AI breakthrough identifies genetic risks that could predict stroke before it strikes

AI breakthrough identifies genetic risks that could predict stroke before it strikes

The study identified 18 genetic variants linked to ischemic stroke, the most common type of stroke.

Researchers in Australia have developed an artificial intelligence (AI) model that analyses DNA to identify genetic risk factors for stroke, paving the way for more personalised risk assessments and prevention.

The study identified 18 genetic variants linked to ischemic stroke, the most common type of stroke.

People in the highest genetic risk group had a 22 per cent higher chance of stroke than those in the lower-risk group, according to a statement released recently by Australia's University of Technology Sydney (UTS).

The team used a type of AI known as a transformer to train the model on thousands of genetic variations and identify links to ischemic stroke.

Researchers tested the AI model using genetic and health data from the UK Biobank and a large US database.

The model was more accurate than previous genetic risk tools at distinguishing people who had suffered a stroke from those who had not.

Latest Stories

• Five Great Lakes countries agree on plan to disarm foreign fighters in conflict-hit region
• Millions of children aren’t getting vaccinated: How mapping tools can help find them
• Kenya’s Ahmed Kalebi makes history as only African named in global pathology Hall of Fame
• Water bowser torched in Eastleigh after allegedly hitting pedestrian as driver flees scene

The study also identified the gene EDEM2 in brain cortex tissue as a key contributor to stroke susceptibility, providing a target for further research.

Researchers are now developing a multimodal AI tool that combines genetic assessments with other modes of data, including health and lifestyle surveys, scans and imaging, to improve risk assessment for stroke and other diseases.