Google can predict when you will DIE with 95% accuracy using AI
Artificial Intelligence
Sep 09, 2018

Google can predict when you will DIE with 95% accuracy using AI

GOOGLE knows everything (or at least it feels that way), and now it can even tell you when you'll die.  On August 24, 2018 the wife of late Arizona Senator John Mccain announced that the family have decided to discontinue his treatment for brain cancer, i knew that we will not live for up to 7 days. Not up to 24 hours later Senator John Mccain passed way. This got me thinking and i knew something was clear somewhere. Either the doctor confine to the family using pass medical records or as a Machine learning Expert i knew there is a system somewhere that can predict when someone will die. I did some google search on topics such as "Can AI predict when a patient will die?", "How to predict death rate using machine learning? and  "Can we build a system that will tell the family members your patient will not be able to survive a certain illness?


Few weeks later i stubbled on research paper release by Google's Medical Brain team on June 19, 2018 indicating that Google’s Medical Brain team has begun training its artificial intelligence system to evaluate the risk of death among hospital patients, and results for the time being are more accurate than those provided by existing medical tools. 

The tech giant helped test an artificial intelligence computer system that can predict whether hospital patients will pass away 24 hours after admission.

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

Google says hospitals could use its death prediction tech to improve patient care. 

Artificial Intelligence systems become smarter over time through a process known as machine learning. The AI was developed by a team of researchers from Standford, the University of Chicago, and UC San Francisco. Google then took the AI system and "taught" it using de-identified data of 216,221 adults from to US medical centres. This meant the AI had more than 46 billion data points to learn from.

Over times, the AI was able to associate certain words with an outcome(i.e life, or death°, and understand how likely (or unlikely) someone was to die.

Google's system can chew up anything and make predictions based on it, due to its powerful machine learning capabilities.

Excitingly, Google's AI doesn't just predict whether you'll live or die.

It can also guess at the length of a patient's stay in hospital, and their chances of being readmitted.

So exactly how accurate is the AI? When we talk about probability, a 1.00 score is perfectly accurate.

And a 0.50 score is a 50/50 chance – so an AI that scores 0.50 is no better than a human making random guesses.

Here's how Google's AI fared based on various outcomes:

  • Predicting if a patient would stay long in a hospital - 0.86(Google) vs 0.76 (traditional methods)
  • Predicting inpatient mortality - 0.9 (Google) vs 0.86 (traditional methods)
  • Predicting unexpected readmissions after a patient was discharged - 0.77 (Google) vs 0.70 (traditional methods)
These model outperformed traditional, clinically-used predictive models in all cases as explained bu Google's Alvin Rajkomar.
Rajkomer said that hospitals adopting the AI could be use it to 'improve care" for patients.

  • Do you thing AI is a force for Good? 
  • When will such a system be tested in Africa?
  • Which Country will lead a research team to carry out research on related AI field in Africa.

Let us know your comments!

Post your comment
Apply Now