Anemia Classification Using Hybrid Machine Learning Models: A Comparative Study of Ensemble Techniques on CBC Data

Gregorius Airlangga

doi:10.47065/josyc.v5i4.5848

Gregorius Airlangga * Atma Jaya Catholic University of Indonesia, Jakarta, Indonesia

(*) Corresponding Author

DOI: https://doi.org/10.47065/josyc.v5i4.5848

Keywords: Anemia Classification; Hybrid Machine Learning; Ensemble Techniques; CBC Data; Medical Diagnostics

Abstract

Anemia is a prevalent and potentially serious medical condition characterized by a deficiency in the number or quality of red blood cells. Accurate classification of anemia types is crucial for ensuring appropriate treatment, as different types of anemia require distinct therapeutic approaches. However, the classification of anemia presents specific challenges due to the complexity of the condition, the variability in CBC data, and the need to differentiate between multiple anemia types that may present with overlapping symptoms. In this study, we explore the application of hybrid machine learning models to classify anemia types using Complete Blood Count (CBC) data. We evaluated the performance of various models, including DecisionTree, RandomForest, XGBoost, LightGBM, CatBoost, and ensemble methods such as Stacking and Voting. The ensemble models, particularly Stacking and Voting, demonstrated superior performance with balanced accuracy reaching 0.9976 and F1 scores of 0.9964, significantly outperforming individual classifiers. These results underscore the efficacy of ensemble techniques in handling the complex and imbalanced datasets commonly encountered in medical diagnostics. Despite their high accuracy, we identified challenges related to model interpretability, computational demands, and data quality. The complexity and resource requirements of these models may limit their practical application in resource-constrained environments. This study provides a comprehensive analysis of the trade-offs between model complexity, accuracy, and interpretability, offering valuable insights for the deployment of machine learning models in clinical settings. Our findings highlight the potential of hybrid models to improve anemia diagnosis, suggesting their integration into healthcare systems could enhance diagnostic accuracy and patient outcomes. Future work will focus on expanding the dataset, refining model interpretability, and addressing ethical considerations in the use of AI in healthcare.

Downloads

Download data is not yet available.

References

B. W. Downs et al., “Anemia: influence of dietary fat, sugar, and salt on hemoglobin and blood health,” Diet. Sugar, Salt Fat Hum. Heal., pp. 103–127, 2020. https://doi.org/10.1016/B978-0-12-816918-6.00005-6

D. Kinyoki, A. E. Osgood-Zimmerman, N. V Bhattacharjee, N. J. Kassebaum, and S. I. Hay, “Anemia prevalence in women of reproductive age in low-and middle-income countries between 2000 and 2018,” Nat. Med., vol. 27, no. 10, pp. 1761–1782, 2021. https://doi.org/10.1038/s41591-021-01498-0

K. Velliyagounder, K. Chavan, and K. Markowitz, “Iron Deficiency Anemia and Its Impact on Oral Health—A Literature Review,” Dent. J., vol. 12, no. 6, p. 176, 2024.

A. G. Godswill, I. V. Somtochukwu, A. O. Ikechukwu, and E. C. Kate, “Health benefits of micronutrients (vitamins and minerals) and their associated deficiency diseases: A systematic review,” Int. J. Food Sci., vol. 3, no. 1, pp. 1–32, 2020. https://doi.org/10.47604/ijf.1024

S. Quazi, “Artificial intelligence and machine learning in precision and genomic medicine,” Med. Oncol., vol. 39, no. 8, p. 120, 2022. https://doi.org/10.20944/preprints202110.0011.v1

K. Sherin, A. P. A. Victoria, S. Harini, and J. C. Jensen, “Automated Diagnosis of Anemia Signs using Machine Learning,” in 2024 11th International Conference on Reliability, Infocom Technologies and Optimization (Trends and Future Directions)(ICRITO), 2024, pp. 1–6. https://doi.org/10.1109/ICRITO61523.2024.10522270

S. Zhang and J. Song, “A chatbot based question and answer system for the auxiliary diagnosis of chronic diseases based on large language model,” Sci. Rep., vol. 14, no. 1, p. 17118, 2024. https://doi.org/10.1038/s41598-024-67429-4

A. A. Abdullah, M. M. Hassan, and Y. T. Mustafa, “A review on bayesian deep learning in healthcare: Applications and challenges,” IEEE Access, vol. 10, pp. 36538–36562, 2022. https://doi.org/10.1109/ACCESS.2022.3163384

B. Omarov, M. Baikuvekov, Z. Momynkulov, A. Kassenkhan, S. Nuralykyzy, and M. Iglikova, “Convolutional LSTM Network for Heart Disease Diagnosis on Electrocardiograms.,” Comput. Mater. & Contin., vol. 76, no. 3, 2023.

