A Concept-based approach to Voice Disorder Detection

TL;DR

This paper explores concept-based, explainable AI models for voice disorder detection, aiming to match deep neural network performance while enhancing interpretability for clinical trustworthiness.

Contribution

It introduces the use of concept-based models like CBM and CEM for voice disorder detection, providing transparency without sacrificing accuracy.

Findings

Concept-based models achieve comparable performance to traditional DNNs.

Enhanced interpretability facilitates clinical trust and decision-making.

Potential for non-invasive, explainable healthcare diagnostics.

Abstract

Voice disorders affect a significant portion of the population, and the ability to diagnose them using automated, non-invasive techniques would represent a substantial advancement in healthcare, improving the quality of life of patients. Recent studies have demonstrated that artificial intelligence models, particularly Deep Neural Networks (DNNs), can effectively address this task. However, due to their complexity, the decision-making process of such models often remain opaque, limiting their trustworthiness in clinical contexts. This paper investigates an alternative approach based on Explainable AI (XAI), a field that aims to improve the interpretability of DNNs by providing different forms of explanations. Specifically, this works focuses on concept-based models such as Concept Bottleneck Model (CBM) and Concept Embedding Model (CEM) and how they can achieve performance comparable to traditional deep learning methods, while offering a more transparent and interpretable decision framework.