Technology news site

This AI System Can Predict How Long A Patient Has To Live


Artificial intelligence is being used to make life better in many ways but some Australian scientists are taking this a step further. They built a system that they say can predict whether or not you will die soon. University of Adelaide researchers say the system does this by analysing images of your organs thereby using an algorithm to calculate the amount of time you have left on this planet.

The researchers used AI to analyse medical images of 48 patient’s test and the system was able to predict which patients are likely to die over the next five years with an accuracy level of 70 percent.

Luke Oakden-Rayner, a PhD student at the University of Adelaide said “Instead of focusing on diagnosing diseases, the automated systems can predict medical outcomes in a way that doctors are not trained to do, by incorporating large volumes of data and detecting subtle patterns.”

We have seen AI systems like Watson proffer diagnostic and curative views which doctors have used to make decisions but this is the first time a system of that nature would be applied in human life longevity.

But it looks like the system better predicts longevity for those who may have been diagnosed by medical staff of some chronic or terminal disease. So the 48 patients had conditions from congestive heart failure and emphysema (a breathing problem) which is why it was able to predict how long they have to live.

Oakden-Rayner added though that “Our research opens new avenues for the application of artificial intelligence technology in medical image analysis, and could offer new hope for the early detection of serious illness, requiring specific medical interventions” signaling that the system could be used not only to predict longevity but early diagnosis.

At the moment, it is said that human doctors can only predict longevity with about 60 percent accuracy and instead of focusing on this, they can rather look at cures. AI systems are able to analyse a large set of data fed into it in a short time making it more efficient.

The London Institute of Medical Services say they a similar system which they say can predict whether a patient would die over the next year with 80 percent accuracy.

HTML Snippets Powered By : XYZScripts.com