AI Readiness in Healthcare through Storytelling XAI

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Dubey, Akshat, Yang, Zewen, Hattab, Georges
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913589764292608
author Dubey, Akshat
Yang, Zewen
Hattab, Georges
author_facet Dubey, Akshat
Yang, Zewen
Hattab, Georges
contents Artificial Intelligence is rapidly advancing and radically impacting everyday life, driven by the increasing availability of computing power. Despite this trend, the adoption of AI in real-world healthcare is still limited. One of the main reasons is the trustworthiness of AI models and the potential hesitation of domain experts with model predictions. Explainable Artificial Intelligence (XAI) techniques aim to address these issues. However, explainability can mean different things to people with different backgrounds, expertise, and goals. To address the target audience with diverse needs, we develop storytelling XAI. In this research, we have developed an approach that combines multi-task distillation with interpretability techniques to enable audience-centric explainability. Using multi-task distillation allows the model to exploit the relationships between tasks, potentially improving interpretability as each task supports the other leading to an enhanced interpretability from the perspective of a domain expert. The distillation process allows us to extend this research to large deep models that are highly complex. We focus on both model-agnostic and model-specific methods of interpretability, supported by textual justification of the results in healthcare through our use case. Our methods increase the trust of both the domain experts and the machine learning experts to enable a responsible AI.
format Preprint
id arxiv_https___arxiv_org_abs_2410_18725
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle AI Readiness in Healthcare through Storytelling XAI
Dubey, Akshat
Yang, Zewen
Hattab, Georges
Artificial Intelligence
Artificial Intelligence is rapidly advancing and radically impacting everyday life, driven by the increasing availability of computing power. Despite this trend, the adoption of AI in real-world healthcare is still limited. One of the main reasons is the trustworthiness of AI models and the potential hesitation of domain experts with model predictions. Explainable Artificial Intelligence (XAI) techniques aim to address these issues. However, explainability can mean different things to people with different backgrounds, expertise, and goals. To address the target audience with diverse needs, we develop storytelling XAI. In this research, we have developed an approach that combines multi-task distillation with interpretability techniques to enable audience-centric explainability. Using multi-task distillation allows the model to exploit the relationships between tasks, potentially improving interpretability as each task supports the other leading to an enhanced interpretability from the perspective of a domain expert. The distillation process allows us to extend this research to large deep models that are highly complex. We focus on both model-agnostic and model-specific methods of interpretability, supported by textual justification of the results in healthcare through our use case. Our methods increase the trust of both the domain experts and the machine learning experts to enable a responsible AI.
title AI Readiness in Healthcare through Storytelling XAI
topic Artificial Intelligence
url https://arxiv.org/abs/2410.18725