What question did this study set out to answer?

The study aims to create a reliable imputation framework for handling missing data in multiple sclerosis datasets using machine learning techniques.

August 2, 2026SclerosisOpen Access

A Data-Driven Approach for Handling Missing Data in a Real Multiple Sclerosis Dataset Based on Machine Learning

View Full Paper

Ask AI

Bookmark

Authors

Randomized trial develops a machine learning framework for imputation of missing data in multiple sclerosis, improving predictive accuracy.

The study aims to create a reliable imputation framework for handling missing data in multiple sclerosis datasets using machine learning techniques.
Developed the Sequential Multiple Imputation Bootstrapping (SMIB) model for data imputation.
Used Random Forest, Multilayer Perceptron, k-Nearest Neighbors, and a multiple imputation algorithm.
Evaluated model through 15-fold cross-validation and assessed performance via various metrics including accuracy and R2.
Achieved imputation accuracy of 97% for categorical outcomes.
RF-based SMIB demonstrated strong numerical performance (R2 up to 0.999; MSE as low as 2.48 × 10−5).
SMIB outperformed Multiple Imputation by Chained Equations (MICE) in predictive performance across evaluated outcomes.

Pilehvari et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark

Randomized trial develops a machine learning framework for imputation of missing data in multiple sclerosis, improving predictive accuracy.