Search

Advancements in machine learning and computing methods have given new life and great excitement to one of the most essential diagnostic tools to date-the electrocardiogram (ECG). The application of artificial intelligence-enabled ECG (AI-ECG) has resulted in the ability to identify electrocardiographic signatures of conventional and unique variables and pathologies, giving way to tremendous clinical potential. However, what these AI-ECG models are detecting that the human eye is missing remains unclear. In this article, we highlight some of the recent developments in the field and their potential clinical implications, while also attempting to shed light on the physiologic and pathophysiologic features that enable these models to have such high diagnostic yield. © 2022 American Physiological Society. Compr Physiol 12:3417-3424, 2022.

In the context of atrial fibrillation (AF), traditional clinical practices have thus fallen short in several domains, such as identifying patients at risk of incident AF or patients with concomitant undetected paroxysmal AF. Novel approaches leveraging artificial intelligence have the potential to provide new tools to deal with some of these old problems.To discuss the roles of artificial intelligence (AI)-enabled electrocardiogram (ECG) pertaining to AF, potential roles of deep learning (DL) models in the context of current knowledge gaps, as well as limitations of these models.An extensive search and review of the currently available literature on the topics.One key area where DL models can translate to better patient outcomes is through automated ECG interpretation. Challenges with regards to the benefits and harms of AF screening remain. In this context, a unique model was developed to detect underlying hidden AF from sinus rhythm.Knowledge gaps remain regarding the best ways to monitor patients with embolic stroke of undetermined source (ESUS) and identifying those who would benefit most from oral anticoagulation. The AI-enabled AF model is one potential way to tackle this complex problem as it could be used to identify a subset of high-risk ESUS patients likely to benefit from empirical oral anticoagulation. The role of DL models assessing AF burden from long-duration ECG data is also discussed as a way of guiding management. There is a trend towards the use of consumer-grade wristbands and watches to detect AF from photoplethysmography data. However, ECG currently remains the gold standard to detect arrythmias including AF. Lastly, the role of adequate external validation of the models and clinical trials to study true performance is discussed.Algorithms using AI to interpret ECGs in various new ways have been developed. While still, much work needs to be done, these technologies have shown enormous potential in a short span of time. With further advancements and continuous research, these novel ways of interpretation may well become part of everyday clinical workflow.

Atrial fibrillation (AF) is one of the most common cardiac arrhythmias. Implantable and wearable cardiac devices have enabled the detection of asymptomatic AF episodes-termed subclinical AF (SCAF). SCAF, the prevalence of which is likely significantly underestimated, is associated with increased cardiovascular and all-cause mortality and a significant stroke risk. Recent advances in machine learning, namely artificial intelligence-enabled ECG (AI-ECG), have enabled identification of patients at higher likelihood of SCAF. Leveraging the capabilities of AI-ECG algorithms to drive screening protocols could eventually allow for earlier detection and treatment and help reduce the burden associated with AF. Expected final online publication date for the Annual Review of Medicine, Volume 73 is January 2022. Please see http://www.annualreviews.org/page/journal/pubdates for revised estimates.

Accurate automated wide QRS complex tachycardia (WCT) differentiation into ventricular tachycardia (VT) and supraventricular wide complex tachycardia (SWCT) can be accomplished using calculations derived from computerized electrocardiogram (ECG) data of paired WCT and baseline ECGs.Develop and trial novel WCT differentiation approaches for patients with and without a corresponding baseline ECG.We developed and trialed WCT differentiation models comprised of novel and previously described parameters derived from WCT and baseline ECG data. In Part 1, a derivation cohort was used to evaluate five different classification models: logistic regression (LR), artificial neural network (ANN), Random Forests [RF], support vector machine (SVM), and ensemble learning (EL). In Part 2, a separate validation cohort was used to prospectively evaluate the performance of two LR models using parameters generated from the WCT ECG alone (Solo Model) and paired WCT and baseline ECGs (Paired Model).Of the 421 patients of the derivation cohort (Part 1), a favorable area under the receiver operating characteristic curve (AUC) by all modeling subtypes: LR (0.96), ANN (0.96), RF (0.96), SVM (0.96), and EL (0.97). Of the 235 patients of the validation cohort (Part 2), the Solo Model and Paired Model achieved a favorable AUC for 103 patients with (Solo Model 0.87; Paired Model 0.95) and 132 patients without (Solo Model 0.84; Paired Model 0.95) a corroborating electrophysiology procedure or intracardiac device recording.Accurate WCT differentiation may be accomplished using computerized data of (i) the WCT ECG alone and (ii) paired WCT and baseline ECGs.

