Home // EXPLAINABILITY 2025, The Second International Conference on Systems Explainability // View article
Authors:
Jalpa Soni
Emelian Gurei
Jaime Lopez Sahuquillo
Sergio Garcia Gomez
Victor M Saenger
Manuel Rodriguez Yañez
Francisco Campos Perez
Keywords: Brain stroke; Causal AI; Explainability; Interpretability; Tsetlin Machine
Abstract:
In this paper, we propose an explainable framework to assess biomarker significance in brain stroke data by combining Causal Artificial Intelligence (AI), which models cause–effect relationships beyond simple correlations, with a Tsetlin Machine, a symbolic rule-based learning algorithm that generates human-readable logic clauses. In a first step, Causal AI is used to uncover complex interdependencies among biomarkers and to identify the most impactful ones, while the interpretable clauses of the Tsetlin Machine enhance understanding and support improved diagnosis, prognosis, and prevention in stroke patients. This methodological strategy sets a novel foundation for better understanding of complex brain diseases.
Pages: 8 to 13
Copyright: Copyright (c) IARIA, 2025
Publication date: October 26, 2025
Published in: conference
ISBN: 978-1-68558-318-7
Location: Barcelona, Spain
Dates: from October 26, 2025 to October 30, 2025