Emerging frontiers of artificial intelligence and machine learning in ischemic stroke: a comprehensive investigation of state-of-the-art methodologies, clinical applications, and unraveling challenges.

Researchers

Journal

Modalities

Models

Abstract

At present, stroke remains the second highest cause of death globally and a leading cause of disability. From 1990 to 2019, the absolute number of strokes worldwide increased by 70.0%, and the prevalence of stroke increased by 85.0%, causing millions of deaths and disability. Ischemic stroke accounts for the majority of strokes, which is caused by arterial occlusion. Effective primary prevention strategies, early diagnosis, and timely interventions such as rapid reperfusion are in urgent implementation to control ischemic stroke. Otherwise, the stroke burden will probably continue to grow across the world as a result of population aging and an ongoing high prevalence of risk factors. To help with the diagnosis and management of ischemic stroke, newer techniques such as artificial intelligence (AI) are highly anticipated and may bring a new revolution. AI is a recent fast-growing research area which aims to mimic cognitive processes through a number of techniques such as machine learning (ML) methods of random forest learning (RFL) and convolutional neural networks (CNNs). With the help of AI, several momentous milestones have already been attained across diverse dimensions of ischemic stroke. In the context of predictive, preventive, and personalized medicine (PPPM/3PM), we aim to transform stroke care from a reactive to a proactive and individualized paradigm. In this way, AI demonstrates strong clinical utility across all three levels of prevention in ischemic stroke. In this paper, we synoptically illustrated the history and current situation of AI and ML. Then, we summarized their clinical applications and efficacy in the management of stroke. We finally provided an outlook on how AI approaches might contribute to enhancing favorable outcomes after stroke and proposed our suggestions on developing AI-based PPPM strategies.The online version contains supplementary material available at 10.1007/s13167-023-00343-3.© The Author(s), under exclusive licence to European Association for Predictive, Preventive and Personalised Medicine (EPMA) 2023. Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.