Artificial intelligence applied to support medical decisions for the automatic analysis of echocardiogram images: A systematic review.

The echocardiogram is a test that is widely used in Heart Disease Diagnoses. However, its analysis is largely dependent on the physician's experience. In this regard, artificial intelligence has become an essential technology to assist physicians. This study is a Systematic Literature Review (SLR) of primary state-of-the-art studies that used Artificial Intelligence (AI) techniques to automate echocardiogram analyses. Searches on the leading scientific article indexing platforms using a search string returned approximately 1400 articles. After applying the inclusion and exclusion criteria, 118 articles were selected to compose the detailed SLR. This SLR presents a thorough investigation of AI applied to support medical decisions for the main types of echocardiogram (Transthoracic, Transesophageal, Doppler, Stress, and Fetal). The article's data extraction indicated that the primary research interest of the studies comprised four groups: 1) Improvement of image quality; 2) identification of the cardiac window vision plane; 3) quantification and analysis of cardiac functions, and; 4) detection and classification of cardiac diseases. The articles were categorized and grouped to show the main contributions of the literature to each type of ECHO. The results indicate that the Deep Learning (DL) methods presented the best results for the detection and segmentation of the heart walls, right and left atrium and ventricles, and classification of heart diseases using images/videos obtained by echocardiography. The models that used Convolutional Neural Network (CNN) and its variations showed the best results for all groups. The evidence produced by the results presented in the tabulation of the studies indicates that the DL contributed significantly to advances in echocardiogram automated analysis processes. Although several solutions were presented regarding the automated analysis of ECHO, this area of research still has great potential for further studies to improve the accuracy of results already known in the literature.

Análise da segurança e dos preditores de arritmias durante o ecocardiograma sob estresse com Dobutamina em um ambiente não hospitalar / Analyzing the safety and predictors of arrhythmias during dobutamine-atropine estress echocardiography in a non-hospital setting

Fundamento: O ecocardiograma sob estresse com dobutamina-atropina (EEDA) é um exame acessível e importante, principalmente em pacientes sob investigação de doença coronariana. Contudo, faz-se necessário a avaliação de sua segurança, devido ao seu emprego em pacientes com patologias cada vez mais complexas, graves e idosos.Objetivo: Confirmar segurança do EEDA e avaliar os preditores de arritmias em ambiente não hospitalar.Métodos: EEDA foi realizado com o objetivo de avaliar isquemia utilizando o protocolo padrão de infusão de dobutamina de 5 a 40 mcg/kg/min associado a atropina.Resultados: Foram avaliados de forma prospectiva 2227 pacientes no período de setembro a novembro de 2010. Idade média foi de 60,7 +/- 12,5 anos e 60,8% eram mulheres. A fração de ejeção média foi de 67,9% +/- 9. Dentre dos eventos adversos, 12 pacientes apresentaram resposta hipertensiva, 466 arritmias, 58 cefaleias e 57 dores precordial. Nenhum paciente apresentou infarto agudo do miocárdio, fibrilação ventricular, ruptura cardíaca, assistolia ou morte. Quanto ao surgimento das arritmias significativas, 3 pacientes apresentaram fibrilação atrial,16 taquicardias supraventricular sustentada, 19 taquicardias ventricular não sustentada e 2 taquicardias ventricular sustentada. Nestes pacientes, idade (OR = 1,0559, p = 0,0002) e o índice de escore de contração segmentar (IECS) em repouso > 1 (OR 2,5039, p = 0,0354) foram preditores independentes para o surgimento de arritmias significativas durante o exame.Conclusão: O EEDA mostrou-se seguro nesse grupo de pacientes em ambiente não hospitalar. Idade e IECS em repouso > 1 foram preditores independentes para o surgimento de arritmias significativas durante o exame

Background: Dobutamine-atropine stress echocardiography (DASE) is an accessible and important test, especially in patients under investigation for coronary artery disease. However, it is necessary to evaluate its safety, as it is used in patients with increasingly complex and serious conditions and in seniors.Objective: To confirm the safety of DASE and evaluate the predictors of arrhythmias in a non-hospital setting. Methods: DASE was performed to evaluate ischemia using the standard protocol of dobutamine infusion of 5 to 40 mcg/kg/min associated with atropine. Results: From September to November 2010, 227 patients were evaluated prospectively. The mean age was 60.7 +/- 12.5 years old and 60.8% were females. Mean ejection fraction was 67.9 +/- 9. Among the adverse events, 12 patients presented hypertensive response, 466 had arrhythmia, 58 had headaches and 57 had precordial pain. No patient had acute myocardial infarction, ventricular fibrillation, cardiac rupture, asystole or death. As for the onset of significant arrhythmia, three patients had atrial fibrillation, 16 had sustained supraventricular tachycardia, 19 had non-sustained ventricular tachycardia and 2 had sustained ventricular tachycardia. In these patients, age (OR = 1.0559, p = 0.0002) and segmental contractility index at rest (SCIr) > 1 (OR 2.5039, p = 0.0354) were independent predictors for the onset significant arrhythmia during the test. Conclusion: DASE was proven safe in this group of patients in a non-hospital setting. Age and SCIr > 1 were independent predictors for the onset of significant arrhythmia during the test