AI’s new trick is predicting when you’re going to die AI’s new trick is predicting when you’re going to die
WHY THIS MATTERS IN BRIEF Every year over 7,000 people in the UK die from pulmonary heart disease die, and this technology could help... AI’s new trick is predicting when you’re going to die


  • Every year over 7,000 people in the UK die from pulmonary heart disease die, and this technology could help save their lives


You could argue that artificial intelligence (AI) is already spooky enough. Whether we’re dreaming up new ways in which we think it can destroy us, or just because of the fact that it’s gaining on us in new and exciting ways, but now it seems to have gained a new skill, one that even the best doctors have trouble with – it can predict when we’re going to die.


An AI backed by Elon Musk just 'evolved' to learn by itself


Yes, I know it’s shocking news but please, don’t have a heart attack about it, because that’s when we’ll turn it on you. Because, you see, being more specific, it can predict when patients with a heart disorder are going to clock out. And that’s a good thing.

A team from the UK’s Medical Research Council (MRC) have announced that their AI first learned how to analyse blood tests and the scans of beating hearts to spot when they were about to fail, and the MRC says the technology could help save lives by discovering patients who need more aggressive, or special, treatment. The results were published in the journal Radiology.


AI produced 3D heart model predicts time of death


The researchers were investigating patients with pulmonary hypertension, a condition where high blood pressure in the lungs damages part of the heart, and where about a third of patients die within five years of being diagnosed.

At the moment there are a mix of treatments available to treat the condition which involves anything from drugs, injections straight into the blood vessels, and in the worst cases, a lung transplant. But in order for the doctors to pick the right treatment they first have to know how long the patient has to live, and that’s where their new AI buddy comes in.

The AI was given MRI scans of 256 patients’ hearts, and blood test results, and it measured the movement of over 30,000 different individual points in the organ’s structure during each a heartbeat.


Google's new AI image recognition software still has a Cock of the Rock problem


When this data was combined with eight years of patient health records, the AI learned which abnormalities predicted when patients would die. Even better – it can look about five years into the future, and the result?

Well, it correctly predicted those who would still be alive after a year 80% of the time, which bearing in mind it’s a new system and even the very best doctors only get it right about 60% of the time means that, in short, it shows promise.

“The AI really allows you to tailor the individual treatment, so it takes the results of dozens of different tests including imaging, to predict what’s going to happen to individual patients very accurately,” said Dr Declan O’Regan, one of the researchers, “so we can tailor getting absolutely the right intensive treatment to those who will benefit the most.”

The team now want to test that the AI works for other patients in different hospitals before assessing whether it should be made widely available to doctors, and eventually they want to use it to help them treat other forms of heart failure, such as cardiomyopathy, to see who might need a pacemaker, or other forms of treatment.


eSight's new glasses give sight back to the legally blind


“This exciting use of computer software in clinical practice will help doctors in the future to make sure that patients are receiving the correct treatment before the condition deteriorates and leaves them needing a lung transplant,” said Dr Mike Knapton, from the British Heart Foundation,” the next step is to test this technology in more hospitals.”

One day, however, if this single use AI works as well as it has so far then no doubt we’ll see the day come when an AI can predict when any one of us might die – whether or not we’re ill at the time, and no matter how far off it might be. After all, if it can gather and correlate enough data about you – from your environment and lifestyle, to your diet, genetic make up and health then, arguably, it could create an awesome model to predict your “estimated time of death,” and when it manages to do all that, then one day it’ll be able to give you tips on how to keep the Grim Reaper at bay…

Matthew Griffin Global Futurist, Tech Evangelist, X Prize Mentor ● Int'l Keynote Speaker ● Disruption, Futures and Innovation expert

Matthew Griffin, Futurist and Founder of the 311 Institute, a global futures think tank, is described as “The Adviser behind the Advisers.” Recognised in 2013, 2015 and 2016 as one of Europe’s foremost futurists, innovation and strategy experts Matthew mentors several XPrize teams, and is an award winning author, entrepreneur and international speaker who is regularly featured on the BBC, Discovery, Kurzweil, Newsweek, TechCrunch and VentureBeat. Working hand in hand with accelerators, investors, governments, multi-nationals and regulators around the world Matthew shines a light on the future and helps them transform their industries, organisations, products and services by demonstrating how the combination of democratised, and increasingly powerful emerging technologies, are helping fuel cultural, industrial and societal change that is transforming old industries and creating new ones. Matthew’s clients include Accenture, Bain & Co, Bank of America, Booz Allen Hamilton, Boston Consulting Group, Dell EMC, Deloitte, Deutsche Bank, E&Y, Fidelity, Goldman Sachs, Huawei, JP Morgan Chase, KPMG, McKinsey & Co, PWC, Qualcomm, SAP, Schroeder’s, Sequoia Capital, UBS, the UK’s HM Treasury, the USAF and many others.

Your email address will not be published. Required fields are marked *

Translate page »

Pin It on Pinterest

Share This