Comprehensive Evaluation of Regression and Classification Models on Brain Stroke Datasets

Dimitar Trajkov, Ana Kostovska, Panče Panov, Dragi Kocev

2025

Abstract

This paper investigates the application of machine learning models for predicting brain stroke outcomes, leveraging publicly available datasets. We evaluate the performance of various classification and regression models, including ensemble methods such as AdaBoost, Gradient Boosting, and Random Forest, across eight datasets related to stroke prediction. Our results show that data quality and dataset characteristics have a more significant impact on model performance than the choice of algorithm, underscoring the importance of high-quality, well-curated data in achieving accurate and reliable predictions. Additionally, we emphasize the need for transparency, reproducibility, and traceability in AI research, highlighting the challenges associated with the scarcity of publicly available stroke datasets. This study provides a foundation for developing more trustworthy AI tools for stroke prediction and encourages further efforts in data sharing and model validation.

Paper Citation

in Harvard Style

Trajkov D., Kostovska A., Panov P. and Kocev D. (2025). Comprehensive Evaluation of Regression and Classification Models on Brain Stroke Datasets. In Proceedings of the 18th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 2: HEALTHINF; ISBN 978-989-758-731-3, SciTePress, pages 631-638. DOI: 10.5220/0013184800003911

in Bibtex Style

@conference{healthinf25,
author={Dimitar Trajkov and Ana Kostovska and Panče Panov and Dragi Kocev},
title={Comprehensive Evaluation of Regression and Classification Models on Brain Stroke Datasets},
booktitle={Proceedings of the 18th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 2: HEALTHINF},
year={2025},
pages={631-638},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013184800003911},
isbn={978-989-758-731-3},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 18th International Joint Conference on Biomedical Engineering Systems and Technologies - Volume 2: HEALTHINF
TI - Comprehensive Evaluation of Regression and Classification Models on Brain Stroke Datasets
SN - 978-989-758-731-3
AU - Trajkov D.
AU - Kostovska A.
AU - Panov P.
AU - Kocev D.
PY - 2025
SP - 631
EP - 638
DO - 10.5220/0013184800003911
PB - SciTePress