The symptoms are confusingly similar: acute myocardial infarction and broken heart syndrome Takotsubo. In an international study, researchers led by ETH Zurich and University Hospital Zurich have now been able to demonstrate that artificial intelligence can outperform experienced cardiologists when it comes to analyzing cardiac ultrasound data. However, the road to clinical use is still long.
In the journal “JAMA Cardiology,” the researchers report on a machine learning algorithm that automatically classifies cardiovascular disease based on image data. Data from cardiac ultrasound studies of approximately 450 patients suffering from acute myocardial infarction or ‘broken heart’ syndrome were included in the algorithm.
Also known as Takotsubo syndrome, this heart failure occurs mainly in women and usually follows emotional or physical stress. A temporary weakness in the heart muscle causes part of the heart to inflate unnaturally, making it resemble a Japanese squid catching vessel, a ‘takotsubo’. The consequences are chest pain, shortness of breath and in the worst case a heart attack and death.
The researchers point out that despite the AI’s good performance, further studies are needed before it can be used clinically. If even larger datasets were available in the future, predictions could be significantly improved and provide greater insight into the dynamics of normal and abnormal heart function, said cardiologist Christian Templin of the University Hospital.
Source: Krone
I’m Wayne Wickman, a professional journalist and author for Today Times Live. My specialty is covering global news and current events, offering readers a unique perspective on the world’s most pressing issues. I’m passionate about storytelling and helping people stay informed on the goings-on of our planet.
