Noseworthy, Peter A.

Introduction: Cardiotoxicity is a serious side effect of anthracycline treatment, most commonly manifesting as a reduction in left ventricular ejection fraction (LVEF) on cardiac imaging. Cost-effective alternatives to cardiac imaging are currently not available. Artificial intelligence (AI) models have been developed to detect a reduced LVEF from 12-lead electrocardiograms (ECGs) in the general population. Hypothesis: AI-ECG model can detect a reduced LVEF after anthracycline therapy (i.e. cardiotoxicity). Methods: We included an unbiased oncological population of 989 female breast cancer patients receiving (neo)adjuvant anthracycline chemotherapy. Average follow-up time was 9.83±4.2 years. Patients with incomplete transthoracic echocardiography (TTE) data, HER-2-directed therapy, significant comorbidities, upfront metastatic disease, second primary malignancy or pre-existing cardiovascular disease were excluded from the analyses. Patients with LVEF decline for reasons other than anthracycline-induced cardiotoxicity were also excluded. Primary readout was the diagnostic performance of AI-ECG by area under the curve (AUC) for various levels of LVEF <50%. Results: Using 1,877 ECGs from 703 unique patients, the AI-ECG model detected an LVEF <50% and ≤35% after anthracycline therapy with an AUC of 0.93 and 0.94, respectively. Conclusions: These data support the use of AI-ECG for cardiomyopathy (cardiotoxicity) screening after anthracycline-based chemotherapy. This technology could serve as a gatekeeper to more costly testing and could enable patients to monitor themselves over long periods of time.

Introduction: Biologic sex and hormonal concentrations shape ECG parameters due to sex hormone effects on cardiac function. AI-enabled ECGs have previously been shown to accurately predict patient sex in adults and correlate with sex hormone levels. Aims: We aimed to test the ability of AI-enabled ECGs to predict pediatric patient sex and explore the influence of pubertal development. Methods: Two AI-enabled ECG models were created using a convolutional neural network trained on pediatric 10-second, 12-lead surface ECGs. The first model was trained de novo using pediatric data. The second model used transfer learning from a previously validated adult data-derived algorithm. We analyzed the first ECG from 89,063 pediatric patients (aged <19 years) recorded from 1988-2022, and divided the cohort into training, validation, and testing datasets. Subgroup analysis was performed on prepubertal (0-7 years), pubertal (8-14 years), and post-pubertal (15-18 years) patients. Results: The cohort consisted of 46.6% males, with 21,434 prepubertal, 26,300 pubertal, and 41,329 post-pubertal children. No significant performance difference was observed between the two models. Both models demonstrated 81% accuracy and an overall AUC of 0.91 in the testing cohorts, with high discriminatory ability in post-pubertal teenagers (AUC = 0.98). (Figure 1) Conclusions: AI-ECG predicts pediatric patient sex with varying performance across pubertal stages. The highest discriminatory ability is observed post-puberty, decreasing in pubertal and prepubertal children. The results suggest hormonal and physiological changes during puberty may influence cardiac electrophysiology measurably. More research is required to interpret CNN-predicted sex discordance with actual sex and its implications for future cardiovascular risk.

Introduction: Over 100 FDA-approved medications, electrolyte perturbations, and many disease states can prolong the QT interval in up to 10% of patients. In contrast, approximately 1 in 2,000 people have congenital long QT syndrome (LQTS) hallmarked by pathological QT prolongation secondary to LQTS-causative mutations. Hypothesis: an artificial intelligence (AI) deep neural network (DNN) analysis of the 12-lead ECG can distinguish patients with LQTS from those with acquired QT prolongation. Methods: The study cohort included 1599 patients with genetically confirmed LQTS and over 2.5 million controls from Mayo Clinic’s ECG data vault. Every patient/control with ≥ 1 ECG above age- and sex- specific 99 th percentile values for QTc [> 460 ms for all patients (male/female) < 13 years of age, or > 470 ms for men and > 480 ms for women above this age] was included. An AI-DNN involving a multi-layer convolutional neural network was developed. To simulate screening conditions, patients were matched at a ratio of 1:2,000 (incidence of LQTS) or 1:200 (balance of LQTS vs acquired QT prolongation in a tertiary referral center). Results: Among the 1,599 patients with LQTS, 808 (> 50%) had ≥ 1 ECG with QTc above the aforementioned QTc thresholds (2,987 ECGs) compared to 361,069/2.5M controls (14% of Mayo Clinic patients getting an ECG, 989,313 ECGs). Following age- and sex- matching and splitting, the model successfully distinguished LQTS from those with acquired QT prolongation at 1:2,000 matching with an AUC of 0.937 (accuracy 89%, sensitivity 81%, specificity 90%, PPV 0.05, NPV 0.99). Furthermore, when matching at a rate that genetically-mediated QT prolongation would be encountered in clinic (1:200), the model still successfully separated the two groups (AUC 0.912, accuracy 88%, sensitivity 78%, specificity 89%, PPV 0.1, NPV 0.99). Conclusion: For patients with a QTc exceeding its 99 th percentile values seen in health, this novel AI-DNN 12-lead ECG distinguishes abnormal QT prolongation stemming from LQTS versus acquired QT prolongation with high performance characteristics (AUC > 0.93). Even when scaled to referral center and LQTS incidence ratios, a negative AI-DNN signal rules out the presence of a LQTS disease-causative mutation with 99% negative predictive value.

