Knowledge Uncertainty Estimation for Reliable Clinical Decision Support: A Delirium Risk Prognosis Case Study
While all models effectively predicted delirium risk, SNGP demonstrated superior performance in OoD detection, highlighting its potential to enhance reliability and trustworthiness of clinical decision support systems through robust KU estimation.
Authors
- Stefan Franke (ORCID: https://orcid.org/0000-0003-2101-9168)
- Sai Veeranki (ORCID: https://orcid.org/0000-0003-2009-6428)
- Adrian Lindenmeyer (ORCID: https://orcid.org/0000-0001-8977-5790)
- Daniel J. Schneider (ORCID: https://orcid.org/0000-0001-6830-0905)
- Diether Kramer
- Thomas Neumuth (ORCID: https://orcid.org/0000-0001-6999-5024)
Institutions
- Graz University of Technology (AT)
- Krankenhaus der Elisabethinen (AT)
- Leipzig University (DE)
Publication Details
- Journal
- Studies in health technology and informatics
- Published
- 2025-04-24
- DOI
- https://doi.org/10.3233/shti250192
- Citations
- 1
- Primary Topic
- Machine Learning in Healthcare
- Type
- article
- Field-Weighted Citation Impact
- 4.74