Challenges facing the explainability of age prediction models: case study for two modalities

TL;DR

This paper examines the challenges of explaining age prediction models using EEG signals and lung X-rays, emphasizing the need for interpretability in high-impact fields despite high model performance.

Contribution

It provides predictive models for age based on EEG and lung X-ray data, serving as a foundation for developing explainability techniques in these modalities.

Findings

Models demonstrate high accuracy in age prediction.

Current explainability methods face challenges with these modalities.

The study highlights the importance of interpretability in sensitive applications.

Abstract

The prediction of age is a challenging task with various practical applications in high-impact fields like the healthcare domain or criminology. Despite the growing number of models and their increasing performance, we still know little about how these models work. Numerous examples of failures of AI systems show that performance alone is insufficient, thus, new methods are needed to explore and explain the reasons for the model's predictions. In this paper, we investigate the use of Explainable Artificial Intelligence (XAI) for age prediction focusing on two specific modalities, EEG signal and lung X-rays. We share predictive models for age to facilitate further research on new techniques to explain models for these modalities.