Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2502.20478 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911123845939200 |
|---|---|
| author | Hou, Jun Wang, Lucy Lu |
| author_facet | Hou, Jun Wang, Lucy Lu |
| contents | Explainable AI (XAI) techniques are necessary to help clinicians make sense of AI predictions and integrate predictions into their decision-making workflow. In this work, we conduct a survey study to understand clinician preference among different XAI techniques when they are used to interpret model predictions over text-based EHR data. We implement four XAI techniques (LIME, Attention-based span highlights, exemplar patient retrieval, and free-text rationales generated by LLMs) on an outcome prediction model that uses ICU admission notes to predict a patient's likelihood of experiencing in-hospital mortality. Using these XAI implementations, we design and conduct a survey study of 32 practicing clinicians, collecting their feedback and preferences on the four techniques. We synthesize our findings into a set of recommendations describing when each of the XAI techniques may be more appropriate, their potential limitations, as well as recommendations for improvement. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_20478 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Explainable AI for Clinical Outcome Prediction: A Survey of Clinician Perceptions and Preferences Hou, Jun Wang, Lucy Lu Computation and Language Explainable AI (XAI) techniques are necessary to help clinicians make sense of AI predictions and integrate predictions into their decision-making workflow. In this work, we conduct a survey study to understand clinician preference among different XAI techniques when they are used to interpret model predictions over text-based EHR data. We implement four XAI techniques (LIME, Attention-based span highlights, exemplar patient retrieval, and free-text rationales generated by LLMs) on an outcome prediction model that uses ICU admission notes to predict a patient's likelihood of experiencing in-hospital mortality. Using these XAI implementations, we design and conduct a survey study of 32 practicing clinicians, collecting their feedback and preferences on the four techniques. We synthesize our findings into a set of recommendations describing when each of the XAI techniques may be more appropriate, their potential limitations, as well as recommendations for improvement. |
| title | Explainable AI for Clinical Outcome Prediction: A Survey of Clinician Perceptions and Preferences |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2502.20478 |