From Interpretability to Clinically Relevant Linguistic Explanations: The Case of Spinal Surgery Decision-Support

Alexander Berman, Eleni Gregoromichelaki, Catharina Parai, Catharina Parai

2025

Abstract

Interpretable models are advantageous when compared to black-box models in the sense that their predictions can be explained in ways that are faithful to the actual reasoning steps performed by the model. However, interpretability does not automatically make AI systems aligned with how explanations are typically communicated in human language. This paper explores the relationship between interpretability and linguistic explanation needs of human users for a particular class of interpretable AI, namely generalized linear models (GLMs). First, a linguistic corpus study of patient-doctor dialogues is performed, resulting in insights that can inform the design of clinically relevant explanations of model predictions. A method for generating natural-language explanations for GLM predictions in the context of spinal surgery decision-support is then proposed, informed by the results of the corpus analysis. Findings from evaluating the proposed approach through a design workshop with orthopaedic surgeons are also presented.

Paper Citation

in Harvard Style

Berman A., Gregoromichelaki E. and Parai C. (2025). From Interpretability to Clinically Relevant Linguistic Explanations: The Case of Spinal Surgery Decision-Support. In Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 1: IAI; ISBN 978-989-758-737-5, SciTePress, pages 909-920. DOI: 10.5220/0013403800003890

in Bibtex Style

@conference{iai25,
author={Alexander Berman and Eleni Gregoromichelaki and Catharina Parai},
title={From Interpretability to Clinically Relevant Linguistic Explanations: The Case of Spinal Surgery Decision-Support},
booktitle={Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 1: IAI},
year={2025},
pages={909-920},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013403800003890},
isbn={978-989-758-737-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 1: IAI
TI - From Interpretability to Clinically Relevant Linguistic Explanations: The Case of Spinal Surgery Decision-Support
SN - 978-989-758-737-5
AU - Berman A.
AU - Gregoromichelaki E.
AU - Parai C.
PY - 2025
SP - 909
EP - 920
DO - 10.5220/0013403800003890
PB - SciTePress