Expectations and Limitations of Artificial Intelligence in Blood Cancer Diagnosis
In this commentary, we open the debate on what can be expected from artificial intelligence (AI) in the diagnosis of hematologic cancers. We discuss the key factors that make AI solutions robust, trustworthy, and, above all, generalizable, with particular emphasis on the importance of dataset quality in shaping the performance and effectiveness of AI models.
Authors
- Charlotte Syrykh (ORCID: https://orcid.org/0000-0002-3201-6109)
- P. Brousset
- Sarah Bertoli
- Jean-Marc Alliot
Institutions
- Centre de Recherches en Cancérologie de Toulouse (FR)
- Toulouse Mathematics Institute (FR)
- Institut de Recherche en Informatique de Toulouse (FR)
Publication Details
- Journal
- Blood Cancer Discovery
- Published
- 2026-01-26
- DOI
- https://doi.org/10.1158/2643-3230.bcd-25-0443
- Primary Topic
- AI in cancer detection
- Type
- article
- Field-Weighted Citation Impact
- 0.00