Evaluating Explainable AI Methods in Deep Learning Models for Early Detection of Cerebral Palsy

TL;DR

This study evaluates the reliability of XAI methods, specifically CAM and Grad-CAM, in deep learning models for early Cerebral Palsy detection using infant skeletal movement data, emphasizing robustness and interpretability.

Contribution

It introduces a quantitative assessment of XAI methods in a novel medical application, comparing their effectiveness and robustness in a deep learning ensemble for CP prediction.

Findings

Grad-CAM outperforms CAM in stability (RISv)

Both XAI methods identify key body points influencing predictions

Ensemble models show varied XAI performance results

Abstract

Early detection of Cerebral Palsy (CP) is crucial for effective intervention and monitoring. This paper tests the reliability and applicability of Explainable AI (XAI) methods using a deep learning method that predicts CP by analyzing skeletal data extracted from video recordings of infant movements. Specifically, we use XAI evaluation metrics -- namely faithfulness and stability -- to quantitatively assess the reliability of Class Activation Mapping (CAM) and Gradient-weighted Class Activation Mapping (Grad-CAM) in this specific medical application. We utilize a unique dataset of infant movements and apply skeleton data perturbations without distorting the original dynamics of the infant movements. Our CP prediction model utilizes an ensemble approach, so we evaluate the XAI metrics performances for both the overall ensemble and the individual models. Our findings indicate that both XAI methods effectively identify key body points influencing CP predictions and that the explanations are robust against minor data perturbations. Grad-CAM significantly outperforms CAM in the RISv metric, which measures stability in terms of velocity. In contrast, CAM performs better in the RISb metric, which relates to bone stability, and the RRS metric, which assesses internal representation robustness. Individual models within the ensemble show varied results, and neither CAM nor Grad-CAM consistently outperform the other, with the ensemble approach providing a representation of outcomes from its constituent models.