Artificial Intelligence-Enabled ECG to Identify Silent Atrial Fibrillation in Embolic Stroke of Unknown Source

OBJECTIVES

Embolic strokes of unknown source (ESUS) are common and often suspected to be caused by unrecognized paroxysmal atrial fibrillation (AF). An AI-enabled ECG (AI-ECG) during sinus rhythm has been shown to identify patients with unrecognized AF. We pursued this study to determine if the AI-ECG model differentiates between patients with ESUS and those with known causes of stroke, and to evaluate whether the AF prediction by AI-ECG among patients with ESUS was associated with the results of prolonged ambulatory cardiac rhythm monitoring.

MATERIALS AND METHODS

We reviewed consecutive patients admitted with acute ischemic stroke to a comprehensive stroke center between January 2018 and August 2019 and employed the TOAST classification to categorize the mechanisms of ischemia. Use and results of ambulatory cardiac rhythm monitoring after discharge were gathered. We ran the AI-ECG model to obtain AF probabilities from all ECGs acquired during the hospitalization and compared those probabilities in patients with ESUS versus those with known stroke causes (apart from AF), and between patients with and without AF detected by ambulatory cardiac rhythm monitoring.

RESULTS

The study cohort had 930 patients, including 263 patients (28.3%) with known AF or AF diagnosed during the index hospitalization and 265 cases (28.5%) categorized as ESUS. Ambulatory cardiac rhythm monitoring was performed in 226 (85.3%) patients with ESUS. AF probability by AI-ECG was not associated with ESUS. However, among patients with ESUS, the probability of AF by AI-ECG was associated with a higher likelihood of AF detection by ambulatory monitoring (P = 0.004). A probability of AF by AI-ECG greater than 0.20 was associated with AF detection by ambulatory cardiac rhythm monitoring with an OR of 5.47 (95% CI 1.51-22.51).

CONCLUSIONS

AI-ECG may help guide the use of prolonged ambulatory cardiac rhythm monitoring in patients with ESUS to identify those who might benefit from anticoagulation.

The effect of cardiac rhythm on artificial intelligence-enabled ECG evaluation of left ventricular ejection fraction prediction in cardiac intensive care unit patients

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.

Conceptual and literature basis for wide complex tachycardia and baseline ECG comparison

Accurate wide QRS complex tachycardia (WCT) differentiation into either ventricular tachycardia or supraventricular wide complex tachycardia using 12‑lead electrocardiogram (ECG) interpretation is essential for diagnostic, therapeutic, and prognostic reasons. There is an ever-expanding variety of WCT differentiation methods and criteria available to clinicians. However, only a few make use of the diagnostic value of comparing the ECG during WCT to that of the patient's baseline ECG. Therefore, we highlight the conceptual rationale and scientific literature supporting the diagnostic value of WCT and baseline ECG comparison.

Left ventricular systolic dysfunction identification using artificial intelligence-augmented electrocardiogram in cardiac intensive care unit patients

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 <70 years (0.85 versus 0.80), males (0.84 versus 0.79), patients without ACS (0.86 versus 0.80), and patients who did not undergo revascularization (0.84 versus 0.80).

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.

Mortality risk stratification using artificial intelligence-augmented electrocardiogram in cardiac intensive care unit patients

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.

Differentiating wide complex tachycardias: A historical perspective

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.

Association of New-Onset Atrial Fibrillation After Noncardiac Surgery With Subsequent Stroke and Transient Ischemic Attack

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 CHA2DS2-VASc scores than those in the no AF group (median, 4 [IQR, 2-5] vs 3 [IQR, 2-5]; P < .001). Over a median follow-up of 5.4 years (IQR, 1.4-9.2 years), there were 71 ischemic strokes or TIAs, 266 subsequent documented AF episodes, and 571 deaths, of which 172 were cardiovascular related. Patients with postoperative AF exhibited a statistically significantly higher risk of ischemic stroke or TIA (incidence rate, 18.9 vs 10.0 per 1000 person-years; absolute risk difference [RD] at 5 years, 4.7%; 95% CI, 1.0%-8.4%; HR, 2.69; 95% CI, 1.35-5.37) compared with those with no AF. Patients with postoperative AF had statistically significantly higher risks of subsequent documented AF (incidence rate 136.4 vs 21.6 per 1000 person-years; absolute RD at 5 years, 39.3%; 95% CI, 33.6%-45.0%; HR, 7.94; 95% CI, 4.85-12.98), and all-cause death (incidence rate, 133.2 vs 86.8 per 1000 person-years; absolute RD at 5 years, 9.4%; 95% CI, 4.9%-13.7%; HR, 1.66; 95% CI, 1.32-2.09). No significant difference in the risk of cardiovascular death was observed for patients with and without postoperative AF (incidence rate, 42.5 vs 25.0 per 1000 person-years; absolute RD at 5 years, 6.2%; 95% CI, 2.2%-10.4%; HR, 1.51; 95% CI, 0.97-2.34).

