FEEIT Bachelor Students Win Federated Learning Challenge on Hospital Readmission Prediction

Објавено: March 22, 2023

Borjan Sazdov, Stefan Krsteski, Matea Tashkovska and Borche Jovanovski students at the Faculty of Electrical Engineering and Information Technologies (FEEIT) at Ss. Cyril and Methodius University in Skopje together with Junoš Lukan researcher at the Jozef Stefan Institute, in Ljubljana, have won a machine learning challenge on hospital readmission prediction using federated learning. The challenge was part the 3rd WideHealth Winter School on Trustworthy AI organized in Potsdam, Germany at the Hasso Plattner Institute

Federated learning is a privacy-preserving machine learning technique that enables the training of models on decentralized data sources without the need to share the data itself. This approach enhances the security and privacy of sensitive data, making it an important tool for building trustworthy AI systems. Trustworthy AI is a rapidly growing field that focuses on the development of ethical, transparent, and robust AI systems that can be trusted by individuals, organizations, and society as a whole. The winter school on Trustworthy AI provided the team with an opportunity to learn about the latest advances in AI and federated learning and apply these techniques to the prediction of hospital readmission.

The competition focused on developing a model that could predict the likelihood of a patient being readmitted to the hospital within 30 days after being discharged. The team utilized federated learning techniques to ensure the privacy and security of the patient data. Their achievement demonstrates the potential of these technologies to improve healthcare outcomes while maintaining data privacy and security. Borjan, Stefan, Matea, Borche and Junoš  competed against participants from various European countries and emerged victorious, showcasing their dedication and hard work. Their accomplishment is a promising sign of the future of AI and federated learning in healthcare and a source of inspiration for other students and researchers.

The achievement of the FEEIT team is a testament to the quality of education and research at FEEIT and the dedication and hard work of the students. It also highlights the importance of interdisciplinary collaboration and international cooperation in advancing the field of AI and healthcare.

The school was sponsored and hosted by the EU Horizon 2020 project WideHealth, which aims to develop innovative solutions for personalized health and wellness using cutting-edge technologies such as AI, wearables, and IoT.