Evaluating the Explainable AI Method Grad-CAM for Breath Classification on Newborn Time Series Data

TL;DR

This study evaluates Grad-CAM, an explainable AI method, for classifying neonatal breaths from time series data, highlighting its perceived usefulness and the need for more detailed explanations among healthcare stakeholders.

Contribution

The paper provides a user study assessing Grad-CAM's effectiveness in medical time series classification, revealing challenges in achieving true transparency and stakeholder desires for better explanations.

Findings

Grad-CAM is perceived as useful by stakeholders.

Achieving true transparency remains challenging.

Participants desire more detailed explanations.

Abstract

With the digitalization of health care systems, artificial intelligence becomes more present in medicine. Especially machine learning shows great potential for complex tasks such as time series classification, usually at the cost of transparency and comprehensibility. This leads to a lack of trust by humans and thus hinders its active usage. Explainable artificial intelligence tries to close this gap by providing insight into the decision-making process, the actual usefulness of its different methods is however unclear. This paper proposes a user study based evaluation of the explanation method Grad-CAM with application to a neural network for the classification of breaths in time series neonatal ventilation data. We present the perceived usefulness of the explainability method by different stakeholders, exposing the difficulty to achieve actual transparency and the wish for more in-depth explanations by many of the participants.