Longitudinal Missing Data Imputation for Predicting Disability Stage of Patients with Multiple Sclerosis

TL;DR

This paper proposes methods for imputing missing functional system scores in MS patients and predicting disability progression, demonstrating that combining specific algorithms yields accurate results in handling irregular longitudinal data.

Contribution

It introduces a novel approach combining imputation and prediction techniques tailored for longitudinal MS data with missing values.

Findings

Exponential Weighted Moving Average achieved the lowest imputation error.

Combining CART for imputation and SVM for prediction yielded the best accuracy.

The methods improve disease progression prediction from incomplete clinical data.

Abstract

Multiple Sclerosis (MS) is a chronic disease characterized by progressive or alternate impairment of neurological functions (motor, sensory, visual, and cognitive). Predicting disease progression with a probabilistic and time-dependent approach might help in suggesting interventions that can delay the progression of the disease. However, extracting informative knowledge from irregularly collected longitudinal data is difficult, and missing data pose significant challenges. MS progression is measured through the Expanded Disability Status Scale (EDSS), which quantifies and monitors disability in MS over time. EDSS assesses impairment in eight functional systems (FS). Frequently, only the EDSS score assigned by clinicians is reported, while FS sub-scores are missing. Imputing these scores might be useful, especially to stratify patients according to their phenotype assessed over the disease progression. This study aimed at i) exploring different methodologies for imputing missing FS sub-scores, and ii) predicting the EDSS score using complete clinical data. Results show that Exponential Weighted Moving Average achieved the lowest error rate in the missing data imputation task; furthermore, the combination of Classification and Regression Trees for the imputation and SVM for the prediction task obtained the best accuracy.