AI tool helps detect heart problems before symptoms start

British researchers have developed an artificial intelligence tool that can identify people at risk of a serious heart condition before symptoms appear, potentially preventing thousands of strokes, the BBC reported.

The AI system, developed by scientists at the University of Leeds and Leeds Teaching Hospitals NHS Trust, analyzes electronic health records to detect warning signs of atrial fibrillation (AF), a condition causing irregular and abnormally fast heart rates, per the BBC.

The tool examines patient data including age, sex, ethnicity and existing medical conditions such as diabetes, high blood pressure and heart disease to calculate individual risk levels.

The algorithm was trained using anonymized health records from over 2.1 million people and validated against 10 million additional records, according to Sky News.

Patients identified as high-risk during the ongoing West Yorkshire trial are given a portable ECG device to monitor their heart rhythm for four weeks.

If successful, researchers hope to expand the trial nationwide.