EUVIMEDEUVIMED entdecken
Crossref

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

Veroniki Komninaka, Sofia Liossi, Nikolaos J Tsagarakis iD, Ioanna Fotopoulou, Georgios Oudatzis iD, Ioulia Chaliori, Christina Karela, Dimitrios Liakopoulos, Paraskevi Vasileiou, Effie G Papageorgiou, Georgios Paterakis

International Journal of Laboratory Hematology · 2026-04 · 48 (2) · 447-457

DOI: 10.1111/ijlh.70033 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Laboratory Hematology, online erschienen am 02.12.2025. Verfasst von Veroniki Komninaka und 10 weiteren Autor:innen. Beteiligte Einrichtung: Hematology Laboratory, GNA G. Gennimatas, Athens, Greece. Hauptthemen laut MEDLINE: Machine Learning, Algorithms, Anemia, Iron-Deficiency. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 36 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Introduction

Thalassemia is a major global health concern, as declared by the World Health Organization (WHO). Accurate screening of heterozygotes is of paramount importance for diagnostic guidance and disease mitigation.

Methods

Multiclass machine‐learning (ML) models were developed to classify alpha, beta, and delta/beta‐thalassemia heterozygotes, individuals with iron deficiency microcytic anemia and healthy individuals. Complete blood count (CBC) data were derived from 1518 individuals, simultaneously measured in four different hematological analyzers [Sysmex K‐1000 (Sysmex), Cell‐Dyn Sapphire (Abbott), ADVIA 2120 (Siemens), BC‐6800 (Mindray)]. The Recursive Feature Elimination (RFE) method was applied to investigate the optimal number and combination of hematological parameters required for adequate model training, and their importance was determined using the SHAP method. Random Forest classifier and Active Learning (AL) method were used to evaluate diagnostic accuracy and enhance the model's performance, respectively. Dimensionality reduction techniques were applied for visualization purposes. Additionally, the existence of subclusters within each class was investigated using unsupervised techniques.

Results

Four hematological parameters (MCH, MCV, HGB, and RDW) are sufficient to classify basic types of microcytosis, achieving an accuracy of over 80%. Adding further parameters to the training process can improve the stability and reliability of the model when applied to unseen data, but does not increase test accuracy beyond 90%. Each microcytosis cluster is discriminated by assigning different weights to selected hematological parameters, forming five distinct clusters in the 2D plane (heterozygous alpha‐, beta‐, and delta/beta‐thalassemia, iron deficiency anemia, and normal individuals). The greatest overlap between clusters occurs between alpha‐ and beta‐thalassemia. The alpha‐thalassemia cluster appears to have a more diffuse scatter on the 2D plane, but two distinct subclusters are identified within this class, characterized by the differential expression of specific parameters (PCT, MPV, P‐LCR, PDW, MCV, MCH, and RBC). The developed model can estimate the probabilities of classifying a new case into the core established clusters and, in the case of alpha‐thalassemia, the possible subcluster.

Conclusion

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.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Machine LearningAlgorithmsAnemia, Iron-DeficiencyHumansMaleFemaleErythrocyte IndicesAdultBlood Cell CountThalassemia

Stichwörter der Autor:innen

CBCanemiamachine learningmicrocytosisthalassemia

Autor:innen und Institutionen

  • Hematology Laboratory, GNA G. Gennimatas, Athens, Greece.
  • Centre of Excellence in Rare Haematological (Haemoglobinopathies) & Rare Metabolic (Gaucher Disease) Diseases, Laiko General Hospital, Athens, Greece.
  • Laboratory of Reliability and Quality Control in Laboratory Hematology, Department of Biomedical Sciences, School of Health and Welfare Sciences, University of West Attica, Athens, Greece.
  • Department of Immunology, GNA G. Gennimatas, Athens, Greece.
  • Flowdiagnosis Diagnostic Center, Athens, Greece.

ORCID-Profile: Nikolaos J Tsagarakis, Georgios Oudatzis

Zitieren

APA

Komninaka, V., Liossi, S., Tsagarakis, N. J., Fotopoulou, I., Oudatzis, G., Chaliori, I., Karela, C., Liakopoulos, D., Vasileiou, P., Papageorgiou, E. G., & Paterakis, G. (2026). 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. International Journal of Laboratory Hematology, 48(2), 447-457. https://doi.org/10.1111/ijlh.70033

Vancouver

Komninaka V, Liossi S, Tsagarakis NJ, Fotopoulou I, Oudatzis G, Chaliori I, et al. 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. International Journal of Laboratory Hematology. 2026;48(2):447-457. doi:10.1111/ijlh.70033

BibTeX
@article{Komninaka2026,
  author = {Komninaka, Veroniki and Liossi, Sofia and Tsagarakis, Nikolaos J and Fotopoulou, Ioanna and Oudatzis, Georgios and Chaliori, Ioulia and Karela, Christina and Liakopoulos, Dimitrios and Vasileiou, Paraskevi and Papageorgiou, Effie G and Paterakis, Georgios},
  title = {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},
  journal = {International Journal of Laboratory Hematology},
  year = {2026},
  volume = {48},
  number = {2},
  pages = {447--457},
  doi = {10.1111/ijlh.70033}
}
Kostenlos starten →