Cardiovascular diseases are the leading cause of death worldwide, and their diagnosis can be a complex process which involves several tests and medical procedures. The addition of artificial intelligence (AI) models aims to help clinicians to make informed decisions by comparing available models, identifying critical variables, and diagnosing heart diseases; further support can be given by the implementation of a user interface. Clinical data from 35,021 healthy and 34,979 affected adults including information on eleven variables, was used to train and test the AI models. Decision trees and random forests were the machine learning algorithms utilized and compared with convolutional and artificial neural networks as deep learning algorithms. The most relevant variables in the diagnosis of cardiovascular diseases, based on the analysis with the four models, were systolic and diastolic blood pressure, weight, and height. Furthermore, regarding the actual diagnosis, the random forest model showed great accuracy and potential as diagnostic tool in the medical field. The potential of AI models to enhance diagnostic accuracy and maximally utilize the capacity of clinical settings is highlighted, laying the foundation for future advances in AI-based diagnosis. Additionally, the implementation of a user interface performed in this study is intended to assist clinicians by making these AI models more accessible and easier to use in practical settings. This study also points out the importance of incorporating more specific and detailed health data to fully leverage the abilities of modern AI technologies.