Can AI predict when you will die?

NO ONE really knows the exact time and date of your death, so goes the old cliché. Still, that has not stopped medical experts and dreamers on working on devices that can actually predict the exact time of a patient’s death.

While the odds of that happening can be a long way off, there’s a chance now that artificial intelligence (AI) can help people determine if they are going to die within five years.

Researchers at the University of Adelaide in Australia recently revealed an AI technology which can help patients and doctors determine when they’re likely to die.

The new technology uses computerized tomography (CT) scans of patient organs, in which the researchers were able to predict whether patients would die within five years around 70 percent of the time. 

The system could one day serve as an early warning system to catch heart disease, cancer, and other diseases early so that intervention can take place.

“The goal of the research isn’t really to predict death, but to produce a more accurate measurement of health,” Dr. Luke Oakden-Rayner, a researcher on the project, told Digital Trends. 

“A patient’s risk of death is directly related to the health of their organs and tissues, but the changes of chronic diseases build up for decades before we get symptoms… Our goal is to identify these changes earlier and more accurately so we can tailor our treatment to individuals.”

At present, this is still a proof-of-concept experiment, however, and Oakden-Rayner points out that there’s a lot more work to be done before this becomes the transformative clinical tool it could be. 

For one thing, the AI’s 70-percent predictive accuracy when looking at scans is in line with the “manual” predictions made by experts. That makes it a potential time-saving tool, or a good means of double-checking, but the hope is that it can be much more than that.

“Our next major step is to expand our dataset,” Oakden-Rayner continued. “We used a very small cohort of 48 patients in this study to show that our approach can work, but in general deep learning works better if you can give it much more data. We are collecting and analyzing a dataset of tens of thousands of cases in the next stage of our project.” (With report from Digital Trends)

 

Like us in Facebook

Features

Latest News

NEDA asks farmers to plant special rice varieties

  By Rose de la Cruz   The National Economic and Development Authority (NEDA) is encouraging farmers to increase their production of special... Read More...
UBS gears for sustainability in its global operations

  By Rose de la Cruz   UBS, the leading investment in the Philippines and consistently ranked top 2 among international investment banks, is... Read More...
Bong still unsure of Senate run

Should he stay or should he go?  This is the question that Special Assistant to the President Christopher “Bong” Go is trying to answer and... Read More...
IMAGE In the know: Solar Philippines

Solar Philippines is currently the country’s – and Southeast Asia’s – largest solar-energy company. Founded in August 2013 by Leandro... Read More...
Stupid Name Giver and Other Laughs

Stupid Name Giver Late one night, a burglar broke into a house. While he was sneaking around he heard a voice say, "Jesús is watching you."  He... Read More...
Confession Code and other laughs

Confession Code AN old priest who became sick of all the people in his parish who kept confessing to adultery said one Sunday, in the pulpit,"If I... Read More...
IMAGE A DELICATE BALANCE

Photo courtesy of Top Gear Philippines Officials of motorcycle-sharing service company Angkas must be grinning all the way to the bank. After a... Read More...
IMAGE TULOY ANG LABAN SA DENGVAXIA

MABUTI naman at tuluyan ng nagpasiya ang pamahalaan na sampahan ng karampatang kaso ang mga sangkot sa kontrobersyal na Dengvaxia anti-dengue... Read More...

Our Guests

Today862
Yesterday916
This week3457
This month21867
Total1285258

Visitor Info

  • Your IP: 34.204.43.11

Who Is Online

32
Online

Wednesday, 26 June 2019
© 2016 OpinYon News Magazine Online. All Rights Reserved.

Please publish modules in offcanvas position.