Background Accurate automated wide QRS complex tachycardia (WCT) discrimination between ventricular tachycardia (VT) and supraventricular wide complex tachycardia (SWCT) can be accomplished using novel calculations derived from computerized electrocardiogram (ECG) data from paired WCT and baseline ECGs. Purpose Our aim was to develop and trial novel WCT discrimination approaches for WCT patients with and without a corresponding baseline ECG. Central to this analysis was the creation and use of a novel parameter (i.e., percent monophasic time-voltage area [PMonoTVA] [%]) that may be derived from computerized ECG measurements present on the WCT ECG alone. Methods In a two-part study, we derived and tested WCT differentiation models comprised of novel and previously established parameters formulated from computerized data of paired WCT and baseline ECGs. In Part 1, novel and established parameters generated from WCT and baseline ECG data were used to derive, validate, and compare five different binary classification models: (i) logistic regression [LR], (ii) artificial neural network [ANN], (iii) Random Forests [RF], (iv) support vector machine [SVM], and (v) ensemble learning (EL). In Part 2, two unique LR models were derived, validated, and compared using parameters generated from computerized data of the (i) WCT ECG alone (i.e., Solo Model) and (ii) paired WCT and baseline ECGs (i.e., Paired Model). Results In Part 1, among 103 patients with VT or SWCT diagnoses established from corroborating electrophysiology studies or intra-cardiac device recordings, favorable diagnostic performance was achieved by all modeling technique subtypes: LR (area under the receiver operating characteristic curve [AUC] 0.95), ANN (AUC 0.91), RF (AUC 0.97), SVM (AUC 0.98), and EL (AUC 0.97). In Part 2, among 235 patients with a VT or SWCT diagnosis established with (Gold Standard cohort) or without (Non-Gold Standard cohort) a corroborating electrophysiology procedure or intra-cardiac device recording, favorable diagnostic performance was achieved by the Solo Model (AUC 0.86) and Paired Model (AUC 0.95) (Table). Conclusion Accurate WCT discrimination may be accomplished using novel parameters derived from computerized data of the WCT ECG alone and paired WCT and baseline ECGs. Funding Acknowledgement Type of funding sources: Public grant(s) – National budget only. Main funding source(s): National Institute of Health

Objective To develop an artificial intelligence (AI)–enabled electrocardiogram (ECG) algorithm capable of comprehensive, human-like ECG interpretation and compare its diagnostic performance against conventional ECG interpretation methods. Methods We developed a novel AI-enabled ECG (AI-ECG) algorithm capable of complete 12-lead ECG interpretation. It was trained on nearly 2.5 million standard 12-lead ECGs from over 720,000 adult patients obtained at the Mayo Clinic ECG laboratory between 2007 and 2017. We then compared the need for human over-reading edits of the reports generated by the Marquette 12SL automated computer program, AI-ECG algorithm, and final clinical interpretations on 500 randomly selected ECGs from 500 patients. In a blinded fashion, 3 cardiac electrophysiologists adjudicated each interpretation as (1) ideal (ie, no changes needed), (2) acceptable (ie, minor edits needed), or (3) unacceptable (ie, major edits needed). Results Cardiologists determined that on average 202 (13.5%), 123 (8.2%), and 90 (6.0%) of the interpretations required major edits from the computer program, AI-ECG algorithm, and final clinical interpretations, respectively. They considered 958 (63.9%), 1058 (70.5%), and 1118 (74.5%) interpretations as ideal from the computer program, AI-ECG algorithm, and final clinical interpretations, respectively. They considered 340 (22.7%), 319 (21.3%), and 292 (19.5%) interpretations as acceptable from the computer program, AI-ECG algorithm, and final clinical interpretations, respectively. Conclusion An AI-ECG algorithm outperforms an existing standard automated computer program and better approximates expert over-read for comprehensive 12-lead ECG interpretation.

