D5.2 – Techniques for early risk identification, predictions and assessment II

This report summarizes the actions performed under T5.1 - “Techniques for early risk identification, predictions and assessment” in this phase of the project and more specifically provides details of the Artificial Intelligence (AI) / Machine Learning (ML) algorithms and implementation techniques that are being used to perform early identification as well as predictions of Pancreatic Cancer (PC) risks in individuals. The previous version of this series of deliverables, i.e., D5.1 - “Techniques for early risk identification, predictions and assessment I”, synthesized several AI/ML techniques that are expected to be able to identify hidden patterns and trends in given secondary clinical and streaming data. When all the data (mainly deriving from the patients e.g., questionnaires) become available in the last phase (3rd year) of the project, these techniques will be used for performing assessment of identified risks and subsequently for making predictions. In this second version of T5.1 - “Techniques for early risk identification, predictions and assessment” deliverables series, i.e., D5.2 - “Techniques for early risk identification, predictions and assessment II”, work has been carried out to further explore the synthetic data on Section 6 which simulate the real data that will be provided later in the project. Finally, in Section 7 the initial architecture and approach of the AI models is provided a) having as a guide the synthetic data that simulate the streaming data (life habit, symptoms questionnaires and data collected from wearable devices) and b) taking into account also the prospective clinical data.