Site icon Wonderful Engineering

This AI System Could Predict When People Are Likely to Die

I guess it was only a matter of time when they came up with something like this. Knowing when you’ll die takes all the fun out of life. If a person knows when they’ll most likely croak then life loses its meaning, why work or study when you know you’re going to die in a few years anyway. According to a new study, a new AI system can now predict when a cardiac arrest or heart attack might take place.

It doesn’t predict when people will die of a heart attack or if the attack will even be fatal enough but it can successfully make a guess. It’s all done using timing and weather data. The research was published in the journal Heart. According to the research, results showed that the out-of-hospital risk of cardiac arrest was highest on Sundays, Mondays, during sharp drops in temperature during or between days, and on public holidays.

The goal of the research is to create awareness and serve as an early warning system. This could potentially lower the risk of fatal attacks and raise survival odds. This could also help emergency services to better prepare for unknown situations. They used machine learning to predict daily out of hospital cardiac arrests via timing, as in the year, season, day of the week, the hour of the day, or public holidays, and daily weather, like relative humidity, snowfall, rainfall, temperature, wind speed, cloud cover, and atmospheric pressure readings.

The machine learning model was trained for 525,374 cases using both timing data and weather data. A heatmap analysis was used to predict accuracy at the local level. Results showed a high accuracy of cardiac arrest predictions for out-of-hospital cases. The heatmap revealed hotspots around Sundays, Mondays, low temperatures, sharp drops in temperatures, winter, and public holidays.

According to the researchers, “Our predictive model for daily incidence of [out of hospital cardiac arrest] is widely generalizable for the general population in developed countries because this study had a large sample size and used comprehensive meteorological data”.

They further explained that “The methods developed in this study serve as an example of a new model for predictive analytics that could be applied to other clinical outcomes of interest related to life-threatening acute cardiovascular disease. This predictive model may be useful for preventing and improving the prognosis of patients via a warning system for citizens and [emergency medical services] on high-risk days in the future”.

The model merely predicts when the risk of having a heart attack is high. No machine learning model will be able to accurately tell you when you’ll be going to die. If you’re religious then you already have your own beliefs about death.

Exit mobile version