Which explanations do clinicians prefer? A comparative evaluation of XAI understandability and actionability in predicting the need for hospitalization
The findings suggest that SHAP and AraucanaXAI are promising candidates for improving the use of XAI in clinical decision support systems (DSSs), highlighting the importance of clinicians' expertise, specialty, and setting on the selection and development of supportive XAI advice. Finally, the study provides valuable insights into the design of future XAI DSSs.
Authors
- Francesco Salinaro (ORCID: https://orcid.org/0000-0002-6117-4392)
- Santi Di Pietro (ORCID: https://orcid.org/0000-0001-6486-1924)
- Lorenzo Preda (ORCID: https://orcid.org/0000-0002-5479-2766)
- Michele Catalano (ORCID: https://orcid.org/0000-0002-0379-4665)
- Paolo Sacchi (ORCID: https://orcid.org/0000-0002-9679-0419)
- Valentina Zuccaro (ORCID: https://orcid.org/0000-0001-6433-506X)
- Giuseppe Crescenzi
- Giovanna Nicora (ORCID: https://orcid.org/0000-0001-7007-0862)
- Elisabetta Pagani (ORCID: https://orcid.org/0000-0003-1795-601X)
- Riccardo Bellazzi (ORCID: https://orcid.org/0000-0002-6974-9808)
- Erika Asperges (ORCID: https://orcid.org/0000-0002-1618-8867)
- Marco Bonzano
- Chiara Podrecca (ORCID: https://orcid.org/0000-0003-4861-7547)
- Chandra Bortolotto (ORCID: https://orcid.org/0000-0002-9193-9309)
- Enea Parimbelli (ORCID: https://orcid.org/0000-0003-0679-828X)
- Laura Bergomi (ORCID: https://orcid.org/0009-0006-0359-5128)
- Caterina Fregosi (ORCID: https://orcid.org/0009-0004-7626-8131)
- Pietro Valsecchi (ORCID: https://orcid.org/0000-0002-3425-9817)
- Francesco Speciale
- Marta Anna Orlowska
Institutions
- University of Pavia (IT)
- Policlinico San Matteo Fondazione (IT)
- Istituti di Ricovero e Cura a Carattere Scientifico (IT)
- University of Milano-Bicocca (IT)
Publication Details
- Journal
- BMC Medical Informatics and Decision Making
- Published
- 2025-07-16
- DOI
- https://doi.org/10.1186/s12911-025-03045-0
- Citations
- 5
- Primary Topic
- Explainable Artificial Intelligence (XAI)
- Type
- article
- Field-Weighted Citation Impact
- 12.40