About this Research Topic
Artificial Intelligence, more specifically Machine Learning, is one of the most transformative technologies with a promise to improve care and outcome if access to high-fidelity and large and multi-resolution datasets become reality. The era of augmented intelligence in healthcare is driven by the notion that intelligent algorithms can support providers in diagnosis, treatment, and outcome prediction, especially with growing digital and connected patient data and advances in computational abilities. The augmented-diagnostic and prognostication models for stroke may be particularly helpful given stroke multifactorial nature, narrow treatment window, and overall burden.
Machine Learning is increasingly becoming an integral part of the healthcare system. Thus, building a decision support system using multi-resolution datasets with the providers-in-the-loop, is the path that many integrated healthcare systems are taking in advancing the field of precision medicine and personalized care. Using advanced machine learning-based technologies and real-world datasets, predictive models can be designed to improve care, reduce diagnostic errors, and minimize the treatment delay.
This Research Topic focuses on recent advances in the design and implementation of machine learning-enabled clinical decision support systems in stroke diagnosis and outcome prediction using real-world datasets, including but not limited to quality data, claims data, electronic health record data, data from wearable technologies. We welcome high-quality Original Research articles or Review Articles related to design, implementation, work-flow integration, limitations, and system performance. We will not include Machine Learning as applied to acute stroke imaging datasets (perfusion, collaterals etc) as part of this Research Topic.
Potential areas of interest include, but are not limited to:
• Automated Stroke Alert system
• Machine Learning-enabled decision support system for triaging transient ischemic attack
• Predictive modeling of stroke and its recurrence
• Models that focus on risk-sensitive optimization rather than performance-driven outcomes
• Models to help in reducing diagnostic errors in real-world settings
• Patient stratification and subtyping
• Optimization models for shared decision making in stroke care
The Topic Editors, Dr. Ramin Zand and Dr. Vida Abedi, received financial support from Genentech (Roche). The other Topic Editors declare no competing interests with regard to the Research Topic subject.
Keywords: Stroke, Machine Learning, Decision support system, Diagnostic accuracy, Outcome
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.