Echocardiography plays a paramount role in day to day clinical practice to highlight structural or functional dysfunction of the heart. The observed abnormalities combined with clinical data of the patient lead to diagnoses, many of which requiring the performance of complementary examinations to diagnose the origin (etiology) of cardiac pathology which will modify the prognosis of patient and the subsequent therapy.

The objective of this project is to develop rigorous and explainable models for the prediction of the origin of targeted cardiac diseases from echocardiographic images and patient data based on artificial intelligence (AI) paradigm. The strength of this study lies in the development of a strong AI framework based on transformer paradigm to model the complex interactions between echocardiographic image-based information and relevant patient data.

Our solution will be developed on the basis of a unique dataset that will be implemented in the particular context of this study. It will include a total of 1500 patients from a multi-center (HCL and CHU of Caen) and multi-vendor (GE and Philips systems) study for which additional examinations were carried out in order to establish an etiological diagnosis.