Introduction: Artificial Intelligence-enabled electrocardiogram (AI-ECG) can estimate the probability of having atrial fibrillation (AFib) while in sinus rhythm. Recurrent stroke in subjects without known AFib may be due to undiagnosed AFib. We evaluated the association between AI-ECG AFib and recurrent ischemic stroke and with incident AFib Methods: Consecutive adults admitted to a Mayo Clinic or Mayo Clinic Health System hospital or to Olmsted Community Hospital for ischemic stroke between January,1,2000 and June,30,2022 were identified using the Rochester Epidemiology Project. Recurrent ischemic strokes were identified after reviewing medical records and imaging studies. We excluded those with known AFib or without ECGs within 3 years prior to the first ischemic stroke. The AI-ECG network was previously developed using 649,931 ECGs from > 180,000 subjects. The primary endpoint was recurrent ischemic stroke; secondary endpoint was incident AFib. Cox model adjusted for age, sex, and CHA2DS2-VASc2 score variables. Results: We included 4,816 subjects, mean age 70±15 yr, 54% male, 92% white, median CHA2DS2-VASc2 score 4 [3-5], median follow-up 3 [1-7] yr. 280 subjects (6%) had a second stroke and 366 (8%) were diagnosed with incident AFib over follow-up. Those with a positive AI-ECG AFib had an increased risk for recurrent ischemic stroke(HR 1.54, 95% CI 1.21-1.96, P<0.001 Figure A) This association remained significant after adjustment for CHA2DS2-VASc2 score(HR 1.37 95% CI 1.07-1.76, P=0.01). These associations were not affected by anticoagulation use over follow-up. AI-ECG AFib was also associated with incident AFib(HR 2.42 95% CI 1.96-2.98, P<0.001 Figure B) Conclusions: AI-ECG AFib predicts recurrent ischemic stroke in the community, possibly reflecting undiagnosed AFib that can be detected by AI-ECG, as it also predicts incident AFib. These results underscore the potential utility of AI-ECG for risk stratification of patients with ischemic stroke.

Introduction: Recently, an artificial intelligence (AI) algorithm was validated for identifying ECG signatures of atrial fibrillation (AF) risk during normal sinus rhythm. Traditionally, socioeconomically disadvantaged populations are less likely to receive novel or guideline-recommended treatments, and have high chronic disease burden, including cardiovascular diseases. There have also been concerns about new technologies creating a digital divide, worsening existing health disparities. Hypothesis: An AI algorithm will detect AF risk unequally across patients with different levels of social determinants of health (SDOH). Methods: The initial prospective, non-randomized, interventional study leveraged EHR and digital technologies to prospectively enroll 1004 patients with a broad range of AI-ECG risks of AF, who received continuous cardiac rhythm monitoring for up to 30 days. The Area Deprivation Index (ADI) was used as a composite measure of SDOH which is comprised of indicators spanning four domains: income, education, employment, and house quality. 904 intervention patients linked to the ADI data were matched to 904 real-world control patients derived from eligible but unenrolled patients. Those with ADI under 33% were defined as having better SODH; and patients with ADI above 33% were defined as having worse SODH. Results: Median age was 74 years and 38% were women. After matching, the intervention and control arms were balanced in all baseline characteristics, including HF, HTN, diabetes, stroke, CAD and ADI. A hazard ratio of 3.11 (P<0.001) was computed when comparing intervention to control for primary AF diagnosis outcome. In patients with worse SDOH, the intervention increased AF detection from 2.6% to 8.8% (HR 3.63 [2.09, 6.32]); in the better SDOH, the intervention increased AF detection from 3.9% to 9.3% (2.41 [1.23, 4.74]). Conclusions: An AI-guided AF screening program increased the detection of AF in both patients with better or worse SDOH. The current study validates the use of AI in historically disadvantaged populations displaying the possibility for broad implementation with decreased possibility of perpetuating disparities.

