Between 15 and 20 million people die each year around the world from heart attacks and other cardiac-related illnesses. But perhaps technology can help now that new artificial intelligence can actually give out better predictive abilities than doctors can. But before thinking that doctors will soon be replaced by AI robots or that you’re conjuring up images of those Star Wars robot physicians, remember that technology is only as good as it provides help to humans, and as good as the humans utilizing it as well.
Doctors are not clairvoyant, but maybe technology can help them predict better. But thanks to a team of researchers at the University of Nottingham in England, we could be closer than ever before to predicting the future when it comes to the health risks of patients. The scientists and researchers have managed to develop an algorithm that outperforms medical doctors when it comes to predicting heart attacks, and according to experts, this could save thousands of lives every year.
Based on worldwide medical statistics, around 20 million people fall victim to cardiovascular disease, and this includes heart attacks, strokes, and blocked arteries. Today, doctors depend on guidelines similar to those of the American College of Cardiology and American Heart Association in order to predict the risks to patients. These guidelines include factors like age, cholesterol level, and blood pressure.
Video Courtesy of Youtube:
Unfortunately, those are often insufficient. According to Stephen Weng, an epidemiologist at the University of Nottingham, in an interview with Science Magazine, “There’s a lot of interaction in biological systems, and some of them make less sense than others. That’s the reality of the human body. What computer science allows us to do is to explore those associations.”
In employing computer science, Weng took the ACC and AHA guidelines and compared them to four machine-learning algorithms: random forest, logistic regression, gradient boosting, and neural networks. The artificially intelligent algorithms began to train themselves using existing data to look for patterns and create their own “rules.” After this they began testing these guidelines against other records. The research turns out that all four of these methods performed significantly better than the ACC and AHA guidelines.
The most successful algorithm, the neural network, actually was correct 7.6 percent more often than the ACC and AHA method, and resulted in 1.6 percent fewer false positives. That means that in a sample size of around 83,000 patient records, 355 additional lives could have been saved. The researchers could not stress enough how important their work is to other doctors and to medical science as a whole. They are all hoping that doctors start to embrace the use of artificial intelligence to assist them in the care of patients.