跳到正文
原文
Medical Xpress·· 2026-10-16AI 评分46

悉尼科技大学开发Transformer AI模型预测基因组缺血性中风风险

Researchers develop new AI tool to better predict stroke risk

AI 导读

悉尼科技大学研究团队在《计算机方法与生物医学程序》发表研究,利用Transformer AI模型分析基因组数据以识别缺血性中风遗传风险因素。该模型基于UK Biobank和All of Us数据库测试,在区分中风患者方面比现有遗传风险工具更准确,并发现18个与中风相关的基因变异及关键致病基因EDEM2。

正文
stroke risk
Credit: cottonbro studio from Pexels

Researchers from the University of Technology Sydney (UTS) have developed an AI model that analyzes a person's DNA to better identify genetic risk factors for stroke, paving the way for more personalized risk assessments.

Stroke is the second leading cause of death worldwide. Around 46,000 Australians have a stroke each year, with one in three survivors experiencing moderate to severe disability, which can include long-term impairment.

First author Dr. Yue (Eric) Yang, who recently completed a Ph.D. in artificial intelligence at UTS, said the AI tool is unique because it not only identifies genetic variants linked with stroke but also considers their location in the genome and how they might interact.

"A stroke happens when blood flow to the brain is cut off or severely reduced, usually by a blood clot, which causes brain cells to die. Genetic susceptibility plays an important role in stroke risk, along with lifestyle factors such as smoking and alcohol consumption.

"We tested our AI model using genetic and health data from the UK Biobank, and also against health records from a large U.S.-based database (All-of-us). Our model was more accurate than previous genetic risk tools at distinguishing people who had suffered a stroke from those who had not."

The recently published study in Computer Methods and Programs in Biomedicine, "Predicting risk of ischemic stroke: A transformer model using genomic data," identified 18 genetic variants associated with ischemic stroke, the most common type of stroke.

The researchers found that people with the highest genetic risk score had a 22% higher chance of stroke compared with the lower-risk group.

The study pointed to the gene EDEM2 in brain cortex tissue as a key contributor to stroke susceptibility, which could provide a specific target for further biological research into the causes of stroke.

The team used a type of AI known as a transformer, which is the technology behind large language models such as ChatGPT, to train the model on thousands of genetic variations and identify links to ischemic stroke.

Distinguished professor Jie Lu, director of the Australian Artificial Intelligence Institute and Australian laureate fellow in the UTS Faculty of Engineering and IT, said the research highlights how AI can be used to develop personalized health care.

"AI can be used to find associations between human genes and disease and build personalized risk assessments to help prevent a potentially life-changing or fatal event," said Lu, who is also the Australian industry laureate fellow in AI-for-Women's Health.

"Genetics is only one part of stroke risk. The ability to combine a genetic score with clinical and lifestyle information, including established risk factors such as blood pressure, age, atrial fibrillation, type 2 diabetes and cholesterol, could enhance monitoring and prevention.

"We are now working on a multimodal AI tool that can combine a genetic risk assessment with other modes of data, including health and lifestyle surveys, scans and imaging, to better assess risk in stroke and other diseases such as endometriosis."

Corresponding author Dr. Kairui Guo has been working with the stroke unit at Liverpool Hospital in Sydney on genomic data analysis, as well as AI applications for acute stroke management, with support from neurologist and co-author Dennis Cordato, an associate professor and senior staff specialist who has provided clinical insights.

"When someone has a stroke, particularly at a young age, they often want to know whether other family members are also at risk. These new AI tools will provide the ability to better help families understand that risk," said Guo.

"We currently have a proposal for a preventive clinical trial. The aim is to recruit the first cohort of patients, sequence their genomes and analyze stroke risk. We are also interested in sex differences in stroke risk between men and women.

"Traditionally, in thinking about stroke risk, genetics hasn't been a main consideration; however, this study highlights the significant impact of genetic factors. Without AI, it would be impossible to process that much data at an individual level to provide a personalized assessment."

More information

Yue Yang et al., Predicting risk of ischemic stroke: A transformer model using genomic data, Computer Methods and Programs in Biomedicine (2026). DOI: 10.1016/j.cmpb.2026.109625

Key medical concepts

Ischemic Stroke

Who's behind this story?

Swati Mestri

Swati Mestri

Swati Mestri holds a bachelor's degree in Electronics Engineering and has worked as a content editor since 2019. She has experience editing research documents across technology, health care, and materials science, and has a particular interest in technology and space. Full profile →

Andrew Zinin

Andrew Zinin

Master's in physics with research experience. Long-time science news enthusiast. Plays key role in Science X's editorial success. Full profile →

Citation: Researchers develop new AI tool to better predict stroke risk (2026, October 16) retrieved 16 October 2026 from https://medicalxpress.com/news/2026-10-ai-tool.html

This document is subject to copyright. Apart from any fair dealing for the purpose of private study or research, no part may be reproduced without the written permission. The content is provided for information purposes only.

来源:Medical Xpress · medicalxpress.com