From Dyad to Triad: Eliciting XAI Requirements in Stroke Rehabilitation

2026-07-28

AI Summary

This study addresses the challenge that stroke patients, hindered by communication impairments and a lack of explanatory mental models, struggle to articulate their needs for explainable artificial intelligence (XAI). To overcome this, the work introduces a scaffolded approach and develops a video-based XAI requirements elicitation protocol, incorporating strategies such as analogical mapping, projected personae, forced binary choices, and extended response windows to reduce cognitive load and facilitate expression. The pilot implementation successfully uncovered heterogeneous—and at times conflicting—XAI preferences between patients and caregivers, identified three types of elicitation-induced biases (normative bias, confirmation bias, and presence effect), and derived a reusable risk-mitigation guideline. This contribution establishes a methodological foundation for designing trustworthy human-AI systems in healthcare contexts.

Abstract

Eliciting explainable AI (XAI) requirements from stroke survivors presents a methodological challenge with direct implications for the design of trustworthy brain-computer interfaces for rehabilitation. How can patients and caregivers articulate preferences about algorithmic transparency when they lack conceptual frameworks for explainability, and when standard elicitation approaches are structurally inadequate for users with acquired communication disorders? We present a video-based scaffolding protocol for XAI requirements elicitation, developed and piloted in a rehabilitation context. In a formative study with three stroke survivors (two with moderate-to-severe aphasia) and three caregivers, facilitators employed four scaffolding approaches alongside the videos: 1) analogical bridging mapping AI states to familiar systems, 2) projective personas depersonalising sensitive topics, 3) binary forcing reducing cognitive load, and 4) extended response time. These approaches successfully surfaced heterogeneous, sometimes conflicting XAI needs across participants. Reflexive analysis additionally revealed three systematic facilitation biases, namely, normative bias, hypothesis confirmation bias, and presence effect, where scaffolding inadvertently shaped responses. We present these as protocol risk guidelines for practitioners. Together, the protocol and guidelines constitute a reusable methodological contribution for eliciting patient-facing XAI requirements in rehabilitation, arguing that such elicitation is a necessary prerequisite for trustworthy human-machine systems design, not an optional preliminary.

Problem

• explainable AI
• stroke rehabilitation
• requirements elicitation
• acquired communication disorders
• trustworthy AI

Innovation

• explainable AI (XAI)
• requirements elicitation
• scaffolding protocol
• stroke rehabilitation
• communication disorders