He stated that with hundreds of thousands of data points, AI can help predict cardiovascular risk and detect it non-invasively, far better than any human doctor can. At that time he pointed out that Google's AI can help doctors predict medical events in cases where a patient gets very sick and preventative measures can save lives. But this time, it predicted the death of a patient.
In a distressing incident, an unidentified woman with late-stage breast cancer was told that according to the vital signs shown by a hospital’s computers, there was an estimated a 9.3 percent chance that she would die during her stay at the medical facility. The prediction was then followed by Google’s assessment. A new type of algorithm created by Google read up on the woman 175,639 data points and estimated her death risk at 19.9 percent. She passed away in a few days.
This account was published by Google in May in research highlighting the health-care potential of neural networks, a form of artificial intelligence software that is good at using data to automatically learn and improve. Medical experts were impressed with the algorithm's ability to read data which was buried in PDFs or scribbled on old charts. It searched through the information, or data points, far faster and more accurately than existing techniques. The AI even showed which records led it to conclusions.
The algorithm that the researchers produced can even help predict the occurrence of a future major cardiovascular event, said Michael McConnell, Head of Cardiovascular Health Innovations at Verily.
The discovery came after Christopher Shallue and Andrew Vanderburg at Google AI trained a computer to learn how to identify exoplanets in the light readings recorded by Kepler -- the minuscule change in brightness captured when a planet passed in front of, or transited, a star.