11.2022 - 02.2026

Neural dynamics and plasticity: Exploring the potential of explainable AI methods to study neuronal dynamics, connectivity, and plasticity for neurorehabilitation

This study investigated the combined effect of cognitive and brain reserves with resting-state functional connectivity on Parkinson's Disease (PD) classification. Specifically, a machine learning approach has been proposed aiming at discriminating between 52 healthy controls and 43 subjects with PD using a support vector machine (SVM) classifier. The approach was augmented with an eXplainable artificial intelligence (XAI) tool, specifically the SHapley Additive exPlanation (SHAP) method for feature ranking, explaining the underlying mechanisms guiding the model decision. The results showed an average accuracy of 94.74% using the top 20 features with the highest SHAP importance score. Specific connections, such as those governing visual central and dorsal attention, emerged as key discriminative features, significantly impacting on the model's ability to classify PD subjects.

Possibili applicazioni: This methodology can be applied for the advanced diagnostics of PD. 

Settori Scientifico Disciplinari

ING-INF/06  ELECTRONIC AND INFORMATICS BIOENGINEERING MED/26  NEUROLOGY

Spoke 2 : Neural Plasticity and Connectivity