AI will read ECG, detect heart attack risk

The system will use machine learning algorithm in reading ECGs.

Artificial Intelligence (AI) has applications in not just business and gaming but even health and fitness. It can predict threats to your health with increasing accuracy – one such health risk is a heart attack.

Around 7.4 million people are living with heart disease in the UK, according to the British Heart Foundation. Each day, 460 people die of heart attacks – one every three minutes. This is why proper prediction of heart attacks is the need of the day.

A new paradigm combines new and old technologies to properly predict heart attacks. Researchers at the Massachusetts Institute of Technology Computer Science and Artificial Intelligence Laboratory have developed a machine learning system that will predict heart attacks in advance.

The system which has been named RiskCardio can estimate the risk of death due to cardiovascular diseases, which block or reduce blood flow to the heart, according to the researchers.

Divya Shanmugam, the lead author on a new paper about RiskCardio, stated in the press release, "We're looking at the data problem of how we can incorporate very long time series into risk scores, and the clinical problem of how we can help doctors identify patients at high risk after an acute coronary event. The intersection of machine learning and healthcare is replete with combinations like this -- a compelling computer science problem with potential real-world impact."

All RiskCardio needs is a 15-minute ECG reading. It analyses repeated heartbeats and finds anomalies that can predict the risk of a heart attack. In case, data is available within 15 minutes of a heart attack, RiskCardio can determine the risk of death between 30 days and a year after the event.

The machine learning algorithm used works on a simple idea – the variability between heartbeats is what reflects heart attack risk. The more data the system gets, the smarter it becomes. The base value is taken from a patient surviving a heart attack and the other value has been taken from deaths that occurred due to cardiovascular disease.

RiskCardio may provide a lot of information to doctors to further research on cardiovascular diseases. With all the information that wearables provide regarding heartbeats, it may even get better with time.