The Application of Machine‐Learning Algorithms for Multiclass Classification of Microcytic Anemia Revealed That a Minimum Required Number of Hematological Parameters Is Enough to Achieve High Diagnostic Accuracy
The application of ML models for the automated differential diagnosis of microcytosis, using CBC data, revealed that the diagnostic accuracy is not proportionally dependent on the use of an increasing number of hematological parameters. A developed model is proposed which can correctly classify a new case in the core clusters or subclusters of patients with microcytosis.
Authors
- Georgios Oudatzis (ORCID: https://orcid.org/0000-0002-8539-5202)
- Veroniki Komninaka (ORCID: https://orcid.org/0009-0004-1935-9205)
- Effie Papageorgiou (ORCID: https://orcid.org/0000-0001-8475-3226)
- Paraskevi Vasileiou
- Ioulia Chaliori (ORCID: https://orcid.org/0000-0003-4151-043X)
- Nikolaos J. Tsagarakis (ORCID: https://orcid.org/0000-0002-9759-0048)
- Sofia Liossi (ORCID: https://orcid.org/0000-0001-8388-8487)
- Dimitrios A. Liakopoulos
- Georgios Paterakis (ORCID: https://orcid.org/0000-0001-9299-8346)
- Christina Karela
- Ioanna Fotopoulou
Institutions
- University of West Attica (GR)
- General Hospital of Athens G. Genimatas (GR)
- Laiko General Hospital of Athens (GR)
- Quality and Reliability (Greece) (GR)
- Athens Medical Center (GR)
Publication Details
- Journal
- International Journal of Laboratory Hematology
- Published
- 2025-12-02
- DOI
- https://doi.org/10.1111/ijlh.70033
- Citations
- 1
- Primary Topic
- Digital Imaging for Blood Diseases
- Type
- article
- Field-Weighted Citation Impact
- 1.28