This review synthesizes the current literature on explainable artificial intelligence and fairness in artificial intelligence applications for acute stroke management, identifies persistent challenges, and outlines recommendations for the development of equitable and trustworthy systems in stroke care.
Abstract
Artificial intelligence is increasingly integrated into acute stroke management, demonstrating strong performance in tasks such as large vessel occlusion detection, Alberta Stroke Program Early Computed Tomography Score scoring, and functional outcome prediction. However, concerns persist regarding both the black-box nature of these models and algorithmic bias that may exacerbate disparities in stroke incidence, treatment, and outcomes across racial and socioeconomic subgroups. This review synthesizes the current literature on explainable artificial intelligence and fairness in artificial intelligence applications for acute stroke management, identifies persistent challenges, and outlines recommendations for the development of equitable and trustworthy systems in stroke care. Recent studies have increasingly adopted post hoc explainability methods, though these are limited by approximation and misleading interpretations, especially since explanations are rarely formally tested. Explainability and fairness remain largely disconnected, with fairness evaluation remaining uncommon due to limited demographic metadata, regulatory constraints, and the absence of stroke-specific fairness criteria. Generalizability also remains a concern due to suboptimal data set partitioning strategies and inadequate reporting practices. Responsible artificial intelligence for acute stroke management requires unified evaluation frameworks that jointly assess explainability, fairness, and generalizability.
A fairness-aware machine learning framework using counterfactual adjustment to account for historical inequities embedded in clinical data reduced treatment disparities by 64.8% without compromising predictive accuracy (AUC = 0.89).
J. Kabangu, V. Lopera, Teresia M. Perkins et al.· Journal of Racial and Ethnic...· 0 citations
AI Morbidity and Mortality (AI M&M) is intended to complement, rather than replace, model monitoring, patient safety reporting, and regulatory oversight by converting individual AI-in-workflow failures into actionable institutional learning.
Paulius Mui, Dean F. Sittig, Steven Labkoff et al.· 0 citations
Artificial intelligence (AI) is moving rapidly from retrospective prediction and image analysis into treatment selection, operative planning, intraoperative guidance, and postoperative prognostication in cardiothoracic surgery. This transition raises an ethical problem that cannot be resolved by model accuracy alone: w...
Vasileios Leivaditis, F. Mulita, V. Androutsopoulou et al.· Medical Science· 0 citations
Overall, the proposed framework advances early cerebral stroke diagnosis using structured clinical data and provides a strong foundation for AI-assisted stroke prediction using tabular healthcare data and contributes to preserving clinical decision support systems.
Asma Aldrees· Current medical imaging· 0 citations
Five priorities define a translational agenda for 2026 and beyond: AI in mental health will succeed not through model performance alone, but through disciplined integration into clinical workflows, measurement systems, and governance structures that ensure safety, equity, and real-world effectiveness.
Martin P. Paulus, J. Torous, R. Perlis et al.· NPP—Digital Psychiatry and N...· 0 citations
Background Telestroke expands access to specialist stroke care and is associated with increased use of intravenous thrombolysis (IVT). Whether this reflects improved access alone or also changes how clinicians act under diagnostic uncertainty remains unclear. Purpose To review evidence on telestroke-associated thrombol...
Wen-Jing Zhang, Li-Kun Wang, Si-Ying Ren et al.· Frontiers in Neurology· 0 citations
Enforcing physics-based constraints prevents AI models from generating unreliable predictions for complex nonlinear systems in weather, climate, and turbulent flows.
MIT News · Artificial Intelligence· news.mit.eduNov 20, 2026
An MIT and Dana-Farber Institute-led team used large language models to examine nearly 4,000 studies and hundreds of code repositories, revealing gaps in the information needed to scrutinize and reuse published research.
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.