EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Prediction of β-thalassemia carrier using federated learning and explainable AI

Hafiz Ali Younas, Bilal Shoaib Khan, Abdul Hannan Khan, Anas Bilal, Asaad Algarni, Raheem Sarwar, Seyed Jalaleddin Mousavirad

Frontiers in Medicine · 30.01.2026 · 13

DOI: 10.3389/fmed.2026.1687773 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Medicine, online erschienen am 30.01.2026. Verfasst von Hafiz Ali Younas und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Science, Green International University, Lahore, Pakistan. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 65 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Millions of people worldwide suffer from β -thalassemia, an inherited blood disorder that requires precise carrier screening to avoid serious health issues. Conventional centralized screening techniques rely on combining patient data, which raises privacy and legal issues under regulations like General Data Protection Regulation (GDPR) and the Health Insurance Portability and Accountability Act (HIPAA). Although machine learning has increased the accuracy of diagnoses, its reliance on shared data raises issues with data security and makes it more difficult to develop collaborative models. Federated learning provides a solution by allowing multi-center collaboration and protecting privacy by training models locally at each clinical site and sharing only model parameters. In this work, a federated multi-kernel support vector machine (SVM) framework is developed, which aggregates updates through federated averaging and deploys linear, polynomial, radial basis function, and Deep kernel (DK) on client devices. We also incorporate explainable AI methods SHapley Additive exPlanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME) to decipher forecasts and pinpoint important hematological characteristics. Our federated model performs on par with centralized methods, achieving 98.4% accuracy, 99.2% sensitivity, and 98.8% specificity when tested on 5,066 complete blood count records. The most significant predictors, according to the explainability analyses, are hemoglobin level and mean corpuscular volume. Our results open the door for scalable, transparent, and compliant β -thalassemia screening across dispersed healthcare systems by demonstrating that federated multi-kernel SVMs with Explainable Artificial Intelligence (XAI) can provide high diagnostic performance while protecting patient privacy.

Schlagwörter

Stichwörter der Autor:innen

LIMESVMexplainable AIfederated learningβ-thalassemia carrier

Autor:innen und Institutionen

  • Department of Computer Science, Green International University, Lahore, Pakistan.
  • Department of Computer Science and IT, The University of Lahore, Lahore, Punjab, Pakistan.
  • College of Information Science and Technology, Hainan Normal University, Haikou, China.
  • Department of Computer Science, Faculty of Computing and Information Technology, King Abdulaziz University, Rabigh, Saudi Arabia.
  • OTEHM, Manchester Metropolitan University, Manchester, United Kingdom.
  • Department of Computer and Electrical Engineering, MidSweden University, Sundsvall, Sweden.

Zitieren

APA

Younas, H. A., Shoaib Khan, B., Khan, A. H., Bilal, A., Algarni, A., Sarwar, R., & Mousavirad, S. J. (2026). Prediction of β-thalassemia carrier using federated learning and explainable AI. Frontiers in Medicine, 13. https://doi.org/10.3389/fmed.2026.1687773

Vancouver

Younas HA, Shoaib Khan B, Khan AH, Bilal A, Algarni A, Sarwar R, et al. Prediction of β-thalassemia carrier using federated learning and explainable AI. Frontiers in Medicine. 2026;13. doi:10.3389/fmed.2026.1687773

BibTeX
@article{Younas2026,
  author = {Younas, Hafiz Ali and Shoaib Khan, Bilal and Khan, Abdul Hannan and Bilal, Anas and Algarni, Asaad and Sarwar, Raheem and Mousavirad, Seyed Jalaleddin},
  title = {Prediction of β-thalassemia carrier using federated learning and explainable AI},
  journal = {Frontiers in Medicine},
  year = {2026},
  volume = {13},
  doi = {10.3389/fmed.2026.1687773}
}
Kostenlos starten →