One of the most critical and challenging skills is the distinction of wide complex tachycardias into ventricular tachycardia or supraventricular wide complex tachycardia. Prompt and accurate differentiation of wide complex tachycardias naturally influences short- and long-term management decisions and may directly affect patient outcomes. Currently, there are many useful electrocardiographic criteria and algorithms designed to distinguish ventricular tachycardia and supraventricular wide complex tachycardia accurately; however, no single approach guarantees diagnostic certainty. In this review, we offer an in-depth analysis of available methods to differentiate wide complex tachycardias by retrospectively examining its rich literature base – one that spans several decades.

Background Automated computerized electrocardiogram (ECG) interpretation algorithms are designed to enhance physician ECG interpretation, minimize medical error, and expedite clinical workflow. However, the performance of current computer algorithms is notoriously inconsistent. We aimed to develop and validate an artificial intelligence–enabled ECG (AI-ECG) algorithm capable of comprehensive 12-lead ECG interpretation with accuracy comparable to practicing cardiologists. Methods We developed an AI-ECG algorithm using a convolutional neural network as a multilabel classifier capable of assessing 66 discrete, structured diagnostic ECG codes using the cardiologist's final annotation as the gold-standard interpretation. We included 2,499,522 ECGs from 720,978 patients ≥18 years of age with a standard 12-lead ECG obtained at the Mayo Clinic ECG laboratory between 1993 and 2017. The total sample was randomly divided into training (n = 1,749,654), validation (n = 249,951), and testing (n = 499,917) datasets with a similar distribution of codes. We compared the AI-ECG algorithm's performance to the cardiologist's interpretation in the testing dataset using receiver operating characteristic (ROC) and precision recall (PR) curves. Results The model performed well for various rhythm, conduction, ischemia, waveform morphology, and secondary diagnoses codes with an area under the ROC curve of ≥0.98 for 62 of the 66 codes. PR metrics were used to assess model performance accounting for category imbalance and demonstrated a sensitivity ≥95% for all codes. Conclusions An AI-ECG algorithm demonstrates high diagnostic performance in comparison to reference cardiologist interpretation of a standard 12-lead ECG. The use of AI-ECG reading tools may permit scalability as ECG acquisition becomes more ubiquitous.

Background Automated wide complex tachycardia (WCT) differentiation into ventricular tachycardia (VT) and supraventricular wide complex tachycardia (SWCT) may be accomplished using novel calculations that quantify the extent of mean electrical vector changes between the WCT and baseline electrocardiogram (ECG). At present, it is unknown whether quantifying mean electrical vector changes within three orthogonal vectorcardiogram (VCG) leads (X, Y, and Z leads) can improve automated VT and SWCT classification. Methods A derivation cohort of paired WCT and baseline ECGs was used to derive five logistic regression models: (i) one novel WCT differentiation model (i.e., VCG Model), (ii) three previously developed WCT differentiation models (i.e., WCT Formula, VT Prediction Model, and WCT Formula II), and (iii) one “all‐inclusive” model (i.e., Hybrid Model). A separate validation cohort of paired WCT and baseline ECGs was used to trial and compare each model's performance. Results The VCG Model, composed of WCT QRS duration, baseline QRS duration, absolute change in QRS duration, X‐lead QRS amplitude change, Y‐lead QRS amplitude change, and Z‐lead QRS amplitude change, demonstrated effective WCT differentiation (area under the curve [AUC] 0.94) for the derivation cohort. For the validation cohort, the diagnostic performance of the VCG Model (AUC 0.94) was similar to that achieved by the WCT Formula (AUC 0.95), VT Prediction Model (AUC 0.91), WCT Formula II (AUC 0.94), and Hybrid Model (AUC 0.95). Conclusion Custom calculations derived from mathematically synthesized VCG signals may be used to formulate an effective means to differentiate WCTs automatically.

