Cooperative effects in feature importance of individual patterns: Application to air pollutants and Alzheimer’s disease

Leveraging recent advances in the analysis of synergy and redundancy in systems of random variables, an adaptive version of the widely used metric Leave One Covariate Out (LOCO) has been recently proposed to quantify cooperative effects in feature importance (Hi-Fi), a key technique in explainable artificial intelligence (XAI), so as to disentangle high-order effects involving a particular input feature in regression problems. Differently from standard feature importance tools, where a single score measures the relevance of each feature, each feature is here characterized by three scores, a two-body (unique) score and higher-order scores (redundant and synergistic). This paper presents a framework to assign those three scores (unique, redundant, and synergistic) to each individual pattern of the data set, while comparing it with the well-known measure of feature importance named Shapley effect . To illustrate the potential of the proposed framework, we focus on a One-Health application: the relation between air pollutants and Alzheimer’s disease mortality rate. Our main result is the synergistic association between features related to O 3 and NO 2 with mortality, especially in the provinces of Bergamo and Brescia; notably also the density of urban green areas displays synergistic influence with pollutants for the prediction of AD mortality. Our results place local Hi-Fi as a promising tool of wide applicability, which opens new perspectives for XAI as well as to analyze high-order relationships in complex systems. • Feature Importance is a major task of Explainable Artificial Intelligence. • Tools from higher-order-interactions allow to quantify the cooperation of features. • Here we quantify the cooperation (synergy) of features on each individual pattern. • We apply our framework to the association between air pollution and Alzheimer.