Accepted for/Published in: Journal of Medical Internet Research
Date Submitted: Apr 20, 2024
Open Peer Review Period: Apr 29, 2024 - Jun 24, 2024
Date Accepted: Jul 15, 2024
(closed for review but you can still tweet)
Artificial intelligence for diagnosing acute stroke: a 25-year retrospective
ABSTRACT
Background:
Background:
Stroke is a leading cause of death and disability in the world. Rapid and accurate diagnosis is crucial for minimizing brain damage and optimize treatment plans.
Objective:
Objective:
This review aims to summarize the methods of artificial intelligence (AI) assisted diagnosis of acute stroke and the assessment of stroke prognosis over the past 25 years, providing an overview of common performance metrics and the development trends of algorithms. It also delves into existing issues and future prospects, intending to provide a comprehensive reference for clinical practice.
Methods:
Method: A total of 33 representative articles published between 1999 and 2024 on utilizing AI technology for acute stroke diagnosis were systematically selected and analyzed in detail.
Results:
Results:
The segmentation of acute stroke lesions from 1999 to 2024 can be divided into three stages. Prior to 2012, research mainly focused on brain white matter segmentation using thresholding techniques. From 2012 to 2016, the focus shifted to stroke lesion segmentation based on machine learning (ML). After 2016, the emphasis was on deep learning (DL) based stroke lesion segmentation, with a significant improvement in accuracy observed. For the classification and prognosis assessment of strokes, both ML and DL have their advantages, achieving a high level of accuracy.
Conclusions:
Conclusion: Over the past 25 years, AI technology has shown promising performance in segmenting, classifying, and assessing the prognosis of acute stroke lesion.
Citation
Request queued. Please wait while the file is being generated. It may take some time.
Copyright
© The authors. All rights reserved. This is a privileged document currently under peer-review/community review (or an accepted/rejected manuscript). Authors have provided JMIR Publications with an exclusive license to publish this preprint on it's website for review and ahead-of-print citation purposes only. While the final peer-reviewed paper may be licensed under a cc-by license on publication, at this stage authors and publisher expressively prohibit redistribution of this draft paper other than for review purposes.