AI Could Predict Heart Attack Risk Up To 10 Years in the Future, Finds Oxford Study (theguardian.com) 21
AI could be used to predict if a person is at risk of having a heart attack up to 10 years in the future, a study has found. From a report: The technology could save thousands of lives while improving treatment for almost half of patients, researchers at the University of Oxford said. The study, funded by the British Heart Foundation (BHF), looked at how AI might improve the accuracy of cardiac CT scans, which are used to detect blockages or narrowing in the arteries.
Prof Charalambos Antoniades, chair of cardiovascular medicine at the BHF and director of the acute multidisciplinary imaging and interventional centre at Oxford, said: "Our study found that some patients presenting in hospital with chest pain -- who are often reassured and sent back home -- are at high risk of having a heart attack in the next decade, even in the absence of any sign of disease in their heart arteries. Here we demonstrated that providing an accurate picture of risk to clinicians can alter, and potentially improve, the course of treatment for many heart patients."
About 350,000 people in the UK have a CT scan each year but, according to the BHF, many patients later die of heart attacks due to their failure in picking up small, undetectable narrowings. Researchers analysed the data of more than 40,000 patients undergoing routine cardiac CT scans at eight UK hospitals, with a median follow-up time of 2.7 years. The AI tool was tested on a further 3,393 patients over almost eight years and was able to accurately predict the risk of a heart attack. AI-generated risk scores were then presented to medics for 744 patients, with 45% having their treatment plans altered by medics as a result.
Prof Charalambos Antoniades, chair of cardiovascular medicine at the BHF and director of the acute multidisciplinary imaging and interventional centre at Oxford, said: "Our study found that some patients presenting in hospital with chest pain -- who are often reassured and sent back home -- are at high risk of having a heart attack in the next decade, even in the absence of any sign of disease in their heart arteries. Here we demonstrated that providing an accurate picture of risk to clinicians can alter, and potentially improve, the course of treatment for many heart patients."
About 350,000 people in the UK have a CT scan each year but, according to the BHF, many patients later die of heart attacks due to their failure in picking up small, undetectable narrowings. Researchers analysed the data of more than 40,000 patients undergoing routine cardiac CT scans at eight UK hospitals, with a median follow-up time of 2.7 years. The AI tool was tested on a further 3,393 patients over almost eight years and was able to accurately predict the risk of a heart attack. AI-generated risk scores were then presented to medics for 744 patients, with 45% having their treatment plans altered by medics as a result.
I can do that too (Score:2)
My company will, for a small fee, predict your heart attack chance with 100% accuracy 10 years down the line.
The answer is always "yes" and we'll file for bankruptcy in 9 years and 11 months.
compared to what (Score:3)
There are already plenty of risk calculators. Those are based, of course, on some kind of statistics. So is "AI". Is this method any better than the others?
Re: (Score:2)
Re: (Score:2)
Not the idea of having a model.
Re: (Score:2)
AI is essentially statistics with blinking investor lights on it right now, so that stands to reason.
Re: (Score:1)
Captain AI-vious (Score:1)
AI predicts those who have unexplained chest pain are likely to have heart attacks later? Gee, who would've guessed. This AI is brilliant! zzzz
Re: (Score:3)
> Gee, who would've guessed.
Let me tell you about my new AI startup that predicts future AI startups.
Now unfortunately, since we haven't perfected the technology we can't use our tool to predict the success of our own startup, but that's why we're letting you in as a ground floor investor.
Re: (Score:2)
It is distressing to me that we won't listen to patients that come in describing an issue unless an AI backs them up and says, "no, really, this guy needs help".
Re: (Score:2)
"Doctor, my AI hurts!"
Pfft (Score:4, Funny)
That's nothing. I can predict risk of death 200 years in the future!!
And? (Score:2)
It's one thing to predict if someone might get a hear attack in ten years. It's another to have that person change their lifestyle to try and prevent it. As we know, humans are lazy and if something involves the least amount of interruption to their daily lives they generally won't do it. Even the threat of death won't make most people doing anything different.
Re: (Score:2)
It's one thing to predict if someone might get a hear attack in ten years. It's another to have that person change their lifestyle to try and prevent it.
It's hard to get people to change their lifestyle even after having a heart attack. I've known several people who quit smoking after having coronary artery bypass surgery, only to start again within a year. Personally, I have found a near-death experiences to be a strong motivator. When an aortic dissection almost killed me nearly six years ago, I quit smoking and have never felt even the slightest urge to start again. It's all I can do to keep my mouth shut when I see an acquaintance lighting up.
What would they do with that info? (Score:2)
There are several likely scenarios here:
1) Insurance finds out that you're uninsurable, that's useful to them (you - not so much).
2) They find out a much larger percentage of the population is at risk, preventative measures for all these is super-expensive.
3) There's a higher risk the at-risk population dies before they can perform proper surgery, which makes it cheaper than keeping old people alive (cynical, yes? But do you really think they care about the non-working population?).
So...
We've invented the m
Re: (Score:2)
General practitioners and specialists alike are generally so busy these days that it's hard to get an appointment within a few weeks of calling to make an appointment. The doctors I know would be happier if they could turn the crank more slowly. Curing the disease or treating the symptoms isn't the choice in most cases. Many cases involve chronic diseases that will never be cured but can be treated to lessen their impact on the patient's life.
Follow the money (Score:2)
Heart-related incidents are lucrative. So much so, that ERs are so insistent that you're having one even when the patient is a physician himself and almost all of the symptoms have nothing to do with a heart-attack. An AI is going to predict it and you're going to be put on expensive drugs that you don't really need. It all comes back to the con-artist/subscription business model. They have to find something wrong with you that isn't a quick fix so you'll be forced to spend money in perpetuity. They'll
Here are your test results... (Score:2)
Also, your insurance company is canceling your policy after this visit.
All hail Almighty Dollar, and lay the sacrifices upon its altar.
Insurance? (Score:1)
Alternative headline:
AI can prevent some people from getting health insurance or life insurance at affordable rates up to 10 years before they have any evident problems.
"Could" (Score:4, Insightful)
10 years? (Score:2)
Heck, that is almost long enough to finally get a doctors appointment these days.