The fears of an AI-controlled robot that is aside aside, artificial intelligence has provided humanity with an incredible opportunity to use incredible computing power for use in a variety of ways, including cancer detection. But can the computer tell us when we are likely to meet the premature end?
Nottingham University researchers decided to understand, and what they found was that the machine learning system was not as good as predicting the individual's chances of death and illness, it was actually better . The system, which assembles the data of over 500,000 people, has managed to guess which individuals will die better than the models developed by human doctors.
The algorithm used in the study had to break an incredible amount of information, including lifestyle differences and eating habits for a massive portion of the UK population.
"We have made a big step forward in this area by developing a unique and comprehensive approach to predicting the risk of premature death from machine training," Dr. Steven Weng, lead author of the work, said in a statement. "It uses computers to build new risk forecasting models that take into account a wide range of demographic, biometric, clinical and lifestyle factors for each evaluated individual, even their consumption of fruit, vegetables and meat per day." [1
the resulting mortality prognosis from the cohort, using the death records of the Office of National Statistics, the UK Cancer Registry, and statistics of "hospital episodes," Weng said. "We have found that the algorithms that have learned the machines were much more accurate when predicting death than the standard predictive models developed by a human expert." personalized health perspectives for individuals. At some point in the not so distant future, computers can tell each of us what diseases are the greatest danger and how to beat them.