Search

Background: Adopting artificial intelligence (AI) in medicine may improve speed and accuracy in patient diagnosis. We sought to develop an AI algorithm to interpret wide-complex tachycardia (WCT) electrocardiograms (ECGs) and compare its diagnostic accuracy with that of cardiologists., Methods: Using 3330 WCT ECGs (2906 supraventricular tachycardia [SVT] and 424 ventricular tachycardia [VT]), we created a training/validation (3131) and a test set (199 ECGs). A convolutional neural network structure using a modification of differentiable architecture search was developed to differentiate between SVT and VT., Results: The mean accuracy of electrophysiology (EP) cardiologists was 92.5% with sensitivity 91.7%, specificity 93.4%, positive predictive value 93.7%, and negative predictive value 91.7%. Non-EP cardiologists had an accuracy of 73.2 ± 14.4% with sensitivity, specificity, and positive and negative predictive values of 59.8 ± 18.2%, 93.8 ± 3.7%, 93.6 ± 2.3%, and 73.2 ± 14.4%, respectively. AI had superior sensitivity and accuracy (91.9% and 93.0%, respectively) than non-EP cardiologists and similar performance compared with EP cardiologists. Mean time to interpret each ECG varied from 10.1 to 13.8 seconds for EP cardiologists and from 3.1 to 16.6 seconds for non-EP cardiologists. AI required a mean of 0.0092 ± 0.0035 seconds for each ECG interpretation., Conclusions: AI appears to diagnose WCT with accuracy superior to non-EP cardiologists and similar to EP cardiologists. Using AI to assist with ECG interpretations may improve patient care., (Copyright © 2024 The Authors. Published by Elsevier Inc. All rights reserved.)

Research in artificial intelligence (AI) has progressed over the past decade. The field of cardiac imaging has seen significant developments using newly developed deep learning methods for automated image analysis and AI tools for disease detection and prognostication. This review is aimed at those without special background in AI. We review AI concepts and survey the growing contemporary applications of AI for image analysis in echocardiography, nuclear cardiology, cardiac computed tomography, cardiac magnetic resonance, and invasive angiography., (Copyright © 2021 Canadian Cardiovascular Society. Published by Elsevier Inc. All rights reserved.)

Noninvasive cardiac imaging is widely used for the diagnosis and management of cardiac patients. The increasing demand for cardiac imaging begins to exceed the number of available interpreting physicians, leaving less time to interpret studies. In addition, the busy clinician is facing the increasingly daunting task of keeping abreast of current medical advancements and the ongoing changes in disease diagnosis and therapy. Committing to memory and recalling such large volumes of information is challenging and is responsible for difficulties in adopting the rapid changes in imaging practice, and is likely partially responsible for errors in patient diagnosis and management. Diagnostic errors rank high in the cause of death in the United States, and are more common than any other medical error and are responsible for most malpractice claims. Most of these errors are related to cognitive errors. The use of artificial intelligence systems that can serve as complementary methods to assist humans with decision making can potentially prevent these errors. The past decades witnessed the development and integration of these tools, which can assist physicians with image interpretation. These tools work to optimize image quality for better visualization and accompany all imaging modalities, starting from patient selection for the appropriate test, patient preparation, image acquisition, processing, and finally interpretation. Current and future directions for technologies that support cardiac imaging physicians are discussed in this review., (Copyright © 2018 Canadian Cardiovascular Society. Published by Elsevier Inc. All rights reserved.)

Background: There is a perception among Canadian physicians that coronary artery disease (CAD) and adverse cardiac events are more common in those of French Canadian heritage. We sought to compare the prevalence of CAD using coronary computed tomographic angiography (CCTA) in French Canadians and non-French white Canadians., Methods: Consecutive patients were prospectively enrolled in our institutional CCTA registry. Of 10,868 CCTA examinations, we analyzed white patients who identified themselves as French Canadian or non-French Canadian. These 2 groups were compared for baseline characteristics, cardiovascular risk factors, and routine markers for CAD on CTCA. Propensity score adjustments were also made to account for differences in demographics., Results: We identified 1683 French Canadians (mean age, 58.5 ± 10.7 years; 54.2% men) and 5077 non-French white Canadians (mean age, 59.4 ± 11.4 years; 57.3% men). French Canadians were more likely to have a smoking history (64.1% vs 56.1%), diabetes (15.6% vs 13.6%), and a family history of premature CAD (53.3% vs 44.6%) (P < 0.05 for all). There was no significant difference in measures of CAD between French Canadians and non-French white Canadians in obstructive CAD (32.5% vs 32.2%; P = 0.997), total plaque score (4.6 ± 4.3 vs 4.5 ± 4.4; P = 0.616) and Agatston score (168.1 ± 319.8 vs 183.6 ± 433.7; P = 0.371). After propensity score adjustment, there was still no significant difference between the groups., Conclusions: Our study suggests that French Canadians in the Champlain region have a greater prevalence of cardiovascular risk factors compared with non-French Canadians; however, they do not appear to have a greater prevalence or severity of coronary atherosclerosis as assessed by CCTA., (Copyright © 2016 Canadian Cardiovascular Society. Published by Elsevier Inc. All rights reserved.)