Introduction: Accurate pre-procedure localization of the premature ventricular contractions (PVCs) is critical in preparing for the ablation. So far, no tools exist for artificial intelligence guided PVC-localization. Hypothesis: Trained deep learning model will be able to predict the site of origin (SOO) of PVCs using 12 lead electrocardiogram (ECG). Methods: We analyzed 707 ECG-ablation pairs from 2403 patients who had at least one ECG flagged for PVCs in the 6 months prior to their procedure. First, we used a cohort of 100,000 ECGs without PVCs and 10,000 ECGs with PVCs to train a convolutional neural network (CNN) to isolate the ECG segments with PVCs in them from a 12-lead ECG (Figure 1). We then trained two models, one utilizing a 10-second 12-lead ECG, and the other with just the isolated PVC beats as input. The models were trained using the Keras framework with TensorFlow (Google). Results: The mean age of the patients in the cohort was 61.2 ± 15.0 years. 66.3 percent of patients underwent left ventricle ablation, 54.6 percent had outflow ablation, and 55.3 percent had ablation of sites with leftward axis (septal location for midline and left ventricle PVCs). The model trained on 10-second ECGs yielded validation and test AUCs of 0.941 and 0.931 for outflow, 0.898 and 0.891 for ventricle, and 0.863 and 0.846 for leftward axis (Figure 1A). The model trained on isolated segments containing PVC beats yielded validation and test AUCs of 0.966 and 0.957 for outflow, 0.879 and 0.907 for ventricle, and 0.846 and 0.829 for SOO for leftward axis (Figure 1B). Conclusions: We have trained an accurate convolutional neural network that can predict SOO using the surface ECG. Further fine-tuning would be needed to refine the model and develop prediction of specific sites.

Background: The impact of computer ECG interpretation (CEI) on medical professionals’ performance is understudied. This study aims to assess the interpretation proficiency of diverse medical professionals with and without access to CEI reports. Methods: Medical professionals from diverse backgrounds interpreted 60 12-lead ECGs with urgent and non-urgent findings. The interpretation process involved two interpretation phases: (i) 30 ECGs with clinical statements and (ii) the same 30 ECGs and clinical statements in random order along with a CEI report. Diagnostic performance was evaluated based on interpretation accuracy, time per ECG, and self-reported confidence (rated 0 [not confident], 1 [somewhat confident], or 2 [confident]). Results: Among 892 participants, there were 44 (4.9%) primary care physicians, 123 (13.8%) cardiology fellows-in-training, 259 (29.0%) resident physicians, 137 (15.4%) medical students, 56 (6.3%) advanced practice providers, 82 (9.2%) nurses, and 191 (21.4%) allied health professionals. The inclusion of the CEI significantly improved interpretation accuracy by 15.1% (95% CI, 14.3 to 16.0; P<0.001), reduced interpretation time by 52 seconds (95% CI, -56 to -48; P<0.001), and increased confidence by 0.06 (95% CI, 0.03 to 0.09; P=0.003) (Table 1) . Conclusions: CEI integration improves ECG interpretation accuracy, efficiency, and confidence across medical professionals. Nevertheless, even with CEI, significant gaps in ECG interpretation proficiency remain.

