Lopez-Jimenez, Francisco

Abstract Aims Electrocardiogram (ECG)-enabled stethoscope (ECG-Scope) acquires a single-lead ECGs during cardiac auscultation and may facilitate real-time screening for pathologies not routinely identified by cardiac auscultation alone. We previously demonstrated an artificial intelligence (AI) algorithm can identify left ventricular dysfunction (LVSD) [defined as ejection fraction (EF) ≤ 40%] with an area under the curve (AUC) of 0.91 using a 12-lead ECG. Methods and results One hundred patients referred for clinically indicated echocardiography were prospectively recruited. ECG-Scope recordings with the patient supine and sitting were obtained in multiple electrode locations at the time of the echocardiogram. The AI algorithm for the detection of LVSD was retrained using single leads from ECG-12 and validated against ECG-Scope to determine accuracy for low EF detection (≤35%, <40%, or <50%). We evaluated the algorithm with respect to body position and lead location. Amongst 100 patients (aged 61.3 ± 13.8; 61% male, BMI: 30.0 ± 5.4), eight had EF≤40%, and six had EF 40–50%. The best single recording position was V2 with the patient supine [AUC: 0.88 (CI: 0.80–0.97) for EF≤35%, 0.85 (CI: 0.75–0.95) for EF≤40%, and 0.81 (CI: 0.71–0.90) for EF < 50%]. When using an AI model to select the recording automatically, AUC was 0.91 (CI: 0.84–0.97) for EF≤35%, 0.89 (CI: 0.83–0.96) for EF≤40%, and 0.84 (CI: 0.73–0.94) for EF < 50%. Conclusion An AI algorithm applied to an ECG-enabled stethoscope recording in standard auscultation positions reliably detected the presence of a low EF in this prospective study of patients referred for echocardiography. The ability to screen patients with a possible low EF during routine physical examination may facilitate rapid detection of LVSD.

Abstract Aims Some artificial intelligence models applied in medical practice require ongoing retraining, introduce unintended racial bias, or have variable performance among different subgroups of patients. We assessed the real-world performance of the artificial intelligence-enhanced electrocardiogram to detect left ventricular systolic dysfunction with respect to multiple patient and electrocardiogram variables to determine the algorithm’s long-term efficacy and potential bias in the absence of retraining. Methods and results Electrocardiograms acquired in 2019 at Mayo Clinic in Minnesota, Arizona, and Florida with an echocardiogram performed within 14 days were analyzed (n = 44 986 unique patients). The area under the curve (AUC) was calculated to evaluate performance of the algorithm among age groups, racial and ethnic groups, patient encounter location, electrocardiogram features, and over time. The artificial intelligence-enhanced electrocardiogram to detect left ventricular systolic dysfunction had an AUC of 0.903 for the total cohort. Time series analysis of the model validated its temporal stability. Areas under the curve were similar for all racial and ethnic groups (0.90–0.92) with minimal performance difference between sexes. Patients with a ‘normal sinus rhythm’ electrocardiogram (n = 37 047) exhibited an AUC of 0.91. All other electrocardiogram features had areas under the curve between 0.79 and 0.91, with the lowest performance occurring in the left bundle branch block group (0.79). Conclusion The artificial intelligence-enhanced electrocardiogram to detect left ventricular systolic dysfunction is stable over time in the absence of retraining and robust with respect to multiple variables including time, patient race, and electrocardiogram features.

Abstract Aims Artificial intelligence (AI) enabled electrocardiography (ECG) can detect latent atrial fibrillation (AF) in patients with sinus rhythm (SR). However, the change of AI-ECG probability before and after the first AF episode is not well characterized. We sought to characterize the temporal trend of AI-ECG AF probability around the first episode of AF. Methods and results We retrospectively studied adults who had at least one ECG in SR prior to an ECG that documented AF. An AI network calculated the AF probability from ECGs during SR (positive defined >8.7%, based on optimal sensitivity and specificity). The AI-ECG probability was reported prior to and after the first episode of AF and stratified by age and CHA2DS2-VASc score. Mixed effect models were used to assess the rate of change between time points. A total of 59 212 patients with 544 330 ECGs prior to AF and 413 486 ECGs after AF were included. The mean time between the first positive AI-ECG and first AF was 5.4 ± 5.7 years. The mean AI-ECG probability was 19.8% 2–5 years prior to AF, 23.6% 1–2 years prior to AF, 34.0% 0–3 months prior to AF, 40.9% 0–3 months after AF, 35.2% 1–2 years after AF, and 42.2% 2–5 years after AF (P < 0.001). The rate of increase prior to AF was higher for age >50 years CHA2DS2-VASc score ≥4. Conclusion The AI-ECG probability progressively increases with time prior to the first AF episode, transiently decreases 1–2 years following AF and continues to increase thereafter.

