Scientists have developed an artificial intelligence model that has the ability to predict the occurrence of cardiac arrhythmias. This model is currently being tested by healthcare professionals in Paris hospitals. This innovation is also a sign that the field of medicine is open to such initiatives and no longer afraid to work hand in hand with new tools of this kind.
Predicting the risk of cardiac arrhythmias through the use of artificial intelligence could soon be part of standard medical care. While the concept may still cause many to raise their eyebrows and express skepticism, largely because of how artificial intelligence is portrayed in the media, the field of medicine is exploring how it can benefit from some of the advantages of deep learning. In their article , published in the European Heart Journal, the scientists explain how their work could be valuable in predicting the risk of occurrence of Torsades de Pointes, a potentially fatal heart disorder. They consider the fears surrounding AI in this regard "unjustified ... most of these new methodologies are just complex and elegant ways to use a rather old instrument: pattern recognition."
And it is within the Paris hospital system that the model is carrying out its first tests with scientists from France's IRD, INSERM and the Sorbonne. So how does it work? The artificial intelligence applies a model that will analyze the signals representing the electrical activity of the heart like an ECG, then will measure the duration of the wave intervals. In this model it is the QT interval which designates the time lapse between the beginning of the polarization and the repolarization of the heart's ventricles. It is by measuring the duration between the two waves that the model is able to predict certain cardiac arrhythmias.
Does the future of medicine involve artificial intelligence?
For several years now, charters of ethics regarding AI principles for medicine have been emerging. While some critics are calling for greater transparency and true verification modules -- and rightfully so -- it is clear that artificial intelligence is continuing to evolve and contribute to new approaches within the medical field. An article in the British Medical Journal questioned whether it was useful in some areas with some models showing less accuracy in screening than experienced radiologists. However, there may be areas and cases where it does prove useful, and scientists are cautiously hopeful. For instance, while 50% of cases of Torsade de Pointes are asymptomatic, artificial intelligence algorithms can detect it almost every time.
In their study, the researchers explain why they're optimistic that this technique holds potential: "the possibility that the risk of life-threatening arrhythmia might be reduced by involving patients in monitoring their own risk with an easy-to-use wearable device that uses AI to detect tell-tale ECG changes well in time for them to call on their physician and for the physician to take appropriate life-saving actions may no longer belong to science fiction."