LATE-AYA

The contribution of the Faculty of Engineering focuses on three main areas: ensuring data quality by developing robust methodologies to collect, clean, and validate diverse data streams; facilitating natural interaction with the digital tools developed through advanced natural language processing techniques, making them intuitive and user-friendly for cancer survivors; and creating machine learning models that predict the evolution of quality of life and late effects in adolescents and young adults who have overcome cancer. These predictive models leverage digital phenotyping data, integrating behavioral, physiological, and psychosocial indicators, thereby supporting personalized, preventive, and participatory healthcare interventions aligned with the project’s objectives.