Background: Left atrial (LA) myopathy is common in patients with heart failure and preserved ejection fraction and leads to the development of atrial fibrillation (AF). We investigated whether the likelihood of LA remodeling, LA dysfunction, altered hemodynamics, and risk for incident AF could be identified from a single 12-lead ECG using a novel artificial intelligence (AI)-enabled ECG analysis. Methods: Patients with heart failure and preserved ejection fraction (n=613) underwent AI-enabled ECG analysis, echocardiography, and cardiac catheterization. Individuals were grouped by AI-enabled ECG probability of contemporaneous AF, taken as an indicator of underlying LA myopathy. Results: Structural heart disease was more severe in patients with higher AI-probability of AF, with more left ventricular hypertrophy, larger LA volumes, and lower LA reservoir and booster strain. Cardiac filling pressures and pulmonary artery pressures were higher in patients with higher AI-probability, while cardiac output reserve was more impaired during exercise. Among patients with sinus rhythm and no prior AF, each 10% increase in AI-probability was associated with a 31% greater risk of developing new-onset AF (hazard ratio, 1.31 [95% CI, 1.20–1.42]; P <0.001). In the population as a whole, each 10% increase in AI-probability was associated with a 12% greater risk of death (hazard ratio, 1.12 [95% CI, 1.08–1.17]; P <0.001) during long-term follow-up, which was no longer significant after adjustments for baseline characteristics. Conclusions: A novel AI-enabled score derived from a single 12-lead ECG identifies the presence of underlying LA myopathy in patients with heart failure and preserved ejection fraction as evidenced by structural, functional, and hemodynamic abnormalities, as well as long-term risk for incident AF. Further research is required to determine the role of the AI-enabled ECG in the evaluation and care of patients with heart failure and preserved ejection fraction.

Background There is wide variability in cardiac rehabilitation (CR) dose (ie, number of sessions) delivered, and no evidence‐based recommendations regarding what dose to prescribe. We aimed to test what CR dose impacts major adverse cardiovascular events (MACEs). Methods and Results This is an historical cohort study of all patients who had coronary artery disease and who initiated supervised CR between 2002 and 2012 from a single major CR center. CR dose was defined as number of visits including exercise and patient education. Follow‐up was performed using record linkage from the Rochester Epidemiology Project. MACEs included acute myocardial infarction, unstable angina, ventricular arrhythmias, stroke, revascularization, or all‐cause mortality. Dose was analyzed in several ways, including tertiles, categories, and as a continuous variable. Cox models were adjusted for factors associated with dose and MACE. The cohort consisted of 2345 patients, who attended a mean of 12.5±11.1 of 36 prescribed sessions. After a mean follow‐up of 6 years, 695 (29.65%) patients had a MACE, including 231 who died. CR dose was inversely associated with MACE (hazard ratio, 0.66 [95% CI]; 0.55–0.91) in those completing ≥20 sessions, when compared with those not exposed to formal exercise sessions (≤1 session; log‐rank P =0.007). We did not find evidence of nonlinearity ( P ≥0.050), suggesting no minimal threshold nor ceiling. Each additional session was associated with a lower rate of MACE (fully adjusted hazard ratio, 0.98 [95% CI, 0.97–0.99]). Greater session frequency was also associated with lower MACE risk (fully adjusted hazard ratio, 0.74 [95% CI, 0.58–0.94]). Conclusions CR reduces MACEs, but the benefit appears to be linear, with greater risk reduction with higher doses, and no upper threshold.

Abstract Aims Cardiovascular disease is a major threat to maternal health, with cardiomyopathy being among the most common acquired cardiovascular diseases during pregnancy and the postpartum period. The aim of our study was to evaluate the effectiveness of an electrocardiogram (ECG)-based deep learning model in identifying cardiomyopathy during pregnancy and the postpartum period. Methods and results We used an ECG-based deep learning model to detect cardiomyopathy in a cohort of women who were pregnant or in the postpartum period seen at Mayo Clinic. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity. We compared the diagnostic probabilities of the deep learning model with natriuretic peptides and a multivariable model consisting of demographic and clinical parameters. The study cohort included 1807 women; 7%, 10%, and 13% had left ventricular ejection fraction (LVEF) of 35% or less, &lt;45%, and &lt;50%, respectively. The ECG-based deep learning model identified cardiomyopathy with AUCs of 0.92 (LVEF ≤ 35%), 0.89 (LVEF &lt; 45%), and 0.87 (LVEF &lt; 50%). For LVEF of 35% or less, AUC was higher in Black (0.95) and Hispanic (0.98) women compared to White (0.91). Natriuretic peptides and the multivariable model had AUCs of 0.85 to 0.86 and 0.72, respectively. Conclusions An ECG-based deep learning model effectively identifies cardiomyopathy during pregnancy and the postpartum period and outperforms natriuretic peptides and traditional clinical parameters with the potential to become a powerful initial screening tool for cardiomyopathy in the obstetric care setting.

