In recent years, advancements in machine learning have resulted in developing significantly fast and accurate methods for diagnosing many severe health conditions. Earlier this month, a team of researchers from MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL) has created a new, improved system for predicting health outcomes. The new machine learning model can estimate a patient's risk of cardiovascular death from the electrical activity of their heart. 

The system is called "RiskCardio." It focuses on patients who have survived an acute coronary syndrome, which is a set of contains where there is a reduction or blockage of blood to the heart. The model works by analyzing the first 15 minutes of patents' electrocardiogram (ECG) signal and producing a score that places the patient into a particular risk category. 

"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," said Divya Shanmugam, lead author on a new paper about RiskCardio, to MIT News. "The intersection of machine learning and healthcare is replete with combinations like this — a compelling computer science problem with potential real-world impact." 

RiskCardio's most significant advantage over other previous machine learning models comes from the fact that it is based on the patient's raw ECG. Previous models use of patient information like age or weight or using knowledge and expertise specific to the system to asses risks in these patients.