An Unsupervised Approach to Achieve Supervised-Level Explainability in Healthcare Records

Joakim Edin, Maria Maistro, Lars Maaløe, Lasse Borgholt, Jakob Havtorn, Tuukka Ruotsalo


Abstract
Electronic healthcare records are vital for patient safety as they document conditions, plans, and procedures in both free text and medical codes. Language models have significantly enhanced the processing of such records, streamlining workflows and reducing manual data entry, thereby saving healthcare providers significant resources. However, the black-box nature of these models often leaves healthcare professionals hesitant to trust them. State-of-the-art explainability methods increase model transparency but rely on human-annotated evidence spans, which are costly. In this study, we propose an approach to produce plausible and faithful explanations without needing such annotations. We demonstrate on the automated medical coding task that adversarial robustness training improves explanation plausibility and introduce AttInGrad, a new explanation method superior to previous ones. By combining both contributions in a fully unsupervised setup, we produce explanations of comparable quality, or better, to that of a supervised approach. We release our code and model weights.
Anthology ID:
2024.emnlp-main.280
Volume:
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2024
Address:
Miami, Florida, USA
Editors:
Yaser Al-Onaizan, Mohit Bansal, Yun-Nung Chen
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4869–4890
Language:
URL:
https://aclanthology.org/2024.emnlp-main.280
DOI:
Bibkey:
Cite (ACL):
Joakim Edin, Maria Maistro, Lars Maaløe, Lasse Borgholt, Jakob Havtorn, and Tuukka Ruotsalo. 2024. An Unsupervised Approach to Achieve Supervised-Level Explainability in Healthcare Records. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 4869–4890, Miami, Florida, USA. Association for Computational Linguistics.
Cite (Informal):
An Unsupervised Approach to Achieve Supervised-Level Explainability in Healthcare Records (Edin et al., EMNLP 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.emnlp-main.280.pdf
Software:
 2024.emnlp-main.280.software.zip