The new structure found with an algorithm can predict heart attack and death with 90% accuracy.
Artificial intelligence has made its mark in various industries with medicine and healthcare not being an exception for it. Previously, AI has made its mark in spotting diseases such as cancer, but a new study shows it is better and more useful than this. A new study reveals the digital brain may be better at predicting overall mortality and specific conditions such as heart attack with superior precision and a trained doctor. The research was presented at the International Conference of Nuclear Cardiology and Cardiac CT that suggests there will be a day when medical practitioners would be working along with artificial intelligence.
According to Dr. Luis Eduardo Juarez-Orozco of the Turku PET Center in Finland, machine learning is overtaking humans in predicting heart attacks or deaths, based on the data from 1000 patients. This research involved patients with chest pain who underwent treatment for coronary artery disease. It involved 58 pieces of data on the presence of coronary plaque, vessel narrowing, and calcification discovered during the scans. The study went on for six years where researchers recorded 24 heart attacks and 49 deaths from various causes.
Thereafter, 85 variables were entered into an algorithm named LogitBoost that analyzed them again and again until it discovered the best structure to predict who had a heart attack or who died. In a comparatively short time, LogitBoost was able to identify patterns correlating the variables to heart attack and death with 90% accuracy. “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,” says Dr. Luis Eduardo Juarez-Orozco.