Translating the machine; An assessment of clinician understanding of ophthalmological artificial intelligence outputs
Clinicians' trust in AI algorithms are affected by explainability methods and factors, including AI's performance, personal judgments and clinical experience. The development of clinical AI systems should consider the above and these responses ideally be factored into real-world assessments. Use of this study's findings could help improve the real world validity of medical AI systems by enhancing the human-computer interactions, with preferred explainability techniques tailored to specific situations.
Authors
- Tariq Aslam (ORCID: https://orcid.org/0000-0002-9739-7280)
- Hannah Frost (ORCID: https://orcid.org/0000-0002-4398-0382)
- Donna M. Graham (ORCID: https://orcid.org/0000-0001-6500-8140)
- Shu Lun Mak (ORCID: https://orcid.org/0000-0002-1675-2237)
- Dónal Landers (ORCID: https://orcid.org/0000-0001-8376-9779)
- Oskar Wysocki (ORCID: https://orcid.org/0000-0002-7053-4919)
Institutions
- Leeds Teaching Hospitals NHS Trust (GB)
- St James's University Hospital (GB)
- Manchester Royal Eye Hospital (GB)
- Wilton Park (GB)
- Cancer Research UK Manchester Institute (GB)
- The Christie NHS Foundation Trust (GB)
Publication Details
- Journal
- International Journal of Medical Informatics
- Published
- 2025-05-06
- DOI
- https://doi.org/10.1016/j.ijmedinf.2025.105958
- Citations
- 2
- Primary Topic
- Artificial Intelligence in Healthcare and Education
- Type
- article
- Field-Weighted Citation Impact
- 1.31
Funders
- Cancer Research UK