Home // HEALTHINFO 2023, The Eighth International Conference on Informatics and Assistive Technologies for Health-Care, Medical Support and Wellbeing // View article
Authors:
Holger Ziekow
Norbert Marschner
Dunja Klein
Benjamin Kasenda
Nina Haug
Keywords: Explainable AI; Oncology; Medical Information Systems
Abstract:
Real-world data on the treatment histories of patients in everyday care contain a large amount of latent knowledge which, to date, is almost only made available via publication with a considerable time lag and only in relation to specific issues. Artificial Intelligence (AI) models can capture the knowledge contained in this kind of data and transfer it to new scenarios. We aim to develop an AI-based tool that enables dynamic data exploration and analysis of real-world datasets on medical treatments. The purpose of the tool is to support oncologists in their decision-making process through a system that is trained with prospectively documented real-world data on historical treatment decisions for a large population of patients. It will facilitate research on treatment routines for specific patient populations by providing information on likely therapy choices. Leveraging Explainable AI (XAI) techniques, the reasoning of the analytics system is made transparent to the user. In this paper, we describe and test a system that follows this concept. Specifically, we address the two use cases (a) “therapy selection” and (b) “identification of similar patients”. We test respective AI and XAI mechanisms with real-world data. Our analysis provides insights into the potential of the approach of using AI/XAI as supporting analytics system for oncologists as well as on the data requirements.
Pages: 13 to 21
Copyright: Copyright (c) IARIA, 2023
Publication date: November 13, 2023
Published in: conference
ISSN: 2519-8491
ISBN: 978-1-68558-105-3
Location: Valencia, Spain
Dates: from November 13, 2023 to November 17, 2023