CONCLUSIONS AND RELEVANCE

Among patients undergoing noncardiac surgery, new-onset postoperative AF compared with no AF was associated with a significant increased risk of stroke or TIA. However, the implications of these findings for the management of postoperative AF, such as the need for anticoagulation therapy, require investigation in randomized trials.

A comprehensive artificial intelligence–enabled electrocardiogram interpretation program

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.

Artificial Intelligence-Enabled ECG Algorithm to Identify Patients With Left Ventricular Systolic Dysfunction Presenting to the Emergency Department With Dyspnea

BACKGROUND

Identification of systolic heart failure among patients presenting to the emergency department (ED) with acute dyspnea is challenging. The reasons for dyspnea are often multifactorial. A focused physical evaluation and diagnostic testing can lack sensitivity and specificity. The objective of this study was to assess the accuracy of an artificial intelligence-enabled ECG to identify patients presenting with dyspnea who have left ventricular systolic dysfunction (LVSD).

METHODS

We retrospectively applied a validated artificial intelligence-enabled ECG algorithm for the identification of LVSD (defined as LV ejection fraction ≤35%) to a cohort of patients aged ≥18 years who were evaluated in the ED at a Mayo Clinic site with dyspnea. Patients were included if they had at least one standard 12-lead ECG acquired on the date of the ED visit and an echocardiogram performed within 30 days of presentation. Patients with prior LVSD were excluded. We assessed the model performance using area under the receiver operating characteristic curve, accuracy, sensitivity, and specificity.

RESULTS

A total of 1606 patients were included. Median time from ECG to echocardiogram was 1 day (Q1: 1, Q3: 2). The artificial intelligence-enabled ECG algorithm identified LVSD with an area under the receiver operating characteristic curve of 0.89 (95% CI, 0.86-0.91) and accuracy of 85.9%. Sensitivity, specificity, negative predictive value, and positive predictive value were 74%, 87%, 97%, and 40%, respectively. To identify an ejection fraction <50%, the area under the receiver operating characteristic curve, accuracy, sensitivity, and specificity were 0.85 (95% CI, 0.83-0.88), 86%, 63%, and 91%, respectively. NT-proBNP (N-terminal pro-B-type natriuretic peptide) alone at a cutoff of >800 identified LVSD with an area under the receiver operating characteristic curve of 0.80 (95% CI, 0.76-0.84).

CONCLUSIONS

The ECG is an inexpensive, ubiquitous, painless test which can be quickly obtained in the ED. It effectively identifies LVSD in selected patients presenting to the ED with dyspnea when analyzed with artificial intelligence and outperforms NT-proBNP. Graphic Abstract: A graphic abstract is available for this article.

Wide Complex Tachycardia Differentiation: A Reappraisal of the State-of-the-Art

The primary goal of the initial ECG evaluation of every wide complex tachycardia is to determine whether the tachyarrhythmia has a ventricular or supraventricular origin. The answer to this question drives immediate patient care decisions, ensuing clinical workup, and long‐term management strategies. Thus, the importance of arriving at the correct diagnosis cannot be understated and has naturally spurred rigorous research, which has brought forth an ever‐expanding abundance of manually applied and automated methods to differentiate wide complex tachycardias. In this review, we provide an in‐depth analysis of traditional and more contemporary methods to differentiate ventricular tachycardia and supraventricular wide complex tachycardia. In doing so, we: (1) review hallmark wide complex tachycardia differentiation criteria, (2) examine the conceptual and structural design of standard wide complex tachycardia differentiation methods, (3) discuss practical limitations of manually applied ECG interpretation approaches, and (4) highlight recently formulated methods designed to differentiate ventricular tachycardia and supraventricular wide complex tachycardia automatically.

The ventricular tachycardia prediction model: Derivation and validation data

In a recent publication [1], we introduced and described a novel means (i.e. VT Prediction Model) to correctly categorize wide complex tachycardias (WCTs) into ventricular tachycardia (VT) and supraventricular wide complex tachycardia (SWCT) using routine measurements shown on electrocardiogram (ECG) paper recordings. In this article, we summarize data components relating to the derivation and validation of the VT Prediction Model.

Immediate and long-term results of percutaneous mitral commissurotomy: up to 15 years

PURPOSE

To evaluate immediate and long-term clinical results of percutaneous mitral commissurotomy (PMC) in patients with severe mitral stenosis.

METHODS

In a retrospective study, data were included from 317 patients over 18 years of age (mean age 45) who had been treated for mitral stenosis between January 1993 and March 2015 with PMC using the Inoue balloon technique. Immediate results: Valvular function improved as evidenced by an increase in mitral valve area from 1.01 ± 0.24 cm² to 2 ± 0.31 cm² (P < 0.001) and a decrease in mean mitral gradient from 13.64 ± 6.03 mm Hg to 5.40 ± 2.49 mm Hg. Long-term follow-up: At 5-15 years (mean 10.2 years, Inter-quartile range 8.25), 105 (33.1%) of the 317 patients were available for follow-up, 95 living patients and 10 deceased. Of the deceased, average time from PMC to death was 8 years. Results were strongly significant showing that age at the time of PMC and surface area before the procedure were the best predictors of survival at 15 years follow-up, showing significance values of P = 0.022 and P = 0.001, respectively.

CONCLUSIONS

PMC using the Inoue balloon technique improves morbidity and long-term mortality rates in patients with severe mitral stenosis. Lower Wilkins score and NYHA class at baseline were not found to be significant predictors of mortality in older patients (age > 45). Overall, 65 (61.9%) had survived at 5-15 years follow-up without further cardiac intervention.

Diffuse ST-segment depression despite prior coronary bypass grafting: An electrocardiographic-angiographic correlation

The standard 12‑lead electrocardiogram (ECG) has become a mainstay diagnostic tool in patients suspected to have myocardial ischemia. The identification of hallmark electrocardiographic abnormalities, such as ST-segment deviation or serial T wave changes, not only helps identify the presence of myocardial ischemia but also may help localize myocardial territories with an ongoing injury. Widespread ST-segment depression is commonly attributed to diffuse subendocardial ischemia precipitated by severe multivessel or left main coronary artery disease. However, among patients with prior coronary revascularization, clear electrocardiographic-angiographic relationships responsible for widespread ST-segment depressions have not been well defined. We report a case in which diffuse ST-segment depression emerged from a patient with prior coronary artery bypass grafting. In this report, we examine the patient's presenting ECG pattern as to (1) establish causal inferences which align with the distribution of myocardial ischemia supported by angiography and (2) provide an accompanying analysis of the relevant scientific literature.

Reversible atrioventricular block and the importance of close follow-up: Two cases of Lyme carditis

Lyme carditis is an uncommon presentation of the early-disseminated phase of Lyme disease, although it is recognizable and often curable. Because of its rarity, diagnosing Lyme carditis requires a high level of suspicion, especially when young patients in certain endemic areas present with symptoms of bradycardia and/or evidence of high-degree atrioventricular (AV) block. Temporary cardiac pacing along with antibiotic therapy has been shown to aid in the management of Lyme carditis until symptoms and conduction blocks have resolved. Herein, we report two cases of Lyme carditis-induced AV block that were successfully managed and reversed with temporary cardiac pacing and antibiotics. In order to monitor for any late sequela that may arise, we also recommend close follow-up for patients treated for Lyme carditis with high-degree AV block. <Learning objective: Lyme carditis manifests as a conduction system disease, predominantly involving the atrioventricular (AV) node. It can present without the classical signs of Lyme disease. It is critical to have a high suspicion of Lyme carditis in patients who present with symptoms of bradycardia or high-degree AV block in high prevalence areas. Early initiation of antibiotics, along with external temporary pacing, dramatically improves mortality rates. Close follow-up is important in patients that develop high-degree AV block.>.