the heart (the atria) beat irregularly instead of beating effectively to move blood into the ventricles. Atrial Fibrillation can double the risk of heart-related deaths and is associated with a higher risk of stroke. Around 15-20 percent of people who experience strokes have atrial fibrillation as a condition.
Even though atrial fibrillation is a pathology that is impacting approximately 140 million people worldwide, it is a pathology that is largely undetected.
Kantify’s breakthrough in Atrial Fibrillation
Over the past few years, our team has worked with Dr Jean-Marie Gregoire, a cardiologist at IRIDIA, the AI Laboratory of the Universite Libre de Bruxelles (ULB). Together, we have successfully developed an Artificial Intelligence model that can predict an upcoming event of atrial fibrillation in patients. This is particularly noteworthy because it was not previously known that atrial fibrillation events showed any symptoms before the occurrence of an AFib episode.
Our model is a world-first and can predict Atrial Fibrillation at an individual level, without any historic data about the patient, except for their RR-intervals collected through a Holter monitor. The model was trained on a dataset of more than ten thousand individual anonymized cardiac monitoring data, collected and annotated over multiple years.
Paving the way for new protocols
We managed to create a world-first algorithm to predict an episode of atrial fibrillation. Our AI model can predict an atrial fibrillation incident 30 seconds before the fibrillation episode starts. Predicting an atrial fibrillation event at the individual level in patients paves the way for new treatment protocols, early detection, and prevention.
Towards prevention of atrial fibrillation episodes
30 seconds may not sound like a lot, but for people with pacemakers, these few seconds represent an opportunity for the pacemaker to intervene and therefore prevent the episode of fibrillation from starting by performing overdrive pacing.
AI is transforming healthcare, and early detection of diseases is one of the most promising areas of development. By powering a new generation of systems that equip clinicians with smart tools, AI will lead the way in a new era of exciting breakthroughs in patient care. Let’s get in touch to discover how you can use AI for early detection of heart abnormalities.