Diagrammatization and Abduction to Improve AI Interpretability With Domain-Aligned Explanations for Medical Diagnosis

要旨

Many visualizations have been developed for explainable AI (XAI), but they often require further reasoning by users to interpret. Investigating XAI for high-stakes medical diagnosis, we propose improving domain alignment with diagrammatic and abductive reasoning to reduce the interpretability gap. We developed DiagramNet to predict cardiac diagnoses from heart auscultation, select the best-fitting hypothesis based on criteria evaluation, and explain with clinically-relevant murmur diagrams. The ante-hoc interpretable model leverages domain-relevant ontology, representation, and reasoning process to increase trust in expert users. In modeling studies, we found that DiagramNet not only provides faithful murmur shape explanations, but also has better performance than baseline models. We demonstrate the interpretability and trustworthiness of diagrammatic, abductive explanations in a qualitative user study with medical students, showing that clinically-relevant, diagrammatic explanations are preferred over technical saliency map explanations. This work contributes insights into providing domain-aligned explanations for user-centric XAI in complex domains.

著者
Brian Y. Lim
National University of Singapore, Singapore, Singapore
Joseph Paul. Cahaly
Massachusetts Institute of Technology, Cambridge, Massachusetts, United States
Yu Feng Chester Sng
National University of Singapore, Singapore, Singapore
Adam Chew
National University of Singapore, Singapore, --- Select One ---, Singapore
DOI

10.1145/3706598.3714058

論文URL

https://dl.acm.org/doi/10.1145/3706598.3714058

動画

会議: CHI 2025

The ACM CHI Conference on Human Factors in Computing Systems (https://chi2025.acm.org/)

セッション: Explainable AI

G303
7 件の発表
2025-04-29 01:20:00
2025-04-29 02:50:00
日本語まとめ
読み込み中…