Saved in:
Bibliographic Details
Main Authors: Hou, Jun, Wang, Lucy Lu
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