Currently, there is a trend of adding Machine Learning and Artificial Intelligence to anything and everything. However, we are getting good results out of those experiments too. We would not have believed if a machine would predict the death of someone or a risk of a heart attack a decade ago. But according to a study, machine learning can predict these risks with 90% accuracy now.
This study was recently presented at the International Conference on Nuclear Cardiology and Cardiac CT. In this conference, the study was presented to show how machine learning can be used in the field of medicine as well. As we know, Google has played a major role in the advancement of machine learning. The search giant has integrated machine learning in almost all its products.
Basically, machine learning is a procedure where the machine is fed some data over a period of time. After that, the machine is expected to predict the possible outcomes. Through historical data and algorithms, machine learning can predict possible outcomes with varying accuracy.
In this study, 85 variables in 950 patients were analyzed and their six-year outcomes were known. After that, an algorithm was created which would study the patterns and predict the chances of death or heart attack. The machine was able to identify these patterns with more than 90 per cent accuracy.
“These advances are far beyond what has been done in medicine, where we need to be cautious about how we evaluate risk and outcomes. We have the data but we are not using it to its full potential yet,” said Finland’s Dr Luis Eduardo Juarez-Orozco of the Turku PET Centre.
He also added that “The algorithm progressively learns from the data and after numerous rounds of analyses, it figures out the high dimensional patterns that should be used to efficiently identify patients who have the event. The result is a score of individual risk,”