Explainability Design Patterns in Clinical Decision Support Systems
Explainability Design Patterns in Clinical Decision Support Systems
This paper reports on the ongoing PhD project in the field of explaining the clinical decision support systems (CDSSs) recommendations to medical practitioners. Recently, the explainability research in the medical domain has witnessed a surge of advances with a focus on two main methods: The first focuses on developing models that are explainable and transparent in its nature (e.g. rule-based algorithms). The second investigates the interpretability of the black-box models without looking at the mechanism behind it (e.g. LIME) as a post-hoc explanation. However, overlooking the human-factors and the usability aspect of the explanation introduced new risks following the system recommendations, e.g. over-trust and under-trust. Due to such limitation, there is a growing demand for usable explanations for CDSSs to enable the integration of trust calibration and informed decision-making in these systems by identifying when the recommendation is correct to follow. This research aims to develop explainability design patterns with the aim of calibrating medical practitioners trust in the CDSSs. This paper concludes the PhD methodology and literature around the research problem is also discussed.
Decision support systems, Explainability, Trust, User-centred design
613-620
Naiseh, Mohammad
ab9d6b3c-569c-4d7c-9bfd-61bbb8983049
2020
Naiseh, Mohammad
ab9d6b3c-569c-4d7c-9bfd-61bbb8983049
Naiseh, Mohammad
(2020)
Explainability Design Patterns in Clinical Decision Support Systems.
Dalpiaz, Fabiano, Zdravkovic, Jelena and Loucopoulos, Pericles
(eds.)
In Research Challenges in Information Science. RCIS 2020.
vol. 385 LNBIP,
Springer.
.
(doi:10.1007/978-3-030-50316-1_45).
Record type:
Conference or Workshop Item
(Paper)
Abstract
This paper reports on the ongoing PhD project in the field of explaining the clinical decision support systems (CDSSs) recommendations to medical practitioners. Recently, the explainability research in the medical domain has witnessed a surge of advances with a focus on two main methods: The first focuses on developing models that are explainable and transparent in its nature (e.g. rule-based algorithms). The second investigates the interpretability of the black-box models without looking at the mechanism behind it (e.g. LIME) as a post-hoc explanation. However, overlooking the human-factors and the usability aspect of the explanation introduced new risks following the system recommendations, e.g. over-trust and under-trust. Due to such limitation, there is a growing demand for usable explanations for CDSSs to enable the integration of trust calibration and informed decision-making in these systems by identifying when the recommendation is correct to follow. This research aims to develop explainability design patterns with the aim of calibrating medical practitioners trust in the CDSSs. This paper concludes the PhD methodology and literature around the research problem is also discussed.
Text
Doctoral
- Accepted Manuscript
More information
Published date: 2020
Additional Information:
Funding Information:
This work is partially funded by iQ HealthTech and Bournemouth university PGR development fund.
Publisher Copyright:
© 2020, Springer Nature Switzerland AG.
Copyright:
Copyright 2020 Elsevier B.V., All rights reserved.
Venue - Dates:
14th International Conference on Research Challenges in Information Sciences, RCIS 2020, , Limassol, Cyprus, 2020-09-23 - 2020-09-25
Keywords:
Decision support systems, Explainability, Trust, User-centred design
Identifiers
Local EPrints ID: 455671
URI: http://eprints.soton.ac.uk/id/eprint/455671
ISSN: 1865-1348
PURE UUID: 27912dad-9968-4266-917c-61bb96ed50a6
Catalogue record
Date deposited: 30 Mar 2022 16:44
Last modified: 18 Mar 2024 04:02
Export record
Altmetrics
Contributors
Author:
Mohammad Naiseh
Editor:
Fabiano Dalpiaz
Editor:
Jelena Zdravkovic
Editor:
Pericles Loucopoulos
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics