AI can calculate personalized risk of having another stroke, new study finds

Artificial intelligence (AI) can be used to give stroke patients a personalized and more precise risk of recurrence, according to a new study presented today at the European Stroke Organization (ESO) conference.

Experts believe the study will help identify the most important factors in preventing stroke recurrence and has the potential to help prevent several thousand strokes per year in Europe, and in so doing, prevent many deaths. and cases of disability.

According to previous research, one in four stroke survivors will have another stroke and yet up to 80% could be prevented with the right treatments and lifestyle changes. The number of people living with stroke is expected to increase by 27% between 2017 and 2047 in the European Union, mainly due to an increase in the number of people over 70 years old.

The study used calculations based both on non-modifiable risk factors, such as age and ethnicity, and on risk factors and modifiable lifestyle habits such as smoking, weight, blood pressure and cholesterol, diet, obesity, levels of physical activity and adherence to treatment, as well as socio-economic factors. These can be used to make a more accurate prediction of an individual’s risk of having a stroke recurrence, within 3 months, a year and over a year, helping to prevent recurrence and improve stroke. patient adherence to treatment.

The research, conducted by scientists at Vall d’Hebrón University in Barcelona, ​​Spain, used a data set of 41,325 patients admitted with a diagnosis of stroke to 88 public hospitals over a six-year period, and integrated them into an AI-based model capable of providing individualized risk of stroke recurrence at 3 and 12 months.

Lead author Giorgio Colangelo, head of AI research at the Vall d’Hebrón University Hospital Research Institute (VHIR), Barcelona, ​​Spain, commented: “We were able to use AI to predict the recurrence of stroke at 3 and 12 months at an individual level, and know that this risk has clinical value for physicians and for patients. Risk factors included high blood pressure and high cholesterol, atrial fibrillation or sleep apnea. We have also determined and quantified which are the most relevant risk factors and which of them each patient can modify in their lifestyle. “

Dr Marta Rubiera, neurologist at Vall d’Hebrón University Hospital and study coordinator, added: “We hope the data can be used to create a much more personalized prediction of if, and when, patients. could have another stroke, and that by explaining the impact of individual risk factors, it will make patients more likely to comply with any prescribed treatment or suggested lifestyle change, thereby reducing the likelihood of having a stroke. other stroke “.

Dr. Marc Ribo, interventional neurologist and Scientific Director of Nora Health, who also participated in the study, concluded that “Patient awareness and empowerment of care are essential in reducing the risk of recurrent stroke. This study will help inform the customization of a newly developed application, NORA, and significantly improve patient risk management. ”

More information:
A personalized predictor of stroke recurrence based on artificial intelligence, presented at the European Stroke Organization conference, September 1, 2021

Provided by the European Stroke Organization