MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) has come up with a Machine Learning system which can estimate the risk of death in people with cardiovascular issues. The system is called RiskCardio and it can analyze the risk by tracking the electrical activity in a heart.
The RiskCardio system especially focuses on those patients who have survived an Acute Coronary Syndrome (ACS). The ML system looks at just the first 15 minutes of a patient’s electrocardiogram (ECG) to place the patient in different risk categories. The RiskCardio system can estimate whether a patient may suffer a cardiovascular death within 30, 60, 90, or 365 days of having an ACS event.
Traditionally, when a patient suffers an ACS and checks into a hospital, a physician estimates the risk of cardiovascular death or heart attack using the medical data. RiskCardio aims to improve this assessment. To make this happen, the system separates a patient’s signal into sets of consecutive beats. This gives the system the idea of whether the variability between adjacent beats isindicativeof any downstream risk.
"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,” says Divya Shanmugam, lead author on a new paper about RiskCardio. “The intersection of machine learning and healthcare is replete with combinations like this - a compelling computer science problem with potential real-world impact.”
The RiskCardio system does require more refining before it enters service. But the system is a promising proposition for healthcare and will help many ACS patients through accurate prediction.