Researchers at the University of Technology Sydney have developed an AI model that analyzes DNA to identify genetic risk factors for stroke.
Key facts
- •Stroke is the second leading cause of death worldwide, affecting around 46,000 Australians each year.
- •The AI model uses a transformer architecture, the same technology used in large language models like ChatGPT.
- •People with the highest genetic risk score had a 22% higher chance of stroke compared to lower-risk individuals.
- •The study identified the gene EDEM2 in brain cortex tissue as a key contributor to stroke susceptibility.
- •Researchers plan to develop a multimodal AI tool and propose a preventive clinical trial.
Researchers at the University of Technology Sydney (UTS) have developed an AI model that analyzes a person's DNA to identify genetic risk factors for stroke. Stroke is the second leading cause of death worldwide, with approximately 46,000 Australians experiencing a stroke each year.
By the numbers
AI Model Details and Testing
First author Dr. Yue (Eric) Yang stated that the AI tool is unique because it identifies genetic variants linked with stroke while considering their location in the genome and how they interact. The research team tested the model using genetic and health data from the UK Biobank and health records from a U.S.-based database called All-of-us. The study, published in Computer Methods and Programs in Biomedicine, identified 18 genetic variants associated with ischemic stroke, which is the most common type of stroke. Researchers found that individuals with the highest genetic risk score had a 22% higher chance of stroke compared to the lower-risk group.
Future Research and Clinical Applications
The study highlighted the gene EDEM2 in brain cortex tissue as a key contributor to stroke susceptibility. Distinguished Professor Jie Lu noted that the research demonstrates how AI can help build personalized risk assessments. The team is currently working on a multimodal AI tool to combine genetic risk assessments with health and lifestyle surveys, scans, and imaging for stroke and other diseases such as endometriosis. Corresponding author Dr. Kairui Guo, working with Liverpool Hospital in Sydney alongside neurologist Dennis Cordato, stated that the team has a proposal for a preventive clinical trial to sequence patient genomes and analyze stroke risk.
Advertisement
This article was independently rewritten by ManyPress editorial AI from reporting originally published by Medical Xpress.
