My postdoctoral research in e-health systems for gastric cancer diagnosis directly supports SDG 3: Good Health and Well-being, aiming to reduce healthcare costs through improved early detection and better patient outcomes, My Bachelor's research in autonomous robotics aligns with SDG 9: Industry, Innovation, and Infrastructure, focusing on automation and robotics to drive innovation in U.S. industries and manufacturing.

Dr. Danish Jamil is an Assistant Professor of Software Engineering at Sir Syed University of Engineering and Technology, Karachi. He specializes in machine learning, AI applications in healthcare, cybersecurity, and robotics. His postdoctoral research at the University of Santiago de Compostela focuses on AI-driven e-health systems for early gastric cancer diagnosis. He has over 15 peer-reviewed publications and has developed an AI-powered gastric cancer care app successfully implemented at NHS Liverpool. Dr. Jamil is actively involved in SDG-aligned research, particularly SDG 3, 9, and 16, and contributes as an editor and reviewer in several international journals. Reference: Federated Learning for Personalized Gastric Cancer Treatment: A systematic review of literature Optimizing the performance and scalability of federated learning (FL) models for gastric cancer diagnosis is crucial to handle large-scale, distributed data efficiently while minimizing communication and computational costs. Various methods can enhance the scalability and performance of FL models in diagnosing gastric cancer from distributed hospital data, including model compression techniques, adaptive communication strategies, and efficient learning algorithms. Additionally, addressing the variability in medical imaging and data annotations across institutions is essential to ensure consistent FL model performance. Techniques such as domain adaptation, standardized annotation protocols, and robust data harmonization can mitigate these variations, leading to more reliable and accurate diagnostic models. By leveraging these approaches, FL can enable collaborative learning across multiple healthcare institutions without compromising patient privacy, improving diagnostic accuracy, and facilitating early detection of gastric cancer. This research aims to develop robust FL frameworks that not only optimize computational resources but also ensure high-quality, standardized diagnostic outcomes across diverse clinical settings.