Machine Learning Algorithms Are Now Able to Predict Premature Death

A team of researchers from the University of Nottingham has developed and tested a machine learning system that is capable of teaching itself to predict premature death.

Though the new technology sounds a bit eerie or something out of a science fiction film the technology could be used to greatly improve preventative healthcare in the near future.

SEE ALSO: DEEP LEARNING EQUIPS ROBOTS TO HELP AUTISTIC CHILDREN WITH THERAPY

Predicting Death

Published by PLOS ONE in a special collections edition of Machine Learning in Health and Biomedicine, the study showcases how useful the tools of AI and machine learning can be and its application across the medical fields.

Machine Learning models have already been implemented in the medical world, using quantitative power to detect cancer. With these new Machine Learning algorithms, researchers are able to predict the risk of early death due to chronic disease in a largely middle-aged population.

Using data collected over half a million people aged between 40 and 69 recruited to the UK Biobank between 2006 and 2010 and followed up until 2016, the team used the machine learning model to analyze a wide range of demographic, biometric, clinical and lifestyle factors from subjects.

[see-also]

The team even considered their dietary consumption of fruit, vegetables, and meat per day. The Nottingham team then proceeded to go about predicting the mortality of these individuals.

As mentioned by Assistant Professor of Epidemiology and Data Science, Dr. Stephen Weng, "We mapped the resulting predictions to mortality data from the cohort, using Office of National Statistics death records, the UK cancer registry and 'hospital episodes' statistics.”

“We found machine-learned algorithms were significantly more accurate in predicting death than the standard prediction models developed by a human expert."

Preventative Medicine

Researchers part of this study are excited about the results. There could come a time where medical professionals are able to identify potential health threats in patients with scary accuracy and proceed to prescribe the right steps of prevention.

“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 health care”, says Dr. Stephen Weng

The research will help build the foundation for important tools in medicine capable of delivering personalized medicine and tailoring risk management to individual patients. The Nottingham research was based on a previous study in which Machine learning techniques were able to predict cardiovascular disease.