Comparative Analysis of Machine and Deep Learning Methods for Multi-Label Classification of Hematological Conditions Using Complete Blood Count Data

Öz

Hematological disorders are clinically common and frequently coexist within the same patient, yet most existing studies have adopted single-label classification frameworks that do not reflect this multi-morbid clinical reality. In this study, the performance of machine learning and deep learning algorithms was comparatively evaluated for the multi-label classification of 15 hematological conditions using complete blood count (CBC) parameters. Fifteen conditions were selected to encompass the most prevalent erythrocyte, leukocyte, and platelet line abnormalities encountered in routine practice, thereby reflecting the heterogeneous diagnostic landscape clinicians face when interpreting hemogram results. A retrospective dataset comprising CBC records of 88,798 patients, collected between 2022 and 2024 from Kars Harakani State Hospital and labeled by specialist physicians, was used. Six models—Random Forest, Logistic Regression, Linear SVM, Deep MLP, 1D-CNN, and Wide & Deep Network—were evaluated across 21 hemogram parameters. The dataset was partitioned into 80% training and 20% testing subsets, and class weighting strategies were applied to address class imbalance. Random Forest achieved the highest overall performance (F1-Micro: 0.9945, ROC-AUC: 0.9999, Subset Accuracy: 98.80%), followed by deep learning architectures. These results demonstrate that Random Forest is highly effective for multi-label hematological classification and holds considerable promise for integration into clinical decision support systems. With its large-scale dataset and comprehensive multi-label classification framework, this study represents one of the most extensive investigations of automated hematological disease diagnosis to date.

Anahtar Kelimeler

• Complete blood count
• Multi-label classification
• Machine learning
• Deep learning
• Random Forest
• Hematological disorders

Destekleyen Kurum

Atatürk University Scientific Research Projects Commission

Proje Numarası

SDK-2024-14892.

Etik Beyan

The authors confirm that the ethical policies of the journal, as noted on the journal's author guidelines page, have been adhered to. Ethical approval for this study was granted by the Kars Provincial Health Directorate on January 7, 2025, under decision number E-74033640-799-264723817.

Teşekkür

This study was supported by Atatürk University Scientific Research Projects Commission (BAP) under project number SDK-2024-14892.

Kaynakça

1. Akter, F., Hossin, M. A., Daiyan, G. M., & Hossain, M. M. (2018). Classification of hematological data using data mining technique to predict diseases. Journal of Computer and Communications, 6(4), 76–83. https://doi.org/10.4236/jcc.2018.64007
2. Bahyat, K., Ammour, A., Cheddadi, M., Fedorova, V., & Houari, M. (2025). The role of artificial intelligence in the hematology department. Scholars Journal of Medical Case Reports, 13(9), 1972–1975. https://doi.org/10.36347/sjmcr.2025.v13i09.005
3. Bain, B. J., Bates, I., & Laffan, M. A. (2017). Dacie and Lewis practical haematology (12th ed.). Elsevier.
4. Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32. https://doi.org/10.1023/A:1010933404324
5. Cheng, H. T., Koc, L., Harmsen, J., Shaked, T., Chandra, T., Aradhye, H., Anil, R., Pfister, T., Ispir, M., Haque, E., & Shah, H. (2016). Wide & deep learning for recommender systems. Proceedings of the 1st Workshop on Deep Learning for Recommender Systems, 7–10. https://doi.org/10.1145/2988450.2988454
6. Cortes, C., & Vapnik, V. (1995). Support-vector networks. Machine Learning, 20(3), 273–297. https://doi.org/10.1007/BF00994018
7. Cox, D. R. (1958). The regression analysis of binary sequences. Journal of the Royal Statistical Society: Series B (Methodological), 20(2), 215–232. https://doi.org/10.1111/j.2517-6161.1958.tb00292.x
8. Demirci, F., Akan, P., Kume, T., Sisman, A. R., Erbayraktar, Z., & Sevinc, S. (2016). Artificial neural network approach in laboratory test reporting: Learning algorithms. American Journal of Clinical Pathology, 146(2), 227–237. https://doi.org/10.1093/ajcp/aqw104

