Konferenssiposteri
Disentangling Blood-Based Markers of Multiple Sclerosis Through Machine Learning: An Evaluation Study
Tekijät: Vlieger, Robin; Rizia, Mst Mousumi; Amjadipour, Abolfazl; Cherbuin, Nicolas; Brüstle, Anne; Suominen, Hanna
Toimittaja: Househ, Mowafa S.; Tariq, Zain Ul Abideen; Al-Zubaidi, Mahmood; Shah, Uzair; Huesing, Elaine
Konferenssin vakiintunut nimi: World Congress on Medical and Health Informatics
Kustantaja: IOS Press
Julkaisuvuosi: 2025
Journal: Studies in Health Technology and Informatics
Kokoomateoksen nimi: MEDINFO 2025 — Healthcare Smart × Medicine Deep: Proceedings of the 20th World Congress on Medical and Health Informatics
Tietokannassa oleva lehden nimi: Studies in health technology and informatics
Sarjan nimi: Studies in Health Technology and Informatics
Numero sarjassa: 329
Vuosikerta: 329
Aloitussivu: 1766
Lopetussivu: 1767
eISBN: 978-1-64368-608-0
ISSN: 0926-9630
eISSN: 1879-8365
DOI: https://doi.org/10.3233/SHTI251204
Verkko-osoite: 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.
Julkaisussa olevat rahoitustiedot:
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.
