Last update:

Cardiology news

Language-based AI model spots early heart disease in ECGs, reaching 94.2% accuracy

A machine-learning model based on Transformer architecture, a form of artificial intelligence originally developed for language processing, can be used to detect heart disease from electrocardiograms (ECGs), according to ...

ECG privacy model shields age, sex and race while preserving heart risk signals

It is a common misperception that electrocardiograms (ECGs) simply contain data about heart activity. However, modern ECGs enhanced with artificial intelligence (AI) can contain data about a patient's sex, age, race and even ...

Cooling ingredients in vapes might cause irregular heartbeats

For years, flavor additives in e-cigarettes have been largely viewed as a secondary concern compared with nicotine. Research and regulation have focused on addiction, nicotine delivery and, more recently, the respiratory ...

GLP-1s tied to elevated risk of fainting, dizziness

Northwestern Medicine scientists have identified a safety concern associated with GLP-1 drugs. Using health record data, the research team tracked more than 42,000 adults already taking at least two types of blood pressure ...

Brain aneurysm map reveals cell types tied to rupture risk

A new study from UC San Francisco shows how certain cells in the brain may cause aneurysms to weaken and rupture. It helps explain why some aneurysms burst while others do not and could lead to new ways of predicting and ...