Cardiac amyloidosis is a major cause of left ventricular hypertrophy, characterized by thickening of the left ventricular walls due to amyloid fibril deposition. Early diagnosis is crucial for optimizing patient management and reducing morbidity. This study proposes an approach based on automated echocardiographic image analysis for cardiac amyloidosis classification. A total of 21 subjects were included in this study. The A4-chamber view was selected from all cardiac chambers, and an automated pipeline was developed for field-of-view recognition. Machine and deep learning models were implemented to differentiate cardiac amyloidosis from healthy conditions using echocardiographic images. Preliminary results show high classification accuracy of 92% using Gradient Boosting, suggesting a potential improvement in differential diagnosis. This study highlights the growing role of artificial intelligence in cardiac imaging and paves the way for more efficient and precise diagnostic tools.