With an ageing population, the growing prevalence of atrial fibrillation (AF) is becoming a public health crisis. In the USA alone, the prevalence of AF is expected to more than double over the next 50 years.1 This undoubtedly has important clinical implications given the morbidity, mortality and tremendous healthcare cost burden associated with AF.2 3 In addition to the increasing numbers of known AF cases, another issue looms: a subset of individuals with silent and subclinical AF coexists in whom capturing the arrhythmia on single standard 12-lead ECG or even extended non-invasive ambulatory ECG monitoring remains a challenge. In fact, the first clinical presentation of those with asymptomatic AF may be an acute ischaemic stroke or decompensated heart failure.4 Therefore, the ability to identify individuals at increased risk of AF can aid in screening, surveillance, management and prevention strategies. The current study by Sanz-Garcia and colleagues,5 represents an innovative approach to doing just that. Until recently, AF prediction has been based on clinical variables integrated into scoring systems such as CHARGE-AF (Cohorts for Aging and Research in Genomic Epidemiology–AF) score, which is the best studied and most well-established clinical AF scoring tool.6 Others include the FHS (Framingham Heart Study), ARIC (Atherosclerosis Risk in Communities) and CHA2DS2-VASc risk scores.6 7 These approaches, however, require time-intensive data abstraction of multiple variables—some …

Atrial fibrillation (AF) is known to affect at least 30 million people worldwide [1,2], although this may be an underestimation. AF can be asymptomatic and fleeting and often goes undetected. In fa...

The prevalence of atrial fibrillation (AF) continues to grow in an aging population, and its impact on both patients and the health care system has has made it a global burden. There are limited available options to detect individuals at risk of AF that may benefit from prevention and treatment strategies. The ECG may be an effective tool do so. In this work, we discuss the latest work by Hayiroglu and colleagues related to this work and the use of novel ECG prediction tools to identify individuals individuals that could benefit from early and proactive screening, surveillance, and management strategies.

It is hard to imagine something more central to the practice of medicine than the performance and interpretation of the ECG. This simple, non-invasive, and ubiquitous test is essential for the diagnosis of a wide range of medical conditions, across a broad range of medical settings—the emergency room, primary care office, intensive care unit and beyond. For nearly 100 years, this test has held up as a fundamental pillar of medical practice. Unfortunately, proficiency in ECG interpretation is not a universal skill, and the barriers in achieving ECG fluency are rooted at multiple levels of medical curricula. To aid in solving the problem of declining ECG competency, clearly defined skill competencies for all healthcare professionals are needed. Once competency expectations are set, centralised educational resources may be used to achieve these benchmarks. The medical education community has been the driver to spearhead such societal initiatives and will need to be integral in the rejuvenation of proper ECG interpretation. In this context, medical educators ought to inspire the next generation as well as current providers to revisit and reinvigorate the complexities and beauty of ECG interpretation. The ECG is one of the most powerful diagnostic tools in modern medicine. As a graphical display of the heart’s electrical activity, the ECG communicates unique and vital information regarding the electrophysiological properties, anatomical structure, myocardial tissue characteristics, haemodynamic condition, and enveloping metabolic milieu of a patient’s beating heart. The ECG is one of the most used diagnostic tests, with an estimated 300 million ECGs performed annually in the USA alone. More recently, the application of artificial intelligence to the ECG has unlocked new promising functions, such as predicting a patient’s chronological age and sex,1 likelihood of developing atrial fibrillation,2 and underlying cardiac function.3 With new smartphone-based electrodes and the potential to serve …

