As part of the AI4EU project, the MED-AI solution is an early prototype with the potential for significant expansion into a comprehensive platform and Clinical Decision Support System (CDSS) aligned with the E-AI Challenge of Centre Hospitalier Universitaire de Liège (CHUL) and user needs.
With project funding, the MED-AI prototype—a CDSS with limited functionality—was developed, tested, and validated (supported by AI4EU and CHUL) to achieve TRL7 in an operational environment. The project aimed to deliver an AI- and data-driven solution to support CHUL’s transition toward personalized medicine.
The primary objective is to develop a web-based software platform for the early detection and diagnosis of COVID-19 and pneumonia. Designed with adaptive principles, the platform is accessible from both PCs and mobile devices. It processes Computed Tomography (CT) and X-ray images using deep convolutional neural networks. Two approaches were explored: training a custom neural network and leveraging transfer learning.