Deciphering knee osteoarthritis diagnostic features with explainable artificial intelligence: A systematic review

TL;DR

This systematic review explores how explainable AI techniques improve transparency and trust in diagnosing knee osteoarthritis, highlighting their potential to enhance clinical decision-making.

Contribution

It is the first survey of XAI methods applied to knee OA diagnosis, analyzing data and model interpretability to promote clinical adoption.

Findings

XAI enhances transparency in knee OA diagnosis

Different XAI techniques reveal model decision processes

Potential for increased clinical trust and adoption

Abstract

Existing artificial intelligence (AI) models for diagnosing knee osteoarthritis (OA) have faced criticism for their lack of transparency and interpretability, despite achieving medical-expert-like performance. This opacity makes them challenging to trust in clinical practice. Recently, explainable artificial intelligence (XAI) has emerged as a specialized technique that can provide confidence in the model's prediction by revealing how the prediction is derived, thus promoting the use of AI systems in healthcare. This paper presents the first survey of XAI techniques used for knee OA diagnosis. The XAI techniques are discussed from two perspectives: data interpretability and model interpretability. The aim of this paper is to provide valuable insights into XAI's potential towards a more reliable knee OA diagnosis approach and encourage its adoption in clinical practice.