The accurate differentiation of wide complex tachycardias (WCTs) into ventricular tachycardia (VT) or supraventricular wide complex tachycardia (SWCT) remains problematic despite numerous manually-operated electrocardiogram (ECG) interpretation methods. We sought to create a new WCT differentiation method that could be automatically implemented by computerized ECG interpretation (CEI) software.In a two-part study, we developed and validated a logistic regression model (i.e. WCT Formula) that utilizes computerized measurements and computations derived from patients' paired WCT and subsequent baseline ECGs. In Part 1, a derivation cohort of paired WCT and baseline ECGs was examined to identify independent VT predictors to be incorporated into the WCT Formula. In Part 2, a separate validation cohort of paired WCT and baseline ECGs was used to prospectively evaluate the WCT Formula's diagnostic performance.The derivation cohort was comprised of 317 paired WCT (157 VT, 160 SWCT) and baseline ECGs. A logistic regression model (i.e. WCT Formula) incorporating WCT QRS duration (ms) (p 0.001), frontal percent amplitude change (%) (p 0.001), and horizontal percent amplitude change (%) (p 0.001) yielded effective WCT differentiation (AUC of 0.96). The validation cohort consisted of 284 paired WCT (116 VT, 168 SWCT) and baseline ECGs. The WCT Formula achieved favorable accuracy (91.5%) with strong sensitivity (89.7%) and specificity (92.9%) for VT.The WCT Formula is an example of how contemporary CEI software could be used to successfully differentiate WCTs. The incorporation of similar automated methods into CEI software may improve clinicians' ability to accurately distinguish VT and SWCT.

Background An artificial intelligence-augmented electrocardiogram (AI-ECG) can identify left ventricular systolic dysfunction (LVSD). We examined the accuracy of AI ECG for identification of LVSD (defined as LVEF ≤40% by transthoracic echocardiogram [TTE]) in cardiac intensive care unit (CICU) patients. Method We included unique Mayo Clinic CICU patients admitted from 2007 to 2018 who underwent AI-ECG and TTE within 7 days, at least one of which was during hospitalization. Discrimination of the AI-ECG for LVSD was determined using receiver-operator characteristic curve (AUC) values. Results We included 5680 patients with a mean age of 68 ± 15 years (37% females). Acute coronary syndrome (ACS) was present in 55%. LVSD was present in 34% of patients (mean LVEF 48 ± 16%). The AI-ECG had an AUC of 0.83 (95% confidence interval 0.82–0.84) for discrimination of LVSD. Using the optimal cut-off, the AI-ECG had 73%, specificity 78%, negative predictive value 85% and overall accuracy 76% for LVSD. AUC values were higher for patients aged Conclusions The AI-ECG algorithm had very good discrimination for LVSD in this critically-ill CICU cohort with a high prevalence of LVSD. Performance was better in younger male patients and those without ACS, highlighting those CICU patients in whom screening for LVSD using AI ECG may be more effective. The AI-ECG might potentially be useful for identification of LVSD in resource-limited settings when TTE is unavailable.

The presence of left ventricular systolic dysfunction (LVSD) alters clinical management and prognosis in most acute and chronic cardiovascular conditions. While transthoracic echocardiography (TTE) remains the most common diagnostic tool to screen for LVSD, it is operator-dependent, time-consuming, effort-intensive, and relatively expensive. Recent work has demonstrated the ability of an artificial intelligence-augment ECG (AI-ECG) model to accurately predict LVSD in critical intensive care unit (CICU) patients. We demonstrate that the AI-ECG algorithm can maintain its performance in these patients with and without AF despite their clinical differences. An AI-ECG algorithm can serve as a non-invasive, inexpensive, and rapid screening tool for early detection of LVSD in resource-limited settings, and potentially expedite clinical decision making and guideline-directed therapies in the acute care setting.