A vast array of noninvasive imaging modalities is available for the evaluation of the presence and severity of coronary artery disease (CAD). Choosing the right test can be challenging but is critical for proper patient diagnosis and management. Presently available imaging tests for CAD include: (1) nuclear myocardial perfusion imaging procedures (single-photon emission tomography) and positron emission tomography, (2) stress echocardiography, (3) computed tomography coronary angiography, and (4) cardiac magnetic resonance imaging. Exercise treadmill testing electrocardiography is another alternative that we will discuss briefly. Selection of the most appropriate imaging modality requires knowledge of the clinical question being addressed, patient characteristics (pretest probability and prevalence of disease), the strengths, limitations, risks, costs, and availability of each procedure. To assist with test selection, we review the relevant literature in detail to consider the relative merits of cardiac imaging modalities for: (1) detection of CAD, (2) risk stratification and prognostication, and (3) guiding clinical decision making., (Copyright © 2013 Canadian Cardiovascular Society. Published by Elsevier Inc. All rights reserved.)

Atherosclerosis exacts a large toll on society in the form of cardiovascular morbidity, mortality, and resource use and is exacerbated by the epidemics of obesity and diabetes. Consequently, there is a critical need for more-effective methods of diagnosis, treatment, and prevention of the complications of atherosclerosis. Careful and well-conducted large population studies are needed in order to truly understand the natural history of the disease, its imaging biomarkers, and their links to patient outcomes. The Canadian Atherosclerosis Imaging Network (CAIN) is a unique research network funded by the Canadian Institutes of Health Research and the Canada Foundation for Innovation and designed to address these needs and to enable large population-based imaging studies. The central objective of CAIN is to move innovations in imaging toward their broad application in clinical research and clinical practice for the improved evaluation of cardiac and neurologic vascular disease. CAIN is established as an international resource for studying the natural history, progression, and regression of atherosclerosis, as well as novel therapeutic interventions aimed at atherosclerosis. The network represents Canada's leading atherosclerosis imaging experts, embodying both basic imaging science and clinical imaging research. The network is improving methods of detection and treatment of atherosclerosis and, through a better understanding of the underlying disease itself, improving strategies for disease prevention. The benefits are expected to appear in the next 2 to 3 years. CAIN will drive innovation in imaging technology within the field of cardiology and neurology and improve health outcomes in Canada and worldwide., (Copyright © 2013 Canadian Cardiovascular Society. Published by Elsevier Inc. All rights reserved.)

Nuclear cardiology came of age in the 1970s and subsequently has expanded so that more than 9 million single-photon emission computed tomography (SPECT) studies are performed annually in North America. Coronary artery disease management has demanded a reliable technique that will detect, risk stratify, and assist with revascularization decisions. Using cardiac SPECT and positron-emission tomography (PET), researchers and clinicians have sought to achieve excellence in coronary artery disease diagnosis and risk stratification, and strive to achieve higher standards in these areas. Developments in other cardiac imaging modalities, however, such as cardiac computed tomography, cardiac magnetic resonance, and echocardiography, have raised expectations in terms of diagnostic accuracy and achieving high quality images with little or no ionizing radiation exposure. The challenge facing nuclear cardiology as it embarks upon a fifth decade of clinical use is whether high quality images can be obtained at lower radiation exposures. In this review we consider current practice in SPECT and PET perfusion imaging. We discuss emerging advances in techniques, technologies, and radiotracers that focus specifically on improvements in image quality that enhance diagnostic accuracy while reducing radiation exposure. We provide a perspective as to the future roles of cardiac SPECT and PET in ischemic heart disease, and consider emerging novel applications beyond perfusion imaging. Although for a number of years nuclear cardiology has shone brightly as a leading light for the imaging of ischemic heart disease, its half-life has not yet been reached. Instead, even with the pressure to reduce radiation exposure, the future continues to look bright for cardiac SPECT and PET., (Copyright © 2013 Canadian Cardiovascular Society. Published by Elsevier Inc. All rights reserved.)

Background: Although positron emission tomography (PET) is routinely performed using vasodilator stress, exercise and dobutamine stress are available alternatives. Evidence suggests that vasodilator PET myocardial perfusion imaging (MPI) has prognostic value, but the prognostic value of treadmill exercise and dobutamine PET MPI is unknown., Objective: To determine the potential prognostic value of nonvasodilator stress PET MPI., Methods: Patients underwent treadmill exercise or dobutamine PET MPI. Images were assessed qualitatively and semiquantitatively. PET results were categorized as normal (summed stress score [SSS] of less than 4), abnormal (SSS of 4 or greater) or inconclusive (SSS of less than 4 and submaximal peak stress heart rate). Patient follow-up (cardiac death, nonfatal myocardial infarction [MI] and/or late revascularization) was performed., Results: Of the 124 patients (mean follow-up period of 2.3+/-1.6 years), 46 patients (37%) had a normal study, 15 patients (12%) had an inconclusive study and 63 (51%) had an abnormal PET. Patients with a normal PET had no deaths or nonfatal MI. One patient with a normal PET underwent late revascularization (annual event rate of 1.7%). Patients with an abnormal PET had 15 cardiac events (one cardiac death, four nonfatal MIs and 10 late revascularizations), with an annual event rate of 13.0% (P=0.002)., Conclusions: Although small, the present study suggests that defects seen on PET myocardial perfusion, resulting from stressors (treadmill exercise and dobutamine) that increase myocardial oxygen demand, may have prognostic value.

