Work

Federated Learning for Early Medical Diagnosis: Enhanced Diabetic Retinopathy Detection in Smart Healthcare

Year: 2026
Type: article
Abstract: This thesis investigates the role of federated learning as a privacy-preserving solution for modern healthcare challenges. In traditional machine learning, sensitive medical data must be centralized for model training, raising concerns about privacy, security, and regulatory compliance. Federated learning offers an alternative by allowing hospitals, clinics, and personal health devices to collaboratively train shared models without exchanging raw patient data. The study first explores how federated learning is being used across various healthcare domains, including cancer detection, medical imaging, and disease prediction— highlighting its potential to support secure collaboration across institutions. It addresses key benefits such as data privacy, scalability, and adaptability to real-world clinical environments, as well as common challenges like data imbalance, communication overhead, and model fairness. As a case study, the thesis applies federated learning techniques to the detection of diabetic retinopathy, a leading cause of blindness. By training models across multiple data sources without transferring patient images, the approach demonstrates how accurate diagnosis can be achieved while respecting data privacy. Overall, this work emphasizes the promise of federated learning in building intelligent, ethical, and collaborative healthcare systems for the future.
Language: English
Open Access status: green
OpenAlex ID: W7200936426
FWCI:
Cites: 153
Cited by:
Related to: 10