Retraction Note: Improving stroke risk prediction by integrating XGBoost, optimized principal component analysis, and explainable artificial intelligence Authors: Lesia Mochurad, Viktoriia Babii, Yuliia Boliubash, Yulianna Mochurad Published: 2026 BMC Medical Informatics and Decision Making (2025) 25:63 10.1186/s12911-025-02894-z The Editors have retracted this Article. After publication, concerns were raised regarding the provenance and reliability of the public datasets used in the study. The authors have used two publicly available datasets [1, 2]. Concerns have been raised regarding the provenance and validity of this dataset [3]. Information regarding ethical oversight of data collection including the inclusion of identifiable information such as age and sex, or an associated data governance framework could not be confirmed, nor is it clear that clinical diagnoses were validated. The authors have been unable to provide any further information regarding the provenance or accuracy of the data included in this dataset. As this dataset was used to train and assess the machine-learning models examined in this article, the Editors no longer have confidence in the reliability of the results and conclusions of this article. Lesia Mochurad did not explicitly state whether or not she agrees or disagrees with the retraction. All other authors did not respond to correspondence from the publisher regarding this retraction.