Clinically Meaningful Explainability for NeuroAI: An ethical, technical, and clinical perspective

TL;DR

This paper emphasizes the importance of clinically meaningful explainability (CME) in neuroAI, advocating for explanations that are relevant and actionable for clinicians rather than exhaustive technical details, to improve patient care.

Contribution

It introduces the NeuroXplain architecture, providing design recommendations for implementing CME in neurostimulation devices to align AI explanations with clinical needs.

Findings

Clinically relevant explanations improve clinician understanding.

Full technical transparency can overwhelm clinicians and reduce usability.

NeuroXplain offers a practical framework for CME implementation.

Abstract

While explainable AI (XAI) is often heralded as a means to enhance transparency and trustworthiness in closed-loop neurotechnology for psychiatric and neurological conditions, its real-world prevalence remains low. Moreover, empirical evidence suggests that the type of explanations provided by current XAI methods often fails to align with clinicians' end-user needs. In this viewpoint, we argue that clinically meaningful explainability (CME) is essential for AI-enabled closed-loop medical neurotechnology and must be addressed from an ethical, technical, and clinical perspective. Instead of exhaustive technical detail, clinicians prioritize clinically relevant, actionable explanations, such as clear representations of input-output relationships and feature importance. Full technical transparency, although theoretically desirable, often proves irrelevant or even overwhelming in practice, as it may lead to informational overload. Therefore, we advocate for CME in the neurotechnology domain: prioritizing actionable clarity over technical completeness and designing interface visualizations that intuitively map AI outputs and key features into clinically meaningful formats. To this end, we introduce a reference architecture called NeuroXplain, which translates CME into actionable technical design recommendations for any future neurostimulation device. Our aim is to inform stakeholders working in neurotechnology and regulatory framework development to ensure that explainability fulfills the right needs for the right stakeholders and ultimately leads to better patient treatment and care.