E fundit!

11:19 TODAY

Left with his finger in his mouth/ Spiropali doesn't get anything wrong, here's the movement against Rama

After being dismissed from every important position and be...

Artificial Intelligence can predict heart attacks

2023-12-03 13:25:03, Shëndeti CNA

Cardiovascular diseases continue to be the most common cause of death worldwide. Globally, about 17.3 million people die from them every year. It is estimated that this number could reach 23.6 million by 2030.

Although the number of cardiovascular diseases is increasing, at the same time mortality from heart attacks, ie the relative number of deaths, has decreased significantly thanks to preventive measures and improved acute medical care. And this positive development is likely to increase further in the future thanks to artificial intelligence.

Because the power of AI lies in the ability to recognize potential risks at the right time. From the totality of test values ??AI can filter out some patterns or irregularities that even the most trained specialist staff would not be able to find so quickly.

10 years ago

In the future, AI technology could for example save the lives of thousands of patients with chest pain, in whom the risk of a heart attack is not identified through computed tomography scanning. Because very small narrowings in the coronary arteries are often not seen. In case of inflammation they can rupture and block the arteries leading to a heart attack. Until recently it was possible to identify these high-risk patients in advance.

These AI instruments developed by researchers from Oxford can detect such abnormalities even in patients without significant narrowing of the coronary arteries and predict the risk, if a patient with chest pain will suffer a heart attack in the next ten years. This comes from a study funded by the British Heart Foundation, which was presented at the Scientific Sessions of the American Heart Association in Philadelphia.

Many high-risk patients remain unidentified

In the UK alone around 350,000 people undergo a CT scan of the heart each year. Such an examination is considered a standard test for the detection of narrowing or blockages of the coronary arteries.

The team, led by Professor Charalambos Antoniades Radcliffe Department of Medicine at the University of Oxford, analyzed for this study the data of more than 40,000 people who had undergone CT examinations of the heart at eight British hospitals.

In about three quarters of the cases there were no clear signs of significant narrowing of the coronary arteries. The patients were discharged and received no further treatment. However, the analysis of the data showed that not only patients with significant narrowing of the coronary arteries are at risk. The data show that twice as many patients without significant narrowing had a heart attack and died of cardiac arrest.

They were not considered high-risk patients because the smallest clues were not highlighted. What man cannot discern, AI makes visible. The IA program developed by Oxford researchers examines changes in fat around inflamed arteries and thus calculates actual risk. Because such changes indicate a significant increase in the risk of a heart attack.

Treatment is tailored as specified

With this pilot project, the first in the world, the team of doctors evaluated the risk for 744 patients through AI. With the help of this project, doctors changed the treatment plan in 45 percent of cases. According to the study, the introduction of this technology led to over 20 percent fewer heart attacks and 8 percent fewer deaths and strokes among those who underwent the test.

Artificial Intelligence can predict heart attacks

"Many people die every year unnecessarily from a heart attack. It is very important that we use the potential of artificial intelligence to guide patient treatment," says study leader Charalambos Antoniades.

IT saves time and money

This is just one example of how artificial intelligence can help, so that treatments often start much earlier. This can save lives, save a lot of time and a lot of money. In mid-2023, for example, British cardiologists developed with artificial intelligence a "Decision-Support System" that can speed up the diagnosis of a heart attack in the emergency room.

This method determines the level of troponin in the blood much faster than the previous methods. The protein troponin is released by the breakdown of heart muscle cells and plays a central role in the diagnosis of heart attack. Until now, patients were often sent to the hospital or had to stay there for a long time under observation, until the troponin level was determined, even though they had not suffered a heart attack. AI can save a lot of time, as well as a lot of unnecessary costs.

Risks are identified earlier

Identifying potential risks by AI is not only faster, but sometimes even safer than by humans. Also in mid-2023, American researchers introduced an artificial intelligence that looks for suspicious patterns in the ECG curve and detects dangerous blockages of the coronary arteries much more accurately than even experienced cardiologists.

If the risk is recognized earlier thanks to AI, the risks are also reduced. Long before a dangerous blockage occurs, relatively harmless so-called stents can be placed in the patient in a routine procedure. A stent is like a small metal or plastic tube, which is placed in the narrowed area by a catheter, keeps the vessel permanently open, preventing the narrowing. The risk of a heart attack is neutralized./ DW