EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

A Code-Free Visual Machine Learning Workflow for Automated Iron Deficiency Screening Using Routine Hematological Parameters

Qanita Sedick, Ziad Baarmah, Abdul Aziz Alqarni, Ibtessam Alosaimi, Hanni Almalki, Siham Atik, Ahmad Saqib, Ziyad Alshutayri, Nadir Hassan

AI in Clinical Medicine · 2026-08 · 2

DOI: 10.14740/aicm33 ↗

Kurz gefasst

Fachartikel in der Zeitschrift AI in Clinical Medicine, 2026-08. Verfasst von Qanita Sedick und 8 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Background

Iron deficiency anemia is a major global health burden requiring early screening. Complete blood count (CBC) parameters—hemoglobin (Hb), mean corpuscular volume (MCV), mean corpuscular hemoglobin (MCH), and mean corpuscular hemoglobin concentration (MCHC)—are key indices used to diagnose this condition. We evaluated machine learning algorithms to differentiate iron deficiency from healthy profiles using standard CBC metrics.

Methods

A retrospective analysis of 1,421 patient records from a public Kaggle dataset was conducted in Orange Data Mining to classify instances as healthy (class 0) or iron-deficient (class 1). Models were evaluated using leave-one-out (LOO) cross-validation applied to parametric logistic regression and a non-parametric decision tree. Evaluation metrics included area under the ROC curve (AUC), classification accuracy (CA), F1-score, precision, recall, and Matthews correlation coefficient (MCC).

Results

The dataset included 794 normal individuals and 627 iron-deficient patients. Logistic regression outperformed the decision tree, achieving a superior AUC (0.909 vs. 0.821), CA (0.834 vs. 0.816), and MCC (0.664 vs. 0.626). Confusion matrix analysis showed that logistic regression had higher sensitivity, correctly identifying 82.0% of iron-deficient cases compared to 77.4% by the decision tree.

Conclusion

A logistic regression model trained on basic CBC indices provides a highly accurate, sensitive, and computationally inexpensive tool for iron deficiency screening, holding significant promise for automated laboratory triage.

Zitieren

APA

Sedick, Q., Baarmah, Z., Alqarni, A. A., Alosaimi, I., Almalki, H., Atik, S., Saqib, A., Alshutayri, Z., & Hassan, N. (2026). A Code-Free Visual Machine Learning Workflow for Automated Iron Deficiency Screening Using Routine Hematological Parameters. AI in Clinical Medicine, 2. https://doi.org/10.14740/aicm33

Vancouver

Sedick Q, Baarmah Z, Alqarni AA, Alosaimi I, Almalki H, Atik S, et al. A Code-Free Visual Machine Learning Workflow for Automated Iron Deficiency Screening Using Routine Hematological Parameters. AI in Clinical Medicine. 2026;2. doi:10.14740/aicm33

BibTeX
@article{Sedick2026,
  author = {Sedick, Qanita and Baarmah, Ziad and Alqarni, Abdul Aziz and Alosaimi, Ibtessam and Almalki, Hanni and Atik, Siham and Saqib, Ahmad and Alshutayri, Ziyad and Hassan, Nadir},
  title = {A Code-Free Visual Machine Learning Workflow for Automated Iron Deficiency Screening Using Routine Hematological Parameters},
  journal = {AI in Clinical Medicine},
  year = {2026},
  volume = {2},
  doi = {10.14740/aicm33}
}
Kostenlos starten →