Artificial Intelligence used to identify a patients’ stroke risk

Strokes pose a significant global health challenge, contributing to widespread mortality and disability. It represents one of the leading causes of death and disability in the UK, impacting around 100,000 patients* each year (*Stroke Association.)

Starting with a basic question, researchers at RGU, used state of the art explainable artificial intelligence (XAI) techniques and a machine learning algorithm called ‘Random Forest’, to ask a series of questions, to pinpoint the most significant factors contributing to a stroke.

The study identified several key stroke risk factors including age, marital status, glucose levels, body mass index, work type, heart disease and gender.

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.

Dr Pascal Ezenkwu, a lecturer in Business and Data Analytics, noted: “With a stroke affecting someone every five minutes, it is crucial that we find a way to reduce this life-changing disease. 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.”

In Scotland, the Scottish Stroke Care Audit identifies a stroke as the third commonest cause of death and the most common cause of severe physical disability amongst adults. It is estimated that about 15,000 people in Scotland have a stroke each year.

A stroke happens when the blood supply to part of the brain is cut off, killing brain cells. Damage to the brain can affect how the body works. It can also change how you think and feel. The effects of a stroke depend on where it takes place in the brain, and how big the damaged area is.

The study led by Dr Ebuka Ibeke and Dr Pascal Ezenkwu was shared at the 2024 International Conference on Electrical Electronics and Computing Technologies by Ogochukwu Williams Ugbomeh, an RGU MSc student, who supported the work as the machine learning engineer and software developer. The conference unites innovative academics and industrial Electrical Engineering and Computer Technology experts from across the world, in a common forum.

Main image credit Pixaby. Gallery image shows RGU researchers RGU Dr Ebuka Ibeke and Dr Pascal Ezenkwu