Can a computer tell you when you plan to die?


Everyone is faced with the prospect of death, but do not know when the time will come can be confusing for many. Now researchers have discovered a large advantage of artificial intelligence – the ability to more accurately predict someone’s demise.

The alarming research, published in PLOS One, is the result of researchers training algorithms to look at a decade of medical records from over 500,000 people in the united kingdom between the ages of 40 and 69, and estimate their chances of dying prematurely. During the period 2006-2010 (which was followed up in 2016), almost 14,500 people died, mostly of cancer and other diseases.

“We have mapped out of the resulting predictions to mortality data of the cohort, using Office of National Statistics death records, the uk cancer registry and hospital episodes statistics, the study’s lead author from the University of Nottingham assistant professor in the Epidemiology and Data Science Dr. Stephen Weng, said in a statement. “We find machine-learned algorithms were significantly more accurate in predicting death than the standard prediction models developed by a human expert.”


To help in the effort to understand premature mortality, Weng and his team of researchers looked into two different types of AI. The first is known as ‘deep learning’, in which the information-centric networking help to find a computer to learn from the past instances. The second is the ‘random forest’, Live Science reports, is able to “combines multiple, tree-like models to consider possible outcomes.” They took the conclusions from the two different AI models, compared with the more commonly used ‘Cox regression’ (which is based on age and gender) and found the performance of the AI models were much better.

The deep learning algorithm correctly predicted 76 percent of the patients who died, while the random forest algorithm registered at 64 percent. The Cox model correctly identified 44% of those who had died.

The various algorithms that are used in a number of different factors, such as body fat, blood pressure and food consumption (random forest), as well as job-related hazards, air pollution and alcohol intake (machine learning). The Cox-model, which largely relied on inputs such as ethnicity and physical activity, eventually turned out to be less.

“We have an important step forward in this area by developing a unique and holistic approach to predicting a person’s risk of premature death from machine-learning,” Dr. Weng added in the statement. “This makes use of computers for the construction of new risk prediction models that take into account a wide range of demographic, biometric, clinical and lifestyle factors for each individual assessed, even their diet, consumption of fruit, vegetables and meat per day.

Although it might be a bit confusing to think that a computer knows when your time is up, in the preventive health care is likely to grow in popularity, as more and more people want to know what about their lifestyle, in an effort to live longer and a better life.


“There is currently an intense interest in the possibilities of ‘AI’ or ‘machine learning’ to better predict health outcomes,” said University of Nottingham professor Joe Kai, who also worked on the study, in a statement. “In some situations we may find it helps, in other cases not. In this specific case, we have shown that with careful tuning, these algorithms can be useful in improving the prediction.”

Weng echoed Kai’s feelings, adding that the work has been to aid humanity.

“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 automated health risk assessment in the general population,” Weng added. “Most of the applications focused on one disease area, but predicting death as a result of a different disease outcomes is very complex, especially given the environmental and individual factors that may affect them.”

In addition to a longer life, there are also economic benefits to preventive health care. The Surgeon General has released a white paper that a 1 percent reduction in weight, blood pressure, glucose and cholesterol risk factors would save $83 to $103 annually in medical costs per person,” while 5 percent reduction in hypertension would save $25 billion over 5 years.


“Research from the Milken Institute suggests that a modest reduction in avoidable risk factors could lead to a profit of more than $1 trillion per year in labor supply and efficiency by 2023,” the white paper added.

Follow us

Don't be shy, get in touch. We love meeting interesting people and making new friends.

Most popular