Exploring the Effect of Explanation Content and Format on User Comprehension and Trust in Healthcare
This addresses the need for trustworthy AI in healthcare by showing that explanation format can influence user perceptions, though it is incremental as it builds on existing explanation methods.
The study investigated how the content and format of explanations for an AI healthcare tool (QCancer) affect user comprehension and trust, finding that text-based Occlusion-1 explanations outperformed chart-based SHAP explanations, with format being a key factor.
AI-driven tools for healthcare are widely acknowledged as potentially beneficial to health practitioners and patients, e.g. the QCancer regression tool for cancer risk prediction. However, for these tools to be trusted, they need to be supplemented with explanations. We examine how explanations' content and format affect user comprehension and trust when explaining QCancer's predictions. Regarding content, we deploy the SHAP and Occlusion-1 explanation methods. Regarding format, we present SHAP explanations, conventionally, as charts (SC) and Occlusion-1 explanations as charts (OC) as well as text (OT), to which their simpler nature lends itself. We conduct experiments with two sets of stakeholders: the general public (representing patients) and medical students (representing healthcare practitioners). Our experiments showed higher subjective comprehension and trust for Occlusion-1 over SHAP explanations based on content. However, when controlling for format, only OT outperformed SC, suggesting this trend is driven by preferences for text. Other findings corroborated that explanation format, rather than content, is often the critical factor.