Background: The present study compared computed tomographic coronary angiography (CTA) and positron emission tomography (PET) for the detection of significant anatomical coronary artery stenosis as defined by conventional invasive coronary angiography (CICA)., Methods: The study protocol was approved by the local ethics board, and informed consent was obtained from all patients. Of the 26 patients (mean age 57+/-9 years, 18 men) who prospectively underwent CTA and rubidium-82 PET before CICA, 24 patients had a history of chest pain. Images were interpreted by expert readers and assessed for the presence of anatomically significant coronary stenosis (50% luminal diameter stenosis or greater) or myocardial perfusion defects. Diagnostic test characteristics were analyzed using patient-based, territory-based, vessel-based and segment-based analyses., Results: In the 24 patients referred for chest pain, CTA had similar sensitivity to PET, but was more specific (sensitivity 95% [95% CI 72% to 100%] versus 95% [95% CI 72% to 100%], respectively; specificity 100% [95% CI 46% to 100%] versus 60% [95% CI 17% to 93%], respectively) in the detection of patients with anatomical coronary artery stenosis of 50% or greater. On a per-segment basis of all 26 patients, CTA had a sensitivity, specificity, positive predictive value and negative predictive value of 72%, 99%, 91% and 95%, respectively, in all coronary segments., Conclusions: Coronary CTA has a similar sensitivity and specificity to rubidium-82 PET for the identification of patients with significant anatomical coronary artery disease.

Over the past decade, enormous progress has been made in the technology of computed tomography (CT) imaging. Substantial improvements in spatial resolution, temporal resolution, hardware and software now permit imaging of the entire coronary artery tree within a single breath-hold. Several studies have demonstrated a high sensitivity and specificity for the detection of significant coronary artery stenoses. In addition to imaging of the native coronary arteries, CT angiography may also be used to assess arterial and venous bypass grafts, and to detect the presence and composition of atherosclerotic plaque. Because CT angiography images are acquired with electrocardiogram gating, the data sets permit the assessment of left ventricular function (ejection fraction and regional wall motion), left ventricular volumes and, potentially, myocardial perfusion at no extra cost. The practical advantages of CT angiography (in regard to safety and cost) along with its future anticipated advancements make it an attractive alternative to diagnostic coronary angiography.

Background: The extent of Q wave 'burden' on electrocardiograms (ECGs) has not been correlated with the extent of scarring and hibernation as determined quantitatively by positron emission tomography (PET)., Objective: A retrospective study was performed to identify if ECG Q wave burden predicts the extent of scarring or mismatch (hibernating myocardium) as defined by rubidium-82/F-18 fluorodeoxyglucose PET viability imaging., Patients and Methods: Eighty-three consecutive patients with coronary artery disease undergoing rubidium-82/F-18 fluoro-deoxyglucose viability imaging (mean age 67.9+/-11 years, with a mean ejection fraction of 27+/-7%) formed the study population. Resting ECG was interpreted for the presence or absence of Q waves using standard ECG criteria for Q wave myocardial infarction. Patients were divided into two groups based on their Q wave burden on ECG (small to moderate scar: zero to four Q waves; large scar: five or more Q waves). Automated analysis was used to calculate the extent of scarring and mismatch (hibernating myocardium) on PET as a percentage of left ventricular myocardium. Mean PET scar and mismatch scores were calculated for the two groups., Results: The mean PET scar scores were significantly different between the small to moderate ECG scar group (13.9+/-7.3% of the left ventricle) and the large scar group (20.6+/-8.1% of the left ventricle; P=0.001). The mismatch scores for the small to moderate scar group (4.6+/-2.8%) were not significantly different from those of the large scar group (4.05+/-2.8%; P=0.7)., Conclusions: ECG Q wave 'burden' was associated with the presence of scars as defined by PET but did not accurately predict the amount of hibernating myocardium.

A case of a 43-year-old man with impending paradoxical embolism (IPE) is described. The patient initially presented with pulmonary embolism and was diagnosed with an IPE on transthoracic and transesophageal echocardiography. He was subsequently treated with heparin and thrombolysis. A comprehensive review of the English literature over the past 20 years identified 60 previously reported cases of IPE. This report discusses the main clinical features, the diagnostic role of echocardiography and the outcome of medical and surgical treatment strategies in patients with IPE. Based on the literature to date, we recommend that patients with impending paradoxical embolism be treated with initial systemic heparinization followed by emergent surgical embolectomy if the surgical risks are acceptable.