Disentangling Blood-Based Markers of Multiple Sclerosis Through Machine Learning: An Evaluation Study

: Vlieger, Robin; Rizia, Mst Mousumi; Amjadipour, Abolfazl; Cherbuin, Nicolas; Brüstle, Anne; Suominen, Hanna

: Househ, Mowafa S.; Tariq, Zain Ul Abideen; Al-Zubaidi, Mahmood; Shah, Uzair; Huesing, Elaine

: World Congress on Medical and Health Informatics

Publisher: IOS Press

: 2025

: Studies in Health Technology and Informatics

: MEDINFO 2025 — Healthcare Smart × Medicine Deep: Proceedings of the 20th World Congress on Medical and Health Informatics

: Studies in health technology and informatics

: Studies in Health Technology and Informatics

: 329

: 1766

: 1767

: 978-1-64368-608-0

: 0926-9630

: 1879-8365

DOI: https://doi.org/10.3233/SHTI251204

: https://doi.org/10.3233/shti251204

Studies of blood-based markers in multiple sclerosis using machine learning for classification use widely varying methods. Here different configurations of machine learning algorithms, feature selection methods, and evaluation approaches were compared. Logistic Regression with Random Forests for feature selection and 10-fold cross-validation classified best, features depended on selection methods, and cross-validation data splits were heterogeneous. This suggests experimental setups influence classification and selected markers.

:
This research was funded by the ANU OHIOH initiative, which aims to transform healthcare by developing new personalised health technologies and solutions in collaboration with patients, clinicians, and healthcare providers.