The PREDICTOR project integrates data from (i) a robotic device specifically developed for upper limb rehabilitation, (ii) Inertial Measurement Units, (iii) wearable sensors for home monitoring, and (iv) clinical scales. 

These data are analyzed by leveraging Artificial Intelligence and Machine Learning techniques, which are playing a significantly increasing role in interpreting data coming from digital health technologies. In fact, they may provide reliable tools to support clinicians' decisions, contributing to identify timely therapeutic decisions in the context of motor recovery prediction for stroke patients with upper limb motor disability.

Particularly, the topic of model explainability is becoming crucial for machine learning (ML) to unveil the reasoning behind the system’s decision and justification of its response. As this aspect can provide arguments to the evidence-based medicine and become determinant when supporting with decisions on patients management and care, we address model explainability in our analyses.