AI has now penetrated and integrated into our daily lives. From conversational AI models for personal use to various AI tools for professional, there is no facet which is left untouched by AI.
AI Model’s 30 Mins Prior Predictions Paves Way for Wearable Warning Systems
AI is also extensively used in the healthcare sector as well in the predictive analytics.
As per a latest scientific report, researchers have now developed new AI-based model which can predict irregular heartbeat, or cardiac arrhythmia as much as 30 minutes before its onset.
This model is proved to be 80% accurate when it comes to the predictions of transition of a normal cardiac rhythm to atrial fibrillation. For the uninitiated, atrial fibrillation is one of the most common types of cardiac arrhythmia in which the heart’s upper chambers (atria) beat irregularly and are out of sync with the lower ones (ventricles).
The team includes researchers at the University of Luxembourg. As per them, this model can easily be installed in the smartphones to process the data recorded on smartwatches. As per the research, the detected warning could allow the patients to take preventive measures to stave off heart attack and keep their cardiac rhythm stable.
The team trained the model on as many as 350 patients, with their 24 hour-long recordings gathered from Tongji Hospital in Wuhan, China.
The researchers have named the model as WARN (Warning of Atrial fibRillatioN). This model is based on deep-learning, which is a branch of machine-learning AI algorithms that learn patterns from past data to make predictions. AI is a branch of pattern recognition and decision-making basis on model which has been trained with a lot of data.
What makes deep learning more special is it ability to make decision making on basis of multiple layers, which makes the decisions ever precise and better than traditional ML models.
30-Minute Warning for Atrial Fibrillation with Wearable Tech
With 30 minutes prior warnings, WARN researcher and Luxembourg Centre for Systems Biomedicine (LCSB), University of Luxembourg, and the study’s corresponding author, Jorge Gonclaves said that “We used heart rate data to train a deep learning model that can recognise different phases — (normal) sinus rhythm, pre-atrial fibrillation and atrial fibrillation — and calculate a ‘probability of danger’ that the patient will have an imminent episode”.
Gonclaves said that when approaching atrial fibrillation, the probability increases until it crosses a specific threshold, providing an early warning.
Since the AI model has low computational cost, it is “ideal for integration into wearable technologies,” the researchers said.
Author Arthur Montanari, an LCSB researcher said that “These devices can be used by patients on a daily basis, so our results open possibilities for the development of real-time monitoring and early warnings from comfortable wearable devices”.