Machine Learning for ALSFRS-R Score Prediction: Making Sense of the Sensor Data

TL;DR

This paper explores machine learning models, including naive and ElasticNet regression, to predict ALSFRS-R scores from sensor data, aiming to improve early detection and personalized care for ALS patients.

Contribution

It evaluates and compares simple and regularized regression models for predicting ALS progression from sensor data, highlighting the effectiveness of naive and ElasticNet approaches.

Findings

Naive model achieved MAE of 0.20 and RMSE of 0.49.

ElasticNet regression achieved MAE of 0.22 and RMSE of 0.50.

Naive approach slightly outperformed ElasticNet in predictive accuracy.

Abstract

Amyotrophic Lateral Sclerosis (ALS) is characterized as a rapidly progressive neurodegenerative disease that presents individuals with limited treatment options in the realm of medical interventions and therapies. The disease showcases a diverse range of onset patterns and progression trajectories, emphasizing the critical importance of early detection of functional decline to enable tailored care strategies and timely therapeutic interventions. The present investigation, spearheaded by the iDPP@CLEF 2024 challenge, focuses on utilizing sensor-derived data obtained through an app. This data is used to construct various machine learning models specifically designed to forecast the advancement of the ALS Functional Rating Scale-Revised (ALSFRS-R) score, leveraging the dataset provided by the organizers. In our analysis, multiple predictive models were evaluated to determine their efficacy in handling ALS sensor data. The temporal aspect of the sensor data was compressed and amalgamated using statistical methods, thereby augmenting the interpretability and applicability of the gathered information for predictive modeling objectives. The models that demonstrated optimal performance were a naive baseline and ElasticNet regression. The naive model achieved a Mean Absolute Error (MAE) of 0.20 and a Root Mean Square Error (RMSE) of 0.49, slightly outperforming the ElasticNet model, which recorded an MAE of 0.22 and an RMSE of 0.50. Our comparative analysis suggests that while the naive approach yielded marginally better predictive accuracy, the ElasticNet model provides a robust framework for understanding feature contributions.