For the 10 million people every year who survive a stroke, AI could provide some hope by assisting treatment to prevent a relapse, researchers believe. — Photo: Fabian Strauch/dpa
WASHINGTON: An AI-based care system could help some stroke survivors avoid immediate relapse, according to research presented at the recent American Stroke Association conference.
People who have a stroke are vulnerable to having another soon after the first, and can remain so for up to five years.
But a team of China-based scientists and doctors found that an AI-based "clinical decision support system" ended up cutting the likelihood of "new vascular events" by 25.6% during the three months after the initial stroke.
"Ischemic stroke survivors who received care recommendations from an artificial intelligence (AI)-based system had fewer recurrent strokes, heart attacks or vascular death within three months, compared to people whose stroke treatment was not guided by AI tools," the research team said.
"An artificial intelligence-based clinical decision support system for stroke care was effective and feasible in clinical settings in China and improved patient outcomes," said Zixiao Li, chief physician, professor and deputy director of neurology at Capital Medical University’s Beijing Tiantan Hospital.
The bot "also improved stroke care quality with patients more likely to be treated with guideline directed medical therapy" the team told the delegates attending the conference, which was held in the second week of February.
Almost 7.5 million people were killed by a stroke in 2021, according to the American Heart Association. Around 87% of strokes in the US are ischemic, the AHA said, a form of stroke that causes around 50% of stroke deaths.
While the use of AI in medical diagnosis and treatments is not new, interest in prospects for its use has increased over the past year, since the commercialisation of machine learning or large language model AI tools such as ChatGPT.
However, recent research by the University of Cologne and Yale University warned that the benefits of AI in healthcare remain "study specific" and defy generalisation. – dpa
