A new study on engineering applications of AI, co-authored by Prof. Javier Villalba-Díez and Prof. Joaquín Ordieres-Meré and published in Digital Signal Processing, demonstrates how digitalization—specifically deep learning and explainable AI—can bring precision and transparency to the monitoring of neurological disorders like Multiple Sclerosis (MS).

The research introduces a novel method that combines Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) models to classify gait patterns from inertial sensor data. What sets this work apart is its focus on explainability: the AI does not only provide high classification accuracy, but also generates interpretable visualizations that clinicians and researchers can use to understand the reasoning behind each prediction.

This human-centered approach bridges a critical gap between powerful AI tools and the need for transparency in clinical settings. It paves the way for digital health solutions that are not only technologically robust but also clinically trustworthy.

The work supports the broader vision of DigiHealth platform, reinforcing digitalization as a key driver in the transformation of personalized and proactive healthcare.