Google is Developing Highly Accurate Medical AI

Google is Developing Highly Accurate Medical AI

Google is developing a new tool that utilizes an algorithm which can predict patients’ prognoses.  The Artificial Intelligence (AI) can also forecast the length of their hospital stays, whether or not that have a high chance of being admitted again and how soon they will pass away.  The tool is more accurate than anything else currently on the market.

In fact, those in the medical field have been developing procedures for years to predict such outcomes.  They have historically used vital signs and other patient-based information to attempt this type of forecasting in order to save time on documentation, so they can focus on patient care.  But, despite their best efforts, the computer has proven in testing to be more reliable.

Nigam Shah, an associate professor at Stanford University said that current methods simply eat up too much time.  Roughly eighty percent of the time spent on existing models goes toward making the findings presentable.  With Google’s program, “You can throw in the kitchen sink and not have to worry about it,” Shah explained.

In recent years, most of the Google crew’s work has been focused on improving the existing interface.  However, the new technology being developed by the Medical Brain team offers the search engine company a chance to enter into a new market entirely – something the company has struggled with.  “They understand what problems are worth solving,” Vik Bajaj, a former executive at Verily said. “They’ve now done enough small experiments to know exactly what the fruitful directions are.”

In order to conduct its research, Google was able to gather 46 billion pieces of patient data from the University of California, San Francisco, and the University of Chicago.  All patients were able to remain anonymous, and it was obtained by permission.  Google is currently working to secure new partners for access to even more files.

“Companies like Google and other tech giants are going to have a unique, almost monopolistic, ability to capitalize on all the data we generate,” said Andrew Burt, chief privacy officer for Immuta. The tech giant will likely have no issues obtaining the desired data as needed.

Medical Brain has come up with Artificial Intelligence systems for radiology, ophthalmology, and cardiology and is in the midst of branching out and developing AI in other medical specialties, including dermatology and diabetic retinopathy.  It’s really not surprising founder Larry Page has been intent on developing AI.  His father was a professor of Computer Science and Artificial Intelligence, so Page was exposed to the fundamentals at a very young age.

AI could also be a big money maker for Google’s founders.  Over time, the company could license the systems they develop to medical personnel or sell them through the company’s cloud-computing division. Microsoft Corp., a top rival, is also working on predictive AI services.

Of course, the research is still in its initial stages, and the tech giant would need to gain access to more data and continue testing before the new systems are ready to be rolled out. Lily Peng, a member of Medical Brain, said, “I want to emphasize that this is really early on.”

Sources:

Google Is Training Machines to Predict When a Patient Will Die

GOOGLE’S MEDICAL BRAIN TEAM USES AI TO PREDICT PATIENT’S HEALTH AND EVEN DEATH RISK