Abstract Aims Spectrum bias can arise when a diagnostic test is derived from study populations with different disease spectra than the target population, resulting in poor generalizability. We used a real-world artificial intelligence (AI)-derived algorithm to detect severe aortic stenosis (AS) to experimentally assess the effect of spectrum bias on test performance. Methods and results All adult patients at the Mayo Clinic between 1 January 1989 and 30 September 2019 with transthoracic echocardiograms within 180 days after electrocardiogram (ECG) were identified. Two models were developed from two distinct patient cohorts: a whole-spectrum cohort comparing severe AS to any non-severe AS and an extreme-spectrum cohort comparing severe AS to no AS at all. Model performance was assessed. Overall, 258 607 patients had valid ECG and echocardiograms pairs. The area under the receiver operator curve was 0.87 and 0.91 for the whole-spectrum and extreme-spectrum models, respectively. Sensitivity and specificity for the whole-spectrum model was 80% and 81%, respectively, while for the extreme-spectrum model it was 84% and 84%, respectively. When applying the AI-ECG derived from the extreme-spectrum cohort to patients in the whole-spectrum cohort, the sensitivity, specificity, and area under the curve dropped to 83%, 73%, and 0.86, respectively. Conclusion While the algorithm performed robustly in identifying severe AS, this study shows that limiting datasets to clearly positive or negative labels leads to overestimation of test performance when testing an AI algorithm in the setting of classifying severe AS using ECG data. While the effect of the bias may be modest in this example, clinicians should be aware of the existence of such a bias in AI-derived algorithms.

Abstract Background We have demonstrated that a neural network is able to predict a person’s age from the electrocardiogram (ECG) [artificial intelligence (AI) ECG age]. However, some discrepancies were observed between ECG-derived and chronological ages. We assessed whether the difference between AI ECG and chronological age (Age-Gap) represents biological ageing and predicts long-term outcomes. Methods and results We previously developed a convolutional neural network to predict chronological age from ECGs. In this study, we used the network to analyse standard digital 12-lead ECGs in a cohort of 25 144 subjects ≥30 years who had primary care outpatient visits from 1997 to 2003. Subjects with coronary artery disease, stroke, and atrial fibrillation were excluded. We tested whether Age-Gap was correlated with total and cardiovascular mortality. Of 25 144 subjects tested (54% females, 95% Caucasian) followed for 12.4 ± 5.3 years, the mean chronological age was 53.7 ± 11.6 years and ECG-derived age was 54.6 ± 11 years (R2 = 0.79, P &lt; 0.0001). The mean Age-Gap was small at 0.88 ± 7.4 years. Compared to those whose ECG-derived age was within 1 standard deviation (SD) of their chronological age, patients with Age-Gap ≥1 SD had higher all-cause and cardiovascular disease (CVD) mortality. Conversely, subjects whose Age-Gap was ≤1 SD had lower all-cause and CVD mortality. Results were unchanged after adjusting for CVD risk factors and other survival influencing factors. Conclusion The difference between AI ECG and chronological age is an independent predictor of all-cause and cardiovascular mortality. Discrepancies between these possibly reflect disease independent biological ageing.

Abstract Aims Early detection of aortic stenosis (AS) is becoming increasingly important with a better outcome after aortic valve replacement in asymptomatic severe AS patients and a poor outcome in moderate AS. We aimed to develop artificial intelligence-enabled electrocardiogram (AI-ECG) using a convolutional neural network to identify patients with moderate to severe AS. Methods and results Between 1989 and 2019, 258 607 adults [mean age 63 ± 16.3 years; women 122 790 (48%)] with an echocardiography and an ECG performed within 180 days were identified from the Mayo Clinic database. Moderate to severe AS by echocardiography was present in 9723 (3.7%) patients. Artificial intelligence training was performed in 129 788 (50%), validation in 25 893 (10%), and testing in 102 926 (40%) randomly selected subjects. In the test group, the AI-ECG labelled 3833 (3.7%) patients as positive with the area under the curve (AUC) of 0.85. The sensitivity, specificity, and accuracy were 78%, 74%, and 74%, respectively. The sensitivity increased and the specificity decreased as age increased. Women had lower sensitivity but higher specificity compared with men at any age groups. The model performance increased when age and sex were added to the model (AUC 0.87), which further increased to 0.90 in patients without hypertension. Patients with false-positive AI-ECGs had twice the risk for developing moderate or severe AS in 15 years compared with true negative AI-ECGs (hazard ratio 2.18, 95% confidence interval 1.90–2.50). Conclusion An AI-ECG can identify patients with moderate or severe AS and may serve as a powerful screening tool for AS in the community.