Google knows everything (or at least it feels that way), and now it can even tell you when you’ll die.

The tech giant has partnered up with Stanford University to help test a new computer system to predict the time-of-death of hospital patients.

What’s more staggering is that trials put the accuracy of the AI’s predictions as high as 95 percent.

 

While there are several barriers to scale up the technology for widespread use in hospitals, they're not insurmountable, and the healthcare potential of an AI-based prediction system for the likelihood of death, discharge, and re-admission is massive.

 

It works by taking in personal data such as age and ethnicity which is then combined with hospital data like vital signs and any prior diagnoses.

 

And what makes the system particularly accurate is that it’s fed data typically out of reach for machines, like doctors notes buried away on charts or in PDFs.

As the AI program is used more and more, it gets smarter at predicting the death of the patient.

 

"These models outperformed traditional, clinically-used predictive models in all cases," explained Google's Alvin Rajkomar.

The system was trained through analysis of 160,000 adult and child patient files from Stanford and Lucile Packard Children's hospital.

When the algorithm was applied to 40,000 active patients (it was asked to predict which would die in the next three to twelve months) it was correct in 90% of cases.

 

Google's findings were published in the Nature journal in May.

------

Hospitals, doctors and other health-care providers have been trying for years to better use stockpiles of electronic health records and other patient data.

------

In one major case study in the research, Google applied its AI algorithm on a patient with late stage breast cancer, and predicted that there was 19.9% chance of the patient dying.

The hospital's Early Warning System, on the other hand, predicted a 9.3% chance of death.

A few days later, the patient died.

 

Hospitals, doctors and other health-care providers have been trying for years to better use stockpiles of electronic health records and other patient data.

 

More information shared and highlighted at the right time could save lives. But current methods of mining health data are costly, cumbersome and time consuming.

 

Google has long sought access to digital medical records, with mixed results. For its recent research, the internet giant cut deals with the University of California, San Francisco, and the University of Chicago for 46 billion pieces of anonymous patient data.

 

Google's AI system created predictive models for each hospital, not one that parses data across the two, a harder problem. A solution for all hospitals would be even more challenging. Google is working to secure new partners for access to more records.

A deeper dive into health would only add to the vast amounts of information Google already has on us. "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 data company Immuta. He and pediatric oncologist Samuel Volchenboum wrote a recent column arguing governments should prevent this data from becoming "the province of only a few companies," like in online advertising where Google reigns.