Background: Accurate ECG interpretation is vital, but variations in skills exist among healthcare professionals. This study aims to identify factors contributing to ECG interpretation proficiency. Methods: Survey data and ECG test scores from participants in the EDUCATE Trial were analyzed. The dependent variable was the test score for interpreting 30 12-lead ECGs. Independent variables included non-modifiable factors (physician status, clinical experience, patient care impact) and modifiable factors (weekly interpretations, training hours, expert supervision frequency). Bivariate and multivariate analyses generated the Comprehensive Model (all factors) and Actionable Model (modifiable factors only). Results: Among 1206 participants, there were 72 (6.0%) primary care physicians, 146 (12.1%) cardiology fellows-in-training, 353 (29.3%) resident physicians, 182 (15.1%) medical students, 84 (7.0%) advanced practice providers, 120 (9.9%) nurses, and 249 (20.7%) allied health professionals. Physicians accounted for 571 (47.3%) of participants, while 453 (37.6%) were non-physicians. Bivariate analysis showed associations between test scores and multiple variables (Table 1) . In the Comprehensive Model, scores were independently associated with weekly interpretations (9.9 score increase; 95% CI 7.9-11.8; P<0.001), physician status (9.0 score increase; 95% CI 7.2-10.8; P<0.001), and training hours (5.7 score increase; 95% CI 3.7-7.6; P<0.001). In the Actionable Model, scores were independently associated with weekly interpretations (12.0 score increase; 95% CI, 10.0-14.0; P<0.001) and training hours (4.7 score increase; 95% CI 2.6-6.7; P<0.001). The Comprehensive and Actionable Models accounted for 18.7% and 12.3% of the variance in test scores, respectively. Conclusions: Being a physician is a non-modifiable predictor, while training and regular practice are modifiable predictors of ECG interpretation performance.

Background: Gaps in ECG interpretation competency among medical professionals exist, with a need for practical, evidence-based, and accessible learning solutions. We conducted an international, prospective, randomized controlled trial to assess the effectiveness of web-based, self-directed ECG learning. Methods: A total of 1206 diverse medical learners and professionals underwent an initial test, followed by random assignment to one of four groups: (i) online question-bank (questions), (ii) online lectures (lectures), (iii) online, question-bank and lectures (hybrid), or (iv) no resources (control). After 4 months, a post-test was administered to evaluate the overall change in performance. Results: Of all participants, 863 (72%) completed the trial. After the 4-month follow-up, all three online, self-directed intervention groups (questions, lectures, and hybrid) showed significant improvement in overall performance (P<0.001), while the control group did not (P=0.544). The questions, lectures, and hybrid interventions demonstrated score improvements of +11.4% (95% CI, 9.1-13.7; P<0.001), +9.8% (95% CI, 7.8-11.9; P<0.001), and +11.0% (95% CI, 9.2-12.9; P<0.001) respectively, compared to +0.8% (95% CI, -1.2-2.8; P=0.544) for the control group. These improvements were consistent across medical professional groups (Figure 1) . Conclusions: Web-based, self-directed learning resources effectively improved ECG interpretation proficiency for diverse medical learners and professionals.

Background: ECG interpretation is crucial in medical practice, but professionals struggle with achieving and maintaining competency. Identifying proficiency gaps aids in designing educational interventions. Methods: Medical professionals from various disciplines interpreted 30 12-lead ECGs containing commonly taught urgent and non-urgent findings. Performance metrics evaluated were overall adjusted score (% of correctly identified findings using a point-value score based on clinical relevance), unadjusted score (% of correctly identified findings), interpretation time per ECG, and self-reported confidence (rated on an ordinal scale of 0 [not confident], 1 [somewhat confident], or 2 [confident]). Results: Among 1206 participants, there were 72 (6%) primary care physicians (PCPs), 146 (12%) cardiology fellows-in-training (FIT), 353 (29%) resident physicians, 182 (15%) medical students, 84 (7%) advanced practice providers (APPs), 120 (10%) nurses, 249 (21%) allied health professionals, 571 (47%) physicians, and 453 (38%) non-physicians. Participants had a mean adjusted score of 46.9% (± 15.9%), unadjusted score of 56.4% (± 17.2%), interpretation time of 142 seconds (± 67 seconds), and confidence of 0.83 (± 0.53) (Table 1) . Performance varied across groups; cardiology FIT had superior performance in all metrics. Physicians generally outperformed non-physicians, with higher overall adjusted score (52% vs. 43%; p<0.01), unadjusted score (62% vs. 52%; p<0.01), and confidence (0.91 vs. 0.80; p<0.01). Unadjusted score for PCPs was higher than nurses and APPs (58% vs. 47% and 51%; p<0.01) but lower than resident physicians (58% vs. 60%; p<0.01). Allied health professionals outperformed nurses and APPs and closely matched resident physicians and PCPs. Conclusions: Significant gaps in ECG interpretation proficiency exist, emphasizing the need for comprehensive, scalable, and accessible educational tools.