Objective To validate an artificial intelligence–augmented electrocardiogram (AI-ECG) algorithm for the detection of preclinical left ventricular systolic dysfunction (LVSD) in a large community-based cohort. Methods We identified a randomly selected community-based cohort of 2041 subjects age 45 years or older in Olmsted County, Minnesota. All participants underwent a study echocardiogram and ECG. We first assessed the performance of the AI-ECG to identify LVSD (ejection fraction ≤40%). After excluding participants with clinical heart failure, we further assessed the AI-ECG to detect preclinical LVSD among all patients (n=1996) and in a high-risk subgroup (n=1348). Next we modelled an imputed screening program for preclinical LVSD detection where a positive AI-ECG triggered an echocardiogram. Finally, we assessed the ability of the AI-ECG to predict future LVSD. Participants were enrolled between January 1, 1997, and September 30, 2000; and LVSD surveillance was performed for 10 years after enrollment. Results For detection of LVSD in the total population (prevalence, 2.0%), the area under the receiver operating curve for AI-ECG was 0.97 (sensitivity, 90%; specificity, 92%); in the high-risk subgroup (prevalence 2.7%), the area under the curve was 0.97 (sensitivity, 92%; specificity, 93%). In an imputed screening program, identification of one preclinical LSVD case would require 88.3 AI-ECGs and 8.7 echocardiograms in the total population and 65.7 AI-ECGs and 5.5 echocardiograms in the high-risk subgroup. The unadjusted hazard ratio for a positive AI-ECG for incident LVSD over 10 years was 2.31 (95% CI, 1.32 to 4.05; P=.004). Conclusion Artificial intelligence–augmented ECG can identify preclinical LVSD in the community and warrants further study as a screening tool for preclinical LVSD.

IMPORTANCE: Outcomes of postoperative atrial fibrillation (AF) after noncardiac surgery are not well defined. OBJECTIVE: To determine the association of new-onset postoperative AF vs no AF after noncardiac surgery with risk of nonfatal and fatal outcomes. DESIGN, SETTING, AND PARTICIPANTS: Retrospective cohort study in Olmsted County, Minnesota, involving 550 patients who had their first-ever documented AF within 30 days after undergoing a noncardiac surgery (postoperative AF) between 2000 and 2013. Of these patients, 452 were matched 1:1 on age, sex, year of surgery, and type of surgery to patients with noncardiac surgery who were not diagnosed with AF within 30 days following the surgery (no AF). The last date of follow-up was December 31, 2018. EXPOSURES: Postoperative AF vs no AF after noncardiac surgery. MAIN OUTCOMES AND MEASURES: The primary outcome was ischemic stroke or transient ischemic attack (TIA). Secondary outcomes included subsequent documented AF, all-cause mortality, and cardiovascular mortality. RESULTS: The median age of the 452 matched patients was 75 years (IQR, 67-82 years) and 51.8% of patients were men. Patients with postoperative AF had significantly higher CHA(2)DS(2)-VASc scores than those in the no AF group (median, 4 [IQR, 2-5] vs 3 [IQR, 2-5]; P

Aims An artificial intelligence-augmented electrocardiogram (AI-ECG) algorithm can identify left ventricular systolic dysfunction (LVSD). We sought to determine whether this AI-ECG algorithm could stratify mortality risk in cardiac intensive care unit (CICU) patients, independent of the presence of LVSD by transthoracic echocardiography (TTE). Methods and results We included 11 266 unique Mayo Clinic CICU patients admitted from 2007 to 2018 who underwent AI-ECG after CICU admission. Left ventricular ejection fraction (LVEF) data were extracted for patients with a TTE during hospitalization. Hospital mortality was analysed using multivariable logistic regression. Mean age was 68 ± 15 years, including 37% females. Higher AI-ECG probability of LVSD remained associated with higher hospital mortality [adjusted odds ratio (OR) 1.05 per 0.1 higher, 95% confidence interval (CI) 1.02–1.08, P = 0.003] after adjustment for LVEF, which itself was inversely related with the risk of hospital mortality (adjusted OR 0.96 per 5% higher, 95% CI 0.93–0.99, P = 0.02). Patients with available LVEF data (n = 8242) were divided based on the presence of predicted (by AI-ECG) vs. observed (by TTE) LVSD (defined as LVEF ≤ 35%), using TTE as the gold standard. A stepwise increase in hospital mortality was observed for patients with a true negative, false positive, false negative, and true positive AI-ECG. Conclusion The AI-ECG prediction of LVSD is associated with hospital mortality in CICU patients, affording risk stratification in addition to that provided by echocardiographic LVEF. Our results emphasize the prognostic value of electrocardiographic patterns reflecting underlying myocardial disease that are recognized by the AI-ECG.