MAR 28, 2019 8:45 AM PDT

Can Computers Predict Our Death?

WRITTEN BY: Nouran Amin

Stethoscope on a computer (stock image). Credit: © lenetsnikolai / Fotolia via ScienceDaily.com

A new study published in the journal PLOS ONE, suggests that computers are capable of teaching themselves to predict premature death—such research could greatly improve preventative healthcare in the future. Using a team of healthcare data scientists, the newly developed computer-based AI system was used to predict the risk of early death due to chronic disease in a middle-aged population study.

"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. Most applications focus on a single disease area but predicting death due to several different disease outcomes is highly complex, especially given environmental and individual factors that may affect them,” says leading author of the study and Assistant Professor of Epidemiology and Data Science, Dr. Stephen Weng.

The developed system are based on models known as as 'random forest' and 'deep learning'. Priamrly, based against the traditionally-used 'Cox regression' prediction model on age and gender – which is believed to now be the least accurate measure of mortality prediction.

“We have taken a major step forward in this field by developing a unique and holistic approach to predicting a person's risk of premature death by machine-learning. This uses computers to build new risk prediction models that take into account a wide range of demographic, biometric, clinical and lifestyle factors for each individual assessed, even their dietary consumption of fruit, vegetables and meat per day. 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."

Source: University of Nottingham

About the Author
  • Nouran earned her BS and MS in Biology at IUPUI and currently shares her love of science by teaching. She enjoys writing on various topics as well including science & medicine, global health, and conservation biology. She hopes through her writing she can make science more engaging and communicable to the general public.
You May Also Like
JUL 06, 2020
Space & Astronomy
New Technology Can Detect Fast Radio Bursts
JUL 06, 2020
New Technology Can Detect Fast Radio Bursts
Fast radio bursts are intense pulses of energy that come from light years away, popping fir a few milliseconds before di ...
JUL 20, 2020
Neuroscience
Phantom-Limb Pain Reduced by Brain-Computer Interface
JUL 20, 2020
Phantom-Limb Pain Reduced by Brain-Computer Interface
Phantom-limb pain is a condition in which amputees feel like their amputated limb is still attached to their bodies. Whi ...
AUG 19, 2020
Technology
Electronic Alert System Prevents Excessive Prescribing
AUG 19, 2020
Electronic Alert System Prevents Excessive Prescribing
Recent research between the intersection of health and tech brings a new development in an automatic electronic alert sy ...
SEP 14, 2020
Clinical & Molecular DX
Cell Line Authentication Using STR Analysis
SEP 14, 2020
Cell Line Authentication Using STR Analysis
Imagine you’re studying colon cancer using a colon cell line model. After three painstaking years of research, you ...
NOV 18, 2020
Technology
Using Machine Learning to Build Chemical Libraries
NOV 18, 2020
Using Machine Learning to Build Chemical Libraries
Using machine learning in drug discovery is no longer a novel procedure and has been well documented in recent literatur ...
NOV 06, 2020
Technology
phyloFlash: New Software for Microbial Analysis
NOV 06, 2020
phyloFlash: New Software for Microbial Analysis
Scientists at the Max Planck Institute for Marine Microbiology are working on developing an easy technique that will all ...
Loading Comments...