Assessment of Artificial Intelligence in Echocardiography Diagnostics in Differentiating Takotsubo Syndrome From Myocardial Infarction

Abstract

IMPORTANCEMachine learning algorithms enable the automatic classification of cardiovascular diseases based on raw cardiac ultrasound imaging data. However, the utility of machine learning in distinguishing between takotsubo syndrome (TTS) and acute myocardial infarction (AMI) has not been studied.OBJECTIVES To assess the utility of machine learning systems for automatic discrimination of TTS and AMI. DESIGN, SETTINGS, AND PARTICIPANTSThis cohort study included clinical data and transthoracic echocardiogram results of patients with AMI from the Zurich Acute Coronary Syndrome Registry and patients with TTS obtained from 7 cardiovascular centers in the International Takotsubo Registry.

Artificial intelligence applied to cardiovascular imaging, a critical focus on echocardiography: The point‐of‐view from “the other side of the coin”

“…AI may improve the characterization of heart failure with preserved ejection fraction (HFpEF), Takotsubo cardiomyopathy, hypertrophic cardiomyopathy, systemic and primary pulmonary hypertension, and coronary artery disease, aiming to personalize the treatment for those heterogeneous syndromes by processing big data. [7][8][9][10]15 Big data are extremely large datasets, otherwise impossible to be analyzed using traditional statistical methods. In fact, in conventional statistics, to apply the widely used logistic regression model, the cstatistic is mainly, although not only, used as the predictive accuracy standard measure.…”

“…In cardiovascular clinical care, AI has been applied to discover new genotypes and phenotypes in known diseases, ameliorate the patient care, optimize cost‐effectiveness in prevention and treatment, and positively impact on readmission and mortality. AI may improve the characterization of heart failure with preserved ejection fraction (HFpEF), Takotsubo cardiomyopathy, hypertrophic cardiomyopathy, systemic and primary pulmonary hypertension, and coronary artery disease, aiming to personalize the treatment for those heterogeneous syndromes by processing big data 7–10,15 …”

Machines that save lives in the intensive care unit: the ultrasonography machine

“…The goal is refined to its maximum to precisely meet needs, without concession on quality, and without superfluous addition [ 4 ]. In anticipation of the development of robust artificial intelligence (AI) capability, the frugal CCUS machine should have the potential to be upgraded in the future, as the rapid development of AI for image interpretation [ 5 ] may allow the building of reliable decision tools that could be remotely available worldwide with the ongoing constellation of satellites for broadband global internet connectivity. While independent of machine design per se, training in image acquisition/interpretation and appropriate application of the results is required for the machine to be used to save lives.…”

“…The goal is refined to its maximum to precisely meet needs, without concession on quality, and without superfluous addition [4]. In anticipation of the development of robust artificial intelligence (AI) capability, the frugal CCUS machine should have the potential to be upgraded in the future, as the rapid development of AI for image interpretation [5] may allow the building of reliable decision tools that could be remotely available worldwide with the ongoing constellation of…”

Advancing cardiovascular medicine with machine learning: Progress, potential, and perspective

“… 44 Several studies have shown the ability to detect heart failure defined by low ejection fraction, 32 , 37 , 38 as well as heart failure with preserved ejection fraction, 45 , 46 , 47 , 48 and to differentiate stress cardiomyopathy from acute myocardial infarction. 49 Ulloa Cerna et al. trained an algorithm that demonstrated the ability to predict all-cause mortality from echo videos, a task not typically performed by cardiologists interpreting echos.…”