Introduction to XAI and Clinical Decision Support

Abstract

Artificial intelligence (AI) and machine learning (ML) offer significant opportunities in healthcare for innovation with its ability to solve cognitive problems normally requiring human intelligence. However, the potential of ML in healthcare has not been realised to date, with limited existing reports of the clinical and cost benefits that have arisen from their real-world in clinical practice. This is due to the lack of understanding about how some ML models operate and ultimately the way they come to make decisions. Explainable AI (XAI) has emerged as a response to this problem investigating methods and techniques that provide insights into the outcome of an ML model and present it in qualitative understandable terms or visualisations to the stakeholders of the model. This chapter introduces XAI and provides some examples of its use within healthcare.