RAME Logo

RAME PUBLISHERS

A better space for Quality Research
International Journal of Computational and Electronics Aspects in Engineering (IJCEAE)
Volume 7 · Issue 4 · September 2026 · pp. 389–398
Research Article · Peer Reviewed
Received: July 10, 2026 · Accepted: August 31, 2026 · Published: September 14, 2026
DOI: 10.26706/ijceae.7.4.20260807
Open Access · CC BY 4.0

A Secure AI-Based Thalassemia Diagnosis Framework

Razan Abdulhammed*
Artificial Research Center, Northern Technical University, Mosul, Nineveh Governorate, 41000, Iraq.
*Corresponding author: rabdulhammed@ntu.edu.iq
Download PDF Cite this article Certificate Volume 7 Issue 4

Abstract

Thalassemia is an illness that affects about ten million human beings worldwide, most notably in poorer nations. To improve the results of patients suffering from the illness, prompt diagnosis of thalassemia is of utmost importance. Unfortunately, many traditional diagnostic techniques suffer from delays in screening, lack of specialists, and ethical issues related to data protection. Artificial intelligence can help to devise reliable methods for diagnosis of thalassemia in adults and children.

The present study proposes an accurate and efficient diagnostic model based on artificial intelligence for the diagnosis of thalassemia using machine learning and deep learning techniques. AES-256-GCM method is used to secure sensitive medical information, thus ensuring its confidentiality and integrity throughout storage and transfer processes. The proposed framework integrates data acquisition, preprocessing, and diagnostic decision support. Naive Bayes, Tabular Transformer, Random Forest, and RNN models are trained and evaluated using the PTPP dataset. Model performance is assessed using accuracy, precision, recall, and F1-score. The Random Forest outperforms other classifiers with an Accuracy of 99.7%. The proposed secure AI diagnostic framework has the potential to support healthcare professionals by enabling earlier, more consistent, and data-driven screening for Thalassemia. By combining intelligent diagnosis with encryption-based data protection, the framework may contribute to secure, scalable, and privacy-aware medical screening technologies.

Keywords

Thalassemia Artificial Intelligence Machine Learning Deep Learning AES-256-GCM Random Forest Medical Screening Data Security

