Researchers from The United Kingdom stated that a self-taught artificial intelligence machine could pave the way in predicting heart attacks better than doctors. The mentioned machine was said to possibly save thousand to millions of people if implemented.
According to Komando, an estimate of 20 million people every year die from cardiovascular disease. In which aside from heart attacks, blocked arteries and strokes were mentioned as well. Yet, thanks to the team, the future of predicting heart attacks better are on the way.
The study was reported to be done by the University of Nottingham who created a bunch of programs that could predict heart attack better and train themselves to learn more. The AI machine included four machine learning algorithms namely: random forest, logistic regression, gradient boosting, and neural networks.
As known by some, doctors predict heart attacks due to eight risk factors and signs that include age, blood pressure, and cholesterol level. The doctors also base on the guidelines set by the American College of Cardiology/American Heart Association (ACC/AHA).
The AI algorithm machine was also said to take in data from the electronic medical records of 378,256 patients in the United Kingdom to train themselves. The result was concluded to predict as high as 72.8 percent of a person's heart attack risk. The AI algorithms took in some of their “own” guidelines in predicting heart attack as well that weren’t included in the ACC/AHA guidelines like severe mental illness and taking oral corticosteroids.
Yet, as much as the artificial intelligence study was much of a success, several holes were still found. It was identified that some of the strongest signs to predict heart attack weren’t mentioned in the ACC/AHA guidelines. Another was that as ACC/AHA identified diabetes as one of the top 10 predictors but wasn’t given by the AI machine per Science Magazine.
Nonetheless, Evangelos Kontopantelis, a data scientist at the University of Manchester in the United Kingdom concluded that more training and more computational power to the AI machine would have “bigger gains.” He then concluded that the heart attack AI machine predictor is like a black box in which things come in and out but nobody knows what goes on in between.
