{"id":20370,"date":"2022-11-29T11:00:16","date_gmt":"2022-11-29T10:00:16","guid":{"rendered":"https:\/\/www.sciencefocus.com\/?p=131330"},"modified":"2022-11-29T11:42:12","modified_gmt":"2022-11-29T10:42:12","slug":"ai-can-predict-the-risk-of-heart-disease-by-analysing-a-single-chest-x-ray","status":"publish","type":"rss_feed","link":"https:\/\/c01.purpledshub.com\/bbcsciencefocus\/rss_feed\/ai-can-predict-the-risk-of-heart-disease-by-analysing-a-single-chest-x-ray\/","title":{"rendered":"AI can predict the risk of heart disease by analysing a single chest X-ray"},"content":{"rendered":"

<\/p>

By Jason Goodyer\n \t\t<\/p>

Published: Tuesday, 29 November 2022 at 12:00 am<\/p>

\n\n

Heart disease is one of the biggest killers in the UK. According to the British Heart Foundation, cardiovascular diseases are currently responsible for around a quarter of all UK deaths<\/a>, that\u2019s around 160,000 per year.<\/p>\n

Patients deemed to be most at risk are prescribed statins \u2013 drugs used to lower the level of cholesterol in the blood and protect the insides of the artery walls. But signs of the disease are not always picked up early, meaning that many patients who would benefit from the drugs aren\u2019t receiving them.<\/p>\n

Now, researchers based at Massachusetts General Hospital have developed a deep learning AI<\/a> model that can reliably predict a patient\u2019s 10-year risk of death from a heart attack<\/a> or stroke by analysing a single routine chest X-ray.<\/p>\n

The team trained the AI, named CXR-CVD Risk, using 150,000 chest X-rays taken from more than 50,000 participants in a prostate, lung, colorectal, and ovarian cancer screening trial carried out by the National Cancer Institute.<\/p>\n

They then tested it on data taken from more than 11,000 patients with a mean age of 60 who were potentially eligible for statin therapy and had routine outpatient chest X-rays at Mass General Brigham.<\/p>\n

They found that almost ten per cent of the patients suffered a major cardiac event such as a heart attack or stroke within the ten-year period following the X-rays. Of these, the CXR-CVD Risk model was successfully able to predict 65 per cent.<\/p>\n

\u201cWe\u2019ve long recognised that X-rays capture information beyond traditional diagnostic findings, but we haven\u2019t used this data because we haven\u2019t had robust, reliable methods. Advances in AI are making it possible now,\u201d said Dr Jakob Weiss<\/a>, of Massachusetts General Hospital.<\/p>\n

\u201cThe beauty of this approach is you only need an X-ray, which is acquired millions of times a day across the world.\u201d<\/p>\n