Have you ever felt that your heart was beating irregularly and often at an abnormally fast rate? It doesn’t mean you’re in love. It is a cardiac condition called atrial fibrillation. It does not cause any symptoms. 

The person who has it may be completely unaware that their heart rate is irregular. You may be aware of noticeable heart palpitations when your heart feels like it’s pounding, fluttering or beating irregularly – often for a few seconds or, in some cases, a few minutes.

A normal heart rate should be regular and between 60 and 100 beats a minute when you’re resting. You can measure your heart rate by checking your pulse in your wrist or neck. The abnormal cardiac condition often causes the heart to beat considerably higher than 100 beats a minute. Atrial fibrillation can cause problems including dizziness, shortness of breath and tiredness.

You should see your doctor if you have chest pain that comes,, if you  chest pain that goes away quickly but you’re still worried, if you notice a sudden change in your heartbeat or if your heart rate is consistently lower than 60 or above 100. It’s important to get medical advice to make sure it’s nothing serious.

Warning patients that they are at risk of developing the condition can give them time to change their lifestyle and avoid or postpone the onset of the condition. It may also encourage regular follow-ups with the patient’s cardiologist, ensuring that if and when the condition develops, it will be identified quickly, and treatment will be started without delay. Known risk factors for atrial fibrillation include sedentary lifestyle, obesity, smoking, genetic predisposition and more.

Shany Biton and Sheina Gendelman – two master’s of science students working under the supervision of assistant Prof. Joachim Behar – head of the Artificial Intelligence in Medicine laboratory (AIMLab.) in the Faculty of Biomedical Engineering of the Technion-Israel Institute of Technology in Haifa – wrote a machine learning algorithm capable of accurately predicting whether a patient will develop atrial fibrillation within five years. 

Conceptually, the researchers sought to find out whether a machine learning algorithm could capture patterns predictive of atrial fibrillation even though there was no atrial fibrillation diagnosed by a human cardiologist at the time.

Biton and Gendelman used more than a million 12-lead electrocardiogram (ECG) recordings from more than 400,000 patients to train a deep neural network to recognize patients at risk of developing atrial fibrillation within five years. Then, they combined the deep neural network with clinical information about the patient, including some of the known risk factors. 

Both the ECG recordings and the patients’ electronic health record were provided by the Telehealth Network of Minas Gerais (TNMG), a public telehealth system assisting 811 of the 853 municipalities in the state of Minas Gerais in Brazil. The resulting machine learning model was able to correctly predict the development of atrial fibrillation risk in 60% of cases, while preserving a high specificity of 95% — meaning that only five percent of those identified as being potentially at risk did not develop the condition.

“Major cardiovascular and cerebrovascular events occur in individuals without known pre-existing cardiovascular conditions. Preventing such events remains a serious public health challenge. For that purpose, clinical risk scores can be used to identify individuals with high cardiovascular risks, they wrote. However, available scoring scales have shown moderate performance. Despite being part of the routine evaluation of many patients in both primary and specialized care, the role of ECG analysis in cardiovascular disease prediction and, hence, prevention is not clear.”

The study was published in the European Heart Journal – Digital Health under the title “Atrial fibrillation risk prediction from the 12-lead electrocardiogram using digital biomarkers and deep representation learning.” 

“Our study has important clinical implications for atrial fibrillation management,” they wrote. “It is the first study integrating feature engineering, deep learning, and electronic medical record system (EMR) metadata to create a risk prediction tool for the management of patients at risk of the condition.”

The team said that they did “not seek to replace the human doctor – we don’t think that would be desirable,” commented Behar on the results, “but we wish to put better decision support tools into the doctors’ hands. Computers are better equipped to process some forms of data. For example, examining an ECG recording today, a cardiologist would be looking for specific features which are known to be associated with a particular disease. Our model, on the other hand, can look for and identify patterns on its own, including patterns that might not be intelligible to the human eye.”

Doctors have progressed from taking a patient’s pulse manually to using a statoscope and then the ECG. Using machine learning to assist the analysis of ECG recordings could be the next step on that road.

Since ECG is a routine, low-cost test, the machine learning model could easily be incorporated into clinical practice and improve healthcare management for many individuals, the team said.  Access to more patients’ datasets would let the algorithm get progressively better as a risk prediction tool. The model could also be adapted to predict other cardiovascular conditions.