Accounting for uncertainty in training data to improve machine learning performance in predicting new disease activity in early multiple sclerosis

Accounting for uncertainty in training data to improve machine learning performance in predicting new disease activity in early multiple sclerosis

IntroductionMachine learning (ML) has great potential for using health data to predict clinical outcomes in individual patients. Missing data are a common challenge in training ML algorithms, such as when subjects withdraw from a clinical study, leaving some samples with missing outcome labels. In t...

Full description

Bibliographic Details
Main Authors: Maryam Tayyab, Luanne M. Metz, David K.B. Li, Shannon Kolind, Robert Carruthers, Anthony Traboulsee, Roger C. Tam
Format: Article
Language:English
Published: Frontiers Media S.A. 2023-05-01
Series:Frontiers in Neurology
Subjects:
multiple sclerosis
machine learning
MRI
label uncertainty
clinical prediction
missing labels
Online Access:https://www.frontiersin.org/articles/10.3389/fneur.2023.1165267/full

Internet

https://www.frontiersin.org/articles/10.3389/fneur.2023.1165267/full

Similar Items