Scottish researchers use AI to predict patients’ risk of stroke

Researchers at Robert Gordon University have used artificial intelligence (AI) to identify patients at risk of suffering a stroke.

The team used cutting-edge explainable AI (XAI) methods and a machine learning algorithm, named Random Forest, to pinpoint the most significant factors contributing to a stroke.

The risk factors the team identified included age, marital status, glucose levels, body mass index, work type, heart disease and gender.

Scientistic claim the findings could underpin a preventative approach to the medical condition, enhancing patient outcomes, and mitigating the impact it has on the NHS. 

Dr Ebuka Ibeke,  course leader of RGU's MSc Business and Data Analytics who led the study, said: “This research significantly contributes to healthcare and healthcare informatics by providing insights that can enhance strategies for stroke prevention and management, ultimately leading to improved patient care.

“The Stroke Association show that one in seven strokes are preventable and therefore identifying predictors of a stroke risk is crucial to enable timely interventions and to reducing the increasing impact of strokes.”

The discovery could be life-changing for thousands in Scotland, as strokes are the third most common cause of death and the most common cause of severe physical disability amongst adults north of the border, according to the Scottish Stroke Care Audit.

Dr Pascal Ezenkwu, a lecturer in business and data analytics, added: “Our research offers a valuable insight that can be used by healthcare professionals to develop targeted interventions, fostering a proactive approach to mitigate the impact of strokes on individuals and the healthcare system.”