TECHNOLOGY DAY SPECIAL: “AI & Machine Learning Predicting Heart Attacks more accurate than Doctors”




It’s still magic even if you know how it’s done.

Happy Technology Day Folks!

Once again, your Techno Geek is here before you with another informative article on this special day. We at Factuals celebrating today as a symbol of quest for scientific inquiry, technological creativity, technological excellence and the translation of that quest in the integration of Science, Society and Industry. This day marks not only our technological innovations but their successful commercialization making the fruits of painstaking research available to the people at large. On 11 May 1998 India achieved a major technological breakthrough by successfully carrying out nuclear tests at Pokhran. Also first, indigenous aircraft Hansa-3 was test flown at Bangalore on this day and India also performed successful test firing of the Trishul missile on the same day. Considering above technological achievements on a particular date i.e. 11 May, the day of 11 May was chosen to be commemorated as National Technology Day. If we look behind, a series of advancements took place in the field of technology in various fields from space technology to Nano Technology, From Bio Technology to Data Science. Either it would be launching of 104 satellites at once by ISRO or it would be presenting a common payment gateway interface as “BHIM” App.  But one of the latest events in this list is from the field of Data. For the first time, Technology is not only giving competitions to medical science but also proving its strength.

Heart disease is the world’s leading killer. Each year, nearly 20 million people die from the effects of cardiovascular disease, including heart attacks, strokes, blocked arteries, and other circulatory system malfunctions. The human body is seriously complex. Doctors can do their best to diagnose issues, but as a mere mortal, there’s just no guarantee that they’ll be able to correctly detect all ailments, especially when diagnosing certain issues in advance, such as heart attacks. This is where machine-learning and artificial intelligence can help. If that sounds simplistic, it is to an extent; and it is because of that simplicity that growing issues could slip through the cracks.

Through the use of machine-learning, doctors took those guidelines, and with four different algorithms, scanned through 378,256 medical records to find patterns that have led to cardiovascular events. In this case, 22 additional data points were considered for even greater granularity. In an effort to predict these cases, many doctors use guidelines similar to those of the American College of Cardiology/American Heart Association (ACC/AHA). Those are based on eight risk factors—including age, cholesterol level, and blood pressure—that physicians effectively add up.

Luckily, a team of researchers from the University of Nottingham in the UK have developed a machine-learning algorithm that can predict your likelihood of having a heart attack or stroke as well as any doctor. The research was led by epidemiologist Stephen Weng with the University of Nottingham. His team plugged electronic medical records of nearly 300,000 UK patients into a quartet of machine-learning algorithms: Random Forest, Logistic Regression, Gradient Boosting and Neural Networks.

The American College of Cardiology/American Heart Association (ACC/AHA) has developed a series of guidelines for estimating a patient’s cardiovascular risk which is based on eight factors including age, cholesterol level and blood pressure. On average, this system correctly guesses a person’s risk at a rate of 72.8 percent. That’s pretty accurate but Stephen Weng and his team set about to make it better. They built four computer learning algorithms, then fed them data from 378,256 patients in the United Kingdom. The systems first used around 295,000 records to generate their internal predictive models. Then they used the remaining records to test and refine them. The algorithms results significantly outperformed the AAA/AHA guidelines, ranging from 74.5 to 76.4 percent accuracy. The neural network algorithm tested highest, beating the existing guidelines by 7.6 percent while raising 1.6 percent fewer false alarms.

Out of the 83,000 patient set of test records, this system could have saved 355 extra lives. That is quite a significant number, as it would result in one fewer individual dying from a stroke or heart attack for nearly every day of the year. Interestingly, the AI systems identified a number of risk factors and predictors not covered in the existing guidelines, like severe mental illness and the consumption of oral corticosteroids.


This does not mean doctors are not doing a good job by any means, though, but it goes to show the human brain can’t necessarily detect every possible sign either. Doctors have to go by existing guidelines, which will help determine the risk of a heart condition. Machine learning-based solutions provide a fresh look at things, and it is expected more of these AI solutions will make their way into the healthcare industry over the coming years.