Google knows everything (or at least it feels that way), and now it can even tell how long someone is going to live.
Google has developed artificial intelligence "A-I" that knows when you are going to die. It sounds a little scary or far fetched, but the information could end up saving lives.
A new paper published in Nature suggests that feeding electronic health record data to a deep learning model could substantially improve the accuracy of projected medical outcomes.
This technology, sometimes called "medical brain," is in trials now, using data from two U.S. Medical Centers. Google collaborated with a team of researchers from Stanford, the University of Chicago and UC San Francisco. The researchers were able to show their collected data could predict a patient's length of stay, time of discharge and time of death with 95 percent accuracy.
It works by chewing up data about patients, like their age, ethnicity and gender. This information is then joined up with hospital information, like prior diagnoses, current vital signs and any lab results. What makes the system particularly accurate is that it is fed data typically out of reach for machines, like doctors notes buried away on old charts or in PDFs.
Google taught the system how to use the de-identified data. Overtime, the A-I was able to associate certain words with an outcome (i.e. life, or death), and understand how likely (or unlikely) someone was to die as well as their chances of being re-admitted to the hospital. What is particularly exciting about Google's system is that researchers can throw almost any type of data at it.
Google said it plans on using this data in clinics. Health-care professionals are already concerned about the effect that AI will have on medicine. A spokesperson from The American Medical Association admits in a statement that combining A-I with human clinicians can bring significant benefits including improving patient safety and outcomes, but states “ A-I tools must strive to meet several key criteria”, to protect sensitive patient information from bias which could affect care.
At the end of the day no matter what technology is being implemented medical experts said all of the information has to be evaluated by a human being.