Using modern technology to bring people back from the dead is another matter; now scientists from the University of Adelaide are employing artificial intelligence systems to predict your death!
The researchers have developed the system using CT scan of 48 patients and used the data collected to create a diagnosis algorithm to predict whether a patient would die within the next five years. The predictions have been 69% accurate up till now, which is about the same as a human doctors’ predictions. The research is one of its kind employing medical images and artificial intelligence and is presented in a paper in the Nature journal Scientific Reports.
But the computers do work at a faster rate and can analyze a huge number of scans in practically no time. The idea is useful since projecting a patient’s death potentially increases the likelihood of life as it ensures proper medical attention in time. The algorithm uses over 16,000 image features using the deep learning system and highlights potential diseases. This kind of proficiency would take a doctor years of practice while the machine adapts in no time.
My 1st article is published! We predict lifespan in hospital patients by applying #deeplearning to medical imaging. https://t.co/qTuLOFmwT3
— Lauren Oakden-Rayner ????? (@DrLaurenOR) May 11, 2017
‘Predicting the future of a patient is useful because it may enable doctors to tailor treatments to the individual,’
Said Dr. Luke Oakden-Rayner, a radiologist and Ph.D. student at the University of Adelaide’s School of Public Health.
He added,
‘The accurate assessment of biological age and the prediction of a patient’s longevity has so far been limited by doctors inability to look inside the body and measure the health of each organ. Our research has investigated the use of “deep learning”, a technique where computer systems can learn how to understand and analyse images.’
The paper also calls the medical community to encourage the
“use of routinely collected, high-resolution radiologic images as sources of high-quality data for precision medicine.”
The team is now working on the using the AI system as a regular part of the future diagnostic systems.
