Google predicts when people will die ‘with 95% accuracy’

Huge benefits for medical profession – but
will patients be willing to give up even more data to tech
giant

One-Minute Read

In a paper published in the journal , the company’s Medical Brain team
detailed how it is using a new type of artificial intelligence
algorithm to make predictions about the likelihood of death among
patients in two separate hospitals.

For predicting patient mortality, Google’s Medical Brain was 95%
accurate in the first hospital and 93% accurate in the second.

It works by analysing patient’s data, such as their age,
ethnicity and gender. This information is then joined up with
hospital information, like prior diagnoses, current vital signs,
and any lab results, reports The Sun.

But according to Bloomberg, what impressed medical experts
most “was Google’s ability to sift through data previously out of
reach: notes buried in PDFs or scribbled on old charts. The neural
net gobbled up all this unruly information then spat out
predictions. And it did it far faster and more accurately than
existing techniques.”

It is not the first time Google has made inroads into the
medical industry. Its DeepMind subsidiary, considered by some
experts to lead the way in AI research, “courted controversy” in
2013 after it was revealed it had access to 1.6 million medical
records of NHS patients at three hospitals, reports The Independent.

Yet despite concerns the search giant could be given access to
even more data, the latest findings prove Google could have a
potentially life-saving impact on its 1.17 billion users
worldwide.

The Medical Brain team said: “These models outperformed
traditional, clinically used predictive models in all cases. We
believe that this approach can be used to create accurate and
scalable predictions for a variety of clinical scenarios.”

“For medical facilities bogged down in bureaucratic red tape,
Google’s software is a godsend” says Vanity Fair. “Not only can it predict when a
patient may die, but it can also estimate how long someone might
stay in a hospital, or the chance they’ll be readmitted”.

But the magazine also offers a word of warning saying that “for
patients, giving a tech giant like Google access to sensitive
medical information may have unintended consequences”.