References

  1. Centers for Disease Control and Prevention, "About thalassemia," U.S. Department of Health & Human Services, May 2024. https://www.cdc.gov/thalassemia/about/index.html (accessed May 28, 2026).
  2. R. Thomson and C. Lebiere, "Cognitive models of influence dynamics in a conformity simulation," Comput. Math. Organ. Theory, vol. 31, no. 4, pp. 323–343, 2025.
  3. E. Foord, D. Sairafi, M. Berg, S. Westerling, T. Adigun, M. Uzunel, T. Papasavva, and M. Uhlin, "Decoding thalassemia and sickle cell disease: Advances in molecular technologies for comprehensive variant detection," Front. Genet., vol. 17, Art. no. 1810737, 2026.
  4. Thalassaemia International Federation, "Global thalassaemia review," 2026. https://thalassaemia.org.cy/what-we-do/global-thalassaemia-review/ (accessed May 28, 2026).
  5. Centers for Disease Control and Prevention, "Thalassemia," U.S. Department of Health & Human Services, 2024. https://www.cdc.gov/thalassemia/index.html (accessed May 28, 2026).
  6. S. Sadiq et al., "Classification of -thalassemia carriers from red blood cell indices using ensemble classifier," IEEE Access, vol. 9, pp. 45528–45538, 2021.
  7. M. U. Nasir, M. Zubair, M. T. Naseem, T. Shahzad, A. Saeed, K. M. Adnan, and A. H. Gandomi, "Multiclass classification of thalassemia types using complete blood count and HPLC data with machine learning," Sci. Rep., vol. 15, no. 1, Art. no. 26379, 2025, doi: 10.1038/s41598-025-06594-6.
  8. F. Rustam, I. Ashraf, and S. Jabbar et al., "Prediction of -thalassemia carriers using complete blood count features," Sci. Rep., vol. 12, no. 1, Art. no. 19999, 2022, doi: 10.1038/s41598-022-22011-8.
  9. M. U. Nasir, M. T. Naseem, T. M. Ghazal, M. Zubair, O. Ali, S. Abbas, M. Ahmad, and K. M. Adnan, "A comprehensive case study of deep learning on the detection of alpha thalassemia and beta thalassemia using public and private datasets," Sci. Rep., vol. 15, no. 1, Art. no. 13359, 2025, doi: 10.1038/s41598-025-97353-0.
  10. H. A. Younas, B. Shoaib Khan, A. H. Khan, A. Bilal, A. Algarni, R. Sarwar, and S. J. Mousavirad, "Prediction of thalassemia carrier using federated learning and explainable AI," Front. Med., vol. 13, Art. no. 1687773, 2026.
  11. F. Christensen, D. K. Kılıç, I. E. Nielsen, T. C. El-Galaly, A. Glenthøj, J. Helby, H. Frederiksen, S. Møller, and A. D. Fuglkjær, "Classification of -thalassemia data using machine learning models," Comput. Methods Programs Biomed., vol. 260, Art. no. 108581, 2025.
  12. S. S. Ayon, M. E. Hossain, M. S. U. Miah, B. M. Arafin, A. Chowdhury, and N. N. I. Prova, "Thalassemia dataset covering clinical, socioeconomic, and mental health aspects," Data Brief, Art. no. 112082, 2025.
  13. S. S. Abdul-Jabbar and A. Farhan, "Thalassemia dataset," Mendeley Data, 2022, doi: 10.17632/p8rv84hrbs.1.
  14. National Institute of Standards and Technology, Advanced Encryption Standard (AES), Federal Information Processing Standards Publication (FIPS) 197-upd1, U.S. Dept. Commerce, Washington, DC, USA, 2023, doi: 10.6028/NIST.FIPS.197-upd1.
  15. Health Informatics—Requirements for an Electronic Health Record Architecture, ISO Standard 18308:2011, International Organization for Standardization, Geneva, Switzerland, 2011.
  16. M. Maharana, S. Mondal, and R. Nemade, "Analyzing the effect of data preprocessing techniques on machine learning-based prediction model outcome," Health Sci. Rep., vol. 6, no. 2, Art. no. e1103, 2023, doi: 10.1002/hsr2.1103.
  17. T. M. Mitchell, "Naive Bayes and logistic regression," in Machine Learning, 2nd ed. (draft chapter), Carnegie Mellon Univ., Pittsburgh, PA, USA.
  18. K. P. Murphy, Machine Learning: A Probabilistic Perspective. Cambridge, MA, USA: MIT Press, 2012.
  19. L. Breiman, "Random forests," Mach. Learn., vol. 45, no. 1, pp. 5–32, 2001, doi: 10.1023/A:1010933404324.
  20. X. Huang, A. Khetan, M. Cvitkovic, and Z. Karnin, "TabTransformer: Tabular data modeling using contextual embeddings," 2020, arXiv:2012.06678, doi: 10.48550/arXiv.2012.06678.
  21. X. Huang, A. Khetan, M. Cvitkovic, and Z. Karnin, "TabTransformer: Tabular data modeling using contextual embeddings," 2020, arXiv:2012.06678, doi: 10.48550/arXiv.2012.06678.
  22. D. M. W. Powers, "Evaluation: From precision, recall and F-measure to ROC, informedness, markedness and correlation," J. Mach. Learn. Technol., vol. 2, no. 1, pp. 37–63, 2011.
  23. L. A. Jeni, J. F. Cohn, and F. De La Torre, "Facing imbalanced data—Recommendations for the use of performance metrics," in Proc. 2013 Humaine Assoc. Conf. Affect. Comput. Intell. Interact., 2013, pp. 245–251, doi: 10.1109/ACII.2013.47.
  24. S. K. Ghanim, "Hybrid ResNet50 and DenseNet121 with adaptive weighted feature fusion in infectious chest diseases classification," Int. J. Comput. Electron. Aspects Eng., vol. 7, no. 2, pp. 211–226, 2026, doi: 10.26706/ijceae.7.2.20260310.
  25. M. H. G. Abdkhaleq, "Hybrid deep learning and neuro-fuzzy approach for COVID-19 diagnosis using CT scan imaging (CNN + ANFIS + PCA)," Int. J. Comput. Electron. Aspects Eng., vol. 6, no. 2, pp. 81–88, 2025, doi: 10.26706/ijceae.6.2.20250404.