The aim – to enhance the efficiency of infective endocarditis (IE) diagnosis and assess embolism risks by employing an intelligent computer-based diagnostic system. Materials and methods. The study utilized intelligent computer processing of echocardiographic images from 20 patients (15 in the training group and 5 in the reference group) diagnosed with IE. The dataset comprised 668 images with pathologies (vegetations and abscesses) and 632 «clean» frames without pathological changes, in total 1,300 images in parasternal and apical views. The images were extracted from echocardiograms in DICOM format. Preprocessing steps included cropping, normalization, and contrast enhancement. To ensure the model’s quality, training, validation, and test sets contained images from different patients.Results. The developed AI-based automated diagnostic system effectively identified vegetations on heart structures and determined their volume almost instantly, eliminating the potential for human error. This approach improves the accuracy, reliability, and speed of embolism risk assessment, enabling the optimization of the IE diagnostic protocol. The developed system was tested on images of a reference group of 5 patients with various IE progression states and in different projections. The system correctly predicted the presence of vegetation in each of the images where it was present, and reliably calculated its volume.Conclusions. The proposed AI-based system significantly enhances the individualization and impartiality of the IE diagnostic process, improving its quality and reducing its duration. This provides the potential to enhance the protocol for IE examination and diagnosis.