9. Efron, B., & Tibshirani, R. J. (1993). An introduction to the bootstrap. Chapman & Hall/CRC.
10. El Alaoui, Y., Elomri, A., Qaraqe, M., Padmanabhan, R., Yasin Taha, R., El Omri, H., El Omri, A., & Aboumarzouk, O. (2022). A review of artificial intelligence applications in hematology management: Current practices and future prospects. Journal of Medical Internet Research, 24(7), Article e36490. https://doi.org/10.2196/36490
11. Grinsztajn, L., Oyallon, E., & Varoquaux, G. (2022). Why do tree-based models still outperform deep learning on typical tabular data? Advances in Neural Information Processing Systems, 35, 507–520.
12. Gunčar, G., Kukar, M., Notar, M., Brvar, M., Černelč, P., Notar, M., & Notar, M. (2018). An application of machine learning to haematological diagnosis. Scientific Reports, 8(1), Article 411. https://doi.org/10.1038/s41598-017-18564-8
13. Haider, R. Z., Ujjan, I. U., Khan, N. A., Urrechaga, E., & Shamsi, T. S. (2022). Beyond the in-practice CBC: The research CBC parameters-driven machine learning predictive modeling for early differentiation among leukemias. Diagnostics, 12(1), Article 138. https://doi.org/10.3390/diagnostics12010138
14. Hoffbrand, A. V., & Steensma, D. P. (2020). Hoffbrand's essential haematology (8th ed.). Wiley-Blackwell.
15. Jackups, R. (2017). Clinical decision support for hematology laboratory test utilization. International Journal of Laboratory Hematology, 39(S1), 80–84. https://doi.org/10.1111/ijlh.12679
16. Kaya, Z. (2013). Tam kan sayım çıktılarının yorumlanması [Interpretation of complete blood count outputs]. Dicle Tıp Dergisi, 40(3), 521–525. https://doi.org/10.5798/diclemedj.0921.2013.03.0326
17. Liu, J., Gou, Y., Yang, W., Wang, H., Zhang, J., Wu, S., Li, Y., Gao, Y., & Zhang, X. (2025). Development and application of machine learning models for hematological disease diagnosis using routine laboratory parameters: A user-friendly diagnostic platform. Frontiers in Medicine, 12, Article 1605868. https://doi.org/10.3389/fmed.2025.1605868
18. Luo, Y., Szolovits, P., Dighe, A. S., & Baron, J. M. (2016). Using machine learning to predict laboratory test results. American Journal of Clinical Pathology, 145(6), 778–788. https://doi.org/10.1093/ajcp/aqw064
19. Mentzer, W. C. (1973). Differentiation of iron deficiency from thalassaemia trait. The Lancet, 301(7808), 882. https://doi.org/10.1016/S0140-6736(73)91446-3
20. Padmanabhan, R., Meskin, N., Khattab, T., Shraim, M., & Al-Hitmi, M. (2023). Detecting chronic lymphocytic leukemia by analyzing hematology laboratory test results using machine learning. BMC Medical Informatics and Decision Making, 23(1), Article 13. https://doi.org/10.1186/s12911-022-02096-3
21. Park, D. J., Park, M. W., Lee, H., Kim, Y. J., Kim, Y., & Park, Y. H. (2021). Development of machine learning model for diagnostic disease prediction based on laboratory tests. Scientific Reports, 11(1), Article 7567. https://doi.org/10.1038/s41598-021-87171-5
22. Pereira, F., Bueno, A., Rodriguez, A., Perpinan, D., & Mello, R. (2024). Evaluation metrics and statistical tests for machine learning. Scientific Reports, 14, Article 6086. https://doi.org/10.1038/s41598-024-56706-x
23. Rajkomar, A., Dean, J., & Kohane, I. (2019). Machine learning in medicine. New England Journal of Medicine, 380(14), 1347–1358. https://doi.org/10.1056/NEJMra1814259
24. Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1986). Learning representations by back-propagating errors. Nature, 323(6088), 533–536. https://doi.org/10.1038/323533a0
25. Santos-Silva, M. A., Sousa, N., & Sousa, J. C. (2024). Artificial intelligence in routine blood tests. Frontiers in Medical Engineering, 2, Article 1369265. https://doi.org/10.3389/fmede.2024.1369265
26. Schapire, R. E., & Singer, Y. (2000). BoosTexter: A boosting-based system for text categorization. Machine Learning, 39(2–3), 135–168. https://doi.org/10.1023/A:1007649029923
27. Schipper, A., Rutten, M., van Gammeren, A., Harteveld, C. L., Urrechaga, E., Weerkamp, F., van Wijnen, M., & Kurstjens, S. (2024). Machine learning-based prediction of hemoglobinopathies using complete blood count data. Clinical Chemistry, 70(8), 1064–1075. https://doi.org/10.1093/clinchem/hvae081
28. Sun, D., Chen, W., He, J., He, Y., Jiang, H., Jiang, H., Li, Z., & He, J. (2025). A novel method for screening malignant hematological diseases by constructing an optimal machine learning model based on blood cell parameters. BMC Medical Informatics and Decision Making, 25(1), Article 72. https://doi.org/10.1186/s12911-025-02892-1
29. Tartan, A. N., Ertuğrul, Ö. F., & Taşdemir, Ş. (2020). Yapay sinir ağları kullanılarak anemi tanısında klinik karar destek sistemi geliştirilmesi [Development of a clinical decision support system for anemia diagnosis using artificial neural networks]. Fırat Üniversitesi Sağlık Bilimleri Tıp Dergisi, 34(2), 135–140.
30. Tsoumakas, G., Katakis, I., & Vlahavas, I. (2010). Mining multi-label data. In O. Maimon & L. Rokach (Eds.), Data mining and knowledge discovery handbook (pp. 667–685). Springer. https://doi.org/10.1007/978-0-387-09823-4_34
31. Walter, W., Pohlkamp, C., Meggendorfer, M., Nadarajah, N., Kern, W., Haferlach, C., & Haferlach, T. (2023). Artificial intelligence in hematological diagnostics: Game changer or gadget? Blood Reviews, 58, Article 101019. https://doi.org/10.1016/j.blre.2022.101019
32. WHO. (2011). World Health Organization. Haemoglobin concentrations for the diagnosis of anaemia and assessment of severity (Report No. WHO/NMH/NHD/MNM/11.1). Vitamin and Mineral Nutrition Information System.
33. Zhang, M. L., & Zhou, Z. H. (2014). A review on multi-label learning algorithms. IEEE Transactions on Knowledge and Data Engineering, 26(8), 1819–1837. https://doi.org/10.1109/TKDE.2013.39