Artificial Intelligence can Predict When You Will Die

Table of Contents

New technology has been developed which can accurately predict when patients with a heart condition will die.
A team from the UK’s medical research council were investigating patients with pulmonary hypertension. This is caused by high blood pressure in the lungs putting too much strain on the heart. Typically patients die within 5 years of diagnoses.

However, there are treatments available. Drugs, injections and lung transplants are all available to sufferers. However, doctors need to know how long the patient has left before they can prescribe the correct treatment.

But now, thanks to the technology and software developed by the MRC this might be far easier than ever before. Some new software was given MRI scans of 256 patients hearts and blood test results. It also measured 30,000 different points of the hearts structure during a heartbeat. When combined with the 8 years of patient health records the software learned which abnormalities predicted when a patient might die.

The software guessed which patients would still be alive after a year, and was 80% accurate, compared to doctors who were only 60% accurate.

Dr Declan O’Regan, one of the researchers said: “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.

“So we can tailor getting absolutely the right intensive treatment to those who will benefit the most.”
The team want to carry out further testing, on different patients and in different hospitals, before releasing the software to other doctors.

This is an incredible achievement and could go on to change the lives of millions of people. Heart related issues are one of the largest killers in the UK. If you want to be part of discoveries like this then you can be. Nearly all medical research teams will have trained phlebotomists among them as the taking of blood is vital in medical research and development. To find out more just give us a call on 01609 751 610.