M. Saleem, W. Aslam, M. I. U. Lali, H. T. Rauf, and E. A. Nasr, “Predicting Thalassemia Using Feature Selection Techniques: A Comparative Analysis,” Diagnostics, vol. 13, no. 22, p. 3441, 2023. https://doi.org/10.3390/diagnostics13223441

J. Brooks, “Statistical Tools for Efficient Confirmation of Diagnosis in Patients with Suspected Primary Central Nervous System Vasculitis,” Université d’Ottawa/University of Ottawa, 2023.

R. Shouval, J. A. Fein, B. Savani, M. Mohty, and A. Nagler, “Machine learning and artificial intelligence in haematology,” Br. J. Haematol., vol. 192, no. 2, pp. 239–250, 2021. https://doi.org/10.1111/bjh.16915

V. Mattiello, M. Schmugge, H. Hengartner, N. von der Weid, R. Renella, and S. P. H. W. Group, “Diagnosis and management of iron deficiency in children with or without anemia: consensus recommendations of the SPOG Pediatric Hematology Working Group,” Eur. J. Pediatr., vol. 179, pp. 527–545, 2020. https://doi.org/10.1007/s00431-020-03597-5

S. Sundararajan and H. Rabe, “Prevention of iron deficiency anemia in infants and toddlers,” Pediatr. Res., vol. 89, no. 1, pp. 63–73, 2021. https://doi.org/10.1038/s41390-020-0907-5

S. Mahmud, T. B. Donmez, M. Mansour, M. Kutlu, and C. Freeman, “Anemia detection through non-invasive analysis of lip mucosa images,” Front. big Data, vol. 6, p. 1241899, 2023. https://doi.org/10.3389/fdata.2023.1241899

K. C. Sahoo, A. Sinha, R. K. Sahoo, S. S. Suman, D. Bhattacharya, and S. Pati, “Diagnostic validation and feasibility of a non-invasive haemoglobin screening device (EzeCheck) for’Anaemia Mukt Bharat’in India,” Cureus, vol. 16, no. 1, 2024. https://doi.org/10.7759/cureus.52877

S. Bodapati, H. Bandarupally, R. N. Shaw, and A. Ghosh, “Comparison and analysis of RNN-LSTMs and CNNs for social reviews classification,” Adv. Appl. Data-Driven Comput., pp. 49–59, 2021. https://doi.org/10.1007/978-981-33-6919-1_4

N. Rane, S. Choudhary, and J. Rane, “Ensemble Deep Learning and Machine Learning: Applications, Opportunities, Challenges, and Future Directions,” Oppor. Challenges, Futur. Dir. (May 31, 2024), 2024.

J. A. Esterhuizen, B. R. Goldsmith, and S. Linic, “Interpretable machine learning for knowledge generation in heterogeneous catalysis,” Nat. Catal., vol. 5, no. 3, pp. 175–184, 2022. https://doi.org/10.1038/s41929-022-00744-z

E. Shehab, A. Khawaga, and others, “Anemia Diagnosis And Prediction Based On Machine Learning,” Kafrelsheikh J. Inf. Sci., vol. 4, no. 2, pp. 1–9, 2023. https://doi.org/10.1007/978-981-99-0071-8_18

S. Akter et al., “AD-CovNet: An exploratory analysis using a hybrid deep learning model to handle data imbalance, predict fatality, and risk factors in Alzheimer’s patients with COVID-19,” Comput. Biol. Med., vol. 146, p. 105657, 2022. https://doi.org/10.1016/j.compbiomed.2022.105657

E. Aboelnaga, “Anemia Types Classification.” 2023. https://www.kaggle.com/datasets/ehababoelnaga/anemia-types-classification

A. Abrol et al., “Deep learning encodes robust discriminative neuroimaging representations to outperform standard machine learning,” Nat. Commun., vol. 12, no. 1, p. 353, 2021. https://doi.org/10.1038/s41467-020-20655-6

A. Carè, “Gender imbalance in medical imaging datasets for Artificial Intelligence,” IGMCONGRESS 2022, p. 30, 2022. https://doi.org/10.1073/pnas.1919012117

Bila bermanfaat silahkan share artikel ini

Berikan Komentar Anda terhadap artikel Anemia Classification Using Hybrid Machine Learning Models: A Comparative Study of Ensemble Techniques on CBC Data