AI can predict when someone will die with unsettling accuracy

More news from CONVERGENCE.

This is very interesting for several reasons. First, here's some of the article.

Medical researchers have unlocked an unsettling ability in artificial intelligence (AI): predicting a person's early death.

Scientists recently trained an AI system to evaluate a decade of general health data submitted by more than half a million people in the United Kingdom. Then, they tasked the AI with predicting if individuals were at risk of dying prematurely — in other words, sooner than the average life expectancy — from chronic disease, they reported in a new study.

The predictions of early death that were made by AI algorithms were "significantly more accurate" than predictions delivered by a model that did not use machine learning, lead study author Dr. Stephen Weng, an assistant professor of epidemiology and data science at the University of Nottingham (UN) in the U.K., said in a statement. [Can Machines Be Creative? Meet 9 AI 'Artists']

To evaluate the likelihood of subjects' premature mortality, the researchers tested two types of AI: "deep learning," in which layered information-processing networks help a computer to learn from examples; and "random forest," a simpler type of AI that combines multiple, tree-like models to consider possible outcomes.

Then, they compared the AI models' conclusions to results from a standard algorithm, known as the Cox model.

www.nbcnews.com...

Here's the relevant portions of the study then I will list my reasons.

Using these three models, the scientists evaluated data in the UK Biobank — an open-access database of genetic, physical and health data — submitted by more than 500,000 people between 2006 and 2016. During that time, nearly 14,500 of the participants died, primarily from cancer, heart disease and respiratory diseases.

The Cox model leaned heavily on ethnicity and physical activity, while the machine-learning models did not. By comparison, the random forest model placed greater emphasis on body fat percentage, waist circumference, the amount of fruit and vegetables that people ate, and skin tone, according to the study. For the deep-learning model, top factors included exposure to job-related hazards and air pollution, alcohol intake and the use of certain medications.

When all the number crunching was done, the deep-learning algorithm delivered the most accurate predictions, correctly identifying 76 percent of subjects who died during the study period. By comparison, the random forest model correctly predicted about 64 percent of premature deaths, while the Cox model identified only about 44 percent.

www.nbcnews.com...

1. I think this could help extend lives, but it won't. Climate Change and population control advocates will object. If the apocalypse is 12 years away and we can't have too many kids or eat hamburgers, there's no way they're going to extend all those lives. You also have to factor in things like advances in Nanotechnology, Gene Therapy and other areas that may give people a better quality of life as their lives are extended. It's a serious conundrum. Do we extend lives and add to the population or let people die that they know they can save?

2. I think it's interesting that one of the factors of the deep learning model factored in medications. This could be for a couple of reasons. The obvious one is certain medicines point to more serious ailments. Secondly, you would have to look at the data to see if certain medications are precursors to certain ailments and are medicines that don't point to a serious ailment contributing to people dying. I will take a closer look at the study to see if the medications are identified.

3. Would you want to know if AI marked you for death?

I think future generations will have to live longer as they colonize space. They will also be modified genetically. A brave new world may be ahead if we can avoid WW 3 or some infectious disease that spreads and kills faster than it can be contained.

I don't know anything about this article, but I can tell you my toaster told me it wanted me to die. Didn't give a timeline, though. Clearly it's outdated.

(just kidding, my toaster told me I would die next Tuesday)

(at least now there's a record of what I heard)

(I'm just saying, question my toaster)

I wonder how it calculates a sudden death by freak accident?

EDIT - I can see health insurance companies using this garbage to deny claims for treatments. Which, you know. Fine. If there's 99.999% probability that said treatment will NOT have any good impact on the outcome, it makes sense. In every way but one. If a person knows all that but still wants to fight until the last breath, they shouldn't be denied by a greedy insurance company.

originally posted by: neoholographic
3. Would you want to know if AI marked you for death?

I don't need a machine to know that my time is running out. Odds are very good that I'll die either from cancer or heart disease when I'm around 83. Unless I get hit by a drunk driver or a meteorite lands on me before then.

I will die when I am no longer relevant to the world.

originally posted by: BrianFlanders
I wonder how it calculates a sudden death by freak accident?

It figures it out, and then sends a killbot to make sure it happens as scheduled.

originally posted by: BrianFlanders
I wonder how it calculates a sudden death by freak accident?

EDIT - I can see health insurance companies using this garbage to deny claims for treatments. Which, you know. Fine. If there's 99.999% probability that said treatment will NOT have any good impact on the outcome, it makes sense. In every way but one. If a person knows all that but still wants to fight until the last breath, they shouldn't be denied by a greedy insurance company.

I know you are jonkig but for people who did not read and think it predicts peoples deaths, in reality the study took 500000 people over ten years and 14000 died. it fed the computer the number14000 and the computer guessed76 percent accurately who the 14000 were who died.

originally posted by: Blue Shift

originally posted by: neoholographic
3. Would you want to know if AI marked you for death?

I don't need a machine to know that my time is running out. Odds are very good that I'll die either from cancer or heart disease when I'm around 83. Unless I get hit by a drunk driver or a meteorite lands on me before then.

I will die when I am no longer relevant to the world.

You must be the AI that is stated in the OP
That answer was spot on for everyone.
Wow

originally posted by: AlexandrosTheGreat

originally posted by: BrianFlanders
I wonder how it calculates a sudden death by freak accident?

EDIT - I can see health insurance companies using this garbage to deny claims for treatments. Which, you know. Fine. If there's 99.999% probability that said treatment will NOT have any good impact on the outcome, it makes sense. In every way but one. If a person knows all that but still wants to fight until the last breath, they shouldn't be denied by a greedy insurance company.

I know you are jonkig but for people who did not read and think it predicts peoples deaths, in reality the study took 500000 people over ten years and 14000 died. it fed the computer the number14000 and the computer guessed76 percent accurately who the 14000 were who died.

Which isn't that surprising, considering that's what it was designed to do.

Studies will be funded by your local State Farm agent.

a reply to: neoholographic

they tasked the AI with predicting if individuals were at risk of dying prematurely — in other words, sooner than the average life expectancy — from chronic disease, they reported in a new study.

AI can predict when someone will die with unsettling accuracy

Predict some people who were at greater risk. No just any person.

lean some about statistics then you will know this is bull!
when it can tell you when they die and how I will be amazed.
remember we all die. and Most get sick first!!!

any remember that cat that could tell who would die?
now that was real.

a reply to: neoholographic

Interesting. Do you happen to have a source to the complete article? I love this type stuff.

a reply to: neoholographic

Interesting. Do you happen to have a source to the complete article? I love this type stuff.

a reply to: neoholographic

Interesting. Do you happen to have a source to the complete article? I love this type stuff.

a reply to: neoholographic

Interesting. Do you happen to have a source to the complete article? I love this type stuff.

a reply to: neoholographic

I know this program.

It even told me that I'd die in the next few seco

originally posted by: DBCowboy
a reply to: neoholographic

I know this program.

It even told me that I'd die in the next few seco

Are you happily married Cowboy?

a reply to: InTheLight

Insanely happy.

originally posted by: DBCowboy
a reply to: InTheLight

Insanely happy.

Insanely?

What a strange word to choose. Perhaps being insane with love is the only way love prevails? Is that the reasoning, Cowboy? Or is it something else?

Perhaps you are on a wave of love that promises much. Hope. Don't give up now.

a reply to: InTheLight

We're off topic and should stop.

My relationship is private in any regard.

____________________________________________________

So an AI can predict death! Insurance companies will love this!