Exercise substantially impacts the cardiovascular system and is associated with many potential benefits across different momentums of the cardiovascular continuum. ^, On the other hand, physical exercise has for several decades been postulated as a possible approach to assess the cardiovascular response. As such, this methodology could be of interest for diagnostic purposes while also providing prognostic information. While the maturation of protocols encompassing the electrocardiographic response to exercise provided major breakthroughs, novel techniques have allowed an expanded view of the complex interplay between exercise and the cardiovascular system. ^–

Exercise stress echocardiography (ESE) has progressively evolved into a highly relevant framework, namely when assessing coronary artery disease (CAD). Echocardiography also has the advantage of assessing components such as exercise capacity, diastolic function, dynamic gradients, and valvular heart disease. ^, Furthermore, blood pressure (BP) and electrocardiographic monitoring also provide pivotal inputs . Recent data also showcases the potential of combining with other techniques, such as lung ultrasound, to assess congestion. While, as illustrated in contemporary guidelines, ESE has garnered great interest (being preferred to pharmacological testing in patients able to exercise), there are still some caveats in its optimal application. ^,

[…]

Since its introduction by Edler and Hertz, echocardiography has become the main test of cardiologic propedeutic. Over the last 50 years, its evolution has been remarkable, from A-mode, M-mode, two-dimensional and Doppler images to modern three-dimensional reconstructions and softwares for studying myocardial deformation currently used. For this reason, echocardiography can provide diagnostic data and important prognostic information in virtually all heart diseases.

One of the major advances in echocardiography was the recognition of substances capable of increasing the ultrasound signal for better visualization of cardiac structures, popularly known as “echocardiographic contrasts.” Its beginning dates back to the late 1960s, with the first experience reported on the use of agitated saline solution associated with cardiac ultrasound. This technique (agitation of a saline solution so that it is aerated, allowing an increase in sound reflection) is still used to detect intracardiac communications. Still, it has as drawbacks the poor intravascular stability of the solution and the fact that air bubbles are eliminated from the body during the passage of blood through the lungs, thus preventing its use for visualization of structures of the left heart when the agitated saline solution is administered in a peripheral vein.

[…]

[…]

We are experiencing a change paradigm in modern life. With the presence of computers and intelligent machines everywhere, the predictions of science-fiction books from years ago gradually become reality; these are the times of pervasive computing. Among the computational most frequently mentioned tools in clinical studies and seen with enthusiasm by the scientific community is the Artificial Intelligence and consequently the machines that learn, which is best quoted in its original English form, Machine Learning. In general Artificial Intelligence is defined as the constellation of items (algorithms, robotics, neural networks) that allow a software to have intelligence properties that are comparable to those of a human being, among them learning from databases with minimal human interference.

Obermeyer and Emanuel recently wrote an editorial stating that Machine Learning has become widespread and imperative for solving complex problems in the various fields of science, and in the medical field its use will transform the practice. The use of artificial intelligence is evolving increasingly in cardiology and there are already excellent examples in several areas. Using a sophisticated learning system to electrocardiographic interpretation, Li et al. achieved that electrocardiographic patterns were automatically recognized with an accuracy of 88% for the classification of abnormal rhythms⁽⁾. One of the most important limitations of the system studied was the quality of the electrocardiographic signal for interpretation and learning, which highlights one of the essential characteristics of Machine Learning, that is the need for accurate and reproducible information for the formation of databases.^, As databases are usually produced from patients selected for their basic condition, one of the most important points for development is the creation of broader and generalizable databases that do not induce biases in the interpretation of findings, point in which industry is heavily investing at the moment.

[…]