Have you ever thought that the death of a human can be predicted? Now with the wonders of artificial intelligence, it has become possible.
Recently, a team of scientists trained an AI system to examine general health data of 10 years in the UK. Next, they asked the AI system if a particular person is prone to premature death due to chronic disease.
New research published in PLOS ONE journal says that ML is expected to be the possible valuable tool for predicting death before average life expectancy. The precision of AI prediction has been tested with prevailing approaches. It has been compared with the statistical ways used by medical research experts to predict actions.
Such research and successful outcomes combined with artificial intelligence and machine learning technology are becoming extremely helpful in the medical arena.
What determines the likelihood of a person to die before expectation?
To observe the probability of a person’s early death, scientists tested two different types of AI. One was deep learning and other was the random forest. While in deep learning layered information processing network aids the computer to understand from instances, the latter one is a simpler AI that amalgamates various models to recognize possible results.
Well, considering the routine lifestyle of a person, certain variables play the key role in the prediction procedure too. The factors such as age, sex and smoking habits along with a prior cancer diagnosis are taken into consideration while evaluating the likelihood of early death. Other factors that contribute to the procedure are:
• Ethnicity and physical activity
• Body fat percentage
• Waist circumference
• The amount of fruit and vegetables that people ate
• Skin tone
• Exposure to job-related hazards
• Air pollution
• Alcohol intake
• Use of certain medications.
However, this is not the first time that AI has exhibited an extraordinary discovery. A team of researchers had demonstrated on AI to identify early symptoms of Alzheimer, in 2017.
Additionally, a study predicted that AI can also predict the onset of autism in a baby who is merely 6 months old.
Also, another research revealed that AI could spot signs of intruding diabetes in a person through an analysis of his/her retina scans.
Stephen Weng, assistant professor of epidemiology and data science at the University of Nottingham said, “We mapped the resulting predictions to mortality data from the cohort using Office of National Statistics death records, the U.K. cancer registry, and ‘hospital episodes’ statistics. Machine learning algorithms were significantly more accurate in predicting death than the standard prediction models developed by a human expert.” Stephen Weng led the research team on the project.
Further, he asserted, “Preventative healthcare is a growing priority in the fight against serious diseases, so we have been working for a number of years to improve the accuracy of computerized health risk assessment in the general population.”
Prof. Joe Kai, a clinical academic who was also the part of the investigation team said, “There is currently intense interest in the potential to use ‘AI’ or ‘machine learning’ to better predict health outcomes. In some situations, we may find it helps, in others it may not. In this particular case, we have shown that with careful tuning, these algorithms can usefully improve prediction.”
Additionally, he said, “These techniques can be new to many in health research and difficult to follow. We believe that by clearly reporting these methods in a transparent way, this could help with scientific verification and future development of this exciting field for healthcare.”