Citations

Introduction: Over 100 FDA-approved medications, electrolyte perturbations, and many disease states can prolong the QTc beyond its 99 th percentile value resulting in acquired QT prolongation. In contrast, approximately 1 in 2000 people have congenital long QT syndrome (LQTS) hallmarked by pathological QT prolongation secondary to genetic defects in the heart. Hypothesis: An artificial intelligence (AI) deep neural network (DNN) can distinguish patients with LQTS from those with acquired QT prolongation. Methods: The study cohort included all patients with LQTS evaluated in the Windland Smith Rice Genetic Heart Rhythm Clinic and controls from Mayo Clinic’s ECG data vault comprising over 2.5 million patients. For the AI-DNN model, 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 c onvolutional n eural n etwork (CNN) was developed to classify patients. LQTS patients were age- and sex- matched to controls at 1:5 ratio. Results: Among the 1,599 patients with genetically confirmed LQTS, 808 had ≥ 1 ECG with QTc above the threshold (2,987 ECGs) compared to 361,069/2.5M controls (14% of Mayo Clinic patients getting an ECG, ‘presumed negative’; 989,313 ECGs). Following age- and sex- matching and splitting, 3,309 (training), 411 (validation) and 887 (testing) control ECGs were used. This model distinguished LQTS from those with acquired QT prolongation with an AUC of 0.896 (accuracy 85%, sensitivity 77%, specificity 88%, PPV 0.58, NPV 0.94). After exclusion of patients with a wide QRS (>150 ms) or pacemaker, the model remained successful in distinguishing the two groups (AUC 0.85, accuracy 78%, sensitivity 78%, specificity 87%, PPV 59%, NPV 94%). Conclusions: For patients with a QTc exceeding its 99 th percentile values, this novel AI-DNN functions as a LQTS mutation detector being able to identify patients with abnormal QT prolongation secondary to a LQTS-causative mutation rather than acquired QT prolongation with a >50% positive predictive value. This algorithm may facilitate screening for this potentially lethal, yet highly treatable, genetic heart disease.

Introduction: Deep-learning artificial intelligence (AI) algorithms can identify hypertrophic cardiomyopathy (HCM) from the electrocardiogram (ECG). Preliminary data indicate that AI-ECG may also track treatment response in HCM patients (pts) receiving mavacamten (Mava). In this placebo-controlled analysis, we investigated the performance of AI-ECG in HCM detection and its changes during Mava treatment compared to placebo in the phase 3, EXPLORER-HCM trial. Methods: Pts with non-paced ECGs enrolled in EXPLORER-HCM, evaluating Mava over 30 weeks of treatment, were included. All pts had a 12-lead ECG pre-treatment, at each study visit, and 8 weeks after treatment end. Two independently developed AI-ECG convolutional neural network algorithms from the Mayo Clinic and the University of California, San Francisco (UCSF) were applied to all ECGs suitable for analysis. Serial AI-ECG-predicted scores, which correlate with HCM likelihood (range 0-1), were examined between Mava and placebo groups. Results: A total of 101 Mava and 110 placebo pts were included (mean age 58.6, female 40%). At baseline, the mean Mayo and UCSF AI-ECG scores for HCM were 0.82 and 0.65, with 94% and 88% of pts exceeding the respective diagnostic thresholds of 0.11 (Mayo) and 0.4 (UCSF). During 30 weeks of follow-up in the Mava group, the algorithms showed a mean AI-ECG score reduction of 0.32 (Mayo) and 0.17 (UCSF) in all pts between start and end of treatment. In comparison, AI-ECG scores decreased by 0.05 (Mayo) and increased by 0.02 (UCSF) in the placebo group (Mava vs placebo, t-test p-values <0.001 for both algorithms; Figure ) Conclusion: In the EXPLORER-HCM trial population, two independent deep-learning AI-ECG algorithms correctly identified most HCM pts and demonstrated significant reductions in predicted HCM scores after treatment with Mava when compared to placebo. This relative normalization of the ECG suggests disease-modifying properties of Mava, deserving further investigation.

Background: We developed a deep learning algorithm to predict elevated coronary artery calcium (CAC) score from 12-lead electrocardiograms (CAC- ECG). We tested the hypothesis that this CAC-ECG algorithm will independently predict long-term survival. Methods: We leveraged a historical cohort of 43,210 consecutive patients who from the years 1997-2020 underwent clinically indicated ECG-gated unenhanced chest computed tomography (CT) to identify and quantify CAC and had an ECG within 1 year of the CT. Data on cardiovascular risk (CV) factors, and to calculate the Pooled Cohort Equation (PCE) for ASCVD was collected as part of preventive cardiology or general medical evaluations. We used the oldest CAC in record and excluded those taking statins at the time of the CAC. The algorithm was trained in 60% of the cohort, and the association between CAC-ECG and survival was evaluated with multivariate cox proportional hazard models in 40% of the remaining observations. Results: Of the 17,284 evaluated patients, mean ± SD age 55.9 ± 9.9, 33% female, 3,714 (21%) had elevated CAC ≥ 300. During an average of 15±5.9 years follow-up, 848 (5%) patients died. The algorithm’s area under the receiving operating characteristics curve (ROC), sensitivity, specificity, and accuracy to detect a CAC ≥ 300 were 0.83, 0.90%, 0.56%, 0.60%. Those with elevated CAC had a nearly two-fold risk of death, a value similar to those deemed positive by the ECG-CAC algorithm ( Figure A ). Risk of death increased with CAC-ECG probability quartiles ( Figure A ). The CAC-ECG algorithm enhanced predicted capabilities of the PCE across all ASCVD risk subgroups ( Figure B ), as well as in those with no CAC and elevated CAC ( Figure C ), all p for trend <0.001. Conclusions: A deep learning-enabled CAC-ECG algorithm was independently associated with long-term survival and enhanced current risk prediction paradigms. The CAC-ECG algorithm could help identify individuals at risk in primary prevention of CV disease.

Introduction: Increasing evidence unravels the role of loneliness and social connection in cardiovascular diseases potentially mediating accelerated biological aging. The present study aims to explore the association between social connection and biological aging as determinate by artificial intelligence-enabled electrocardiography (ECG). Methods: This is an observational retrospective cohort of adults aged ≥18 seen at Mayo Clinic from 2019-2022 who completed the social determinants of health questionnaire and had a 12-lead ECG within one year of completing the questionnaire. Five questions were asked to understand each patient’s social connection . The answers were scored to assess their level of social connection from socially isolated (score of 0) to socially connected (score of 4). The biological age was predicted from ECGs using the previously developed convolutional neural network (AI-ECG age). Delta age (Δage) was defined as AI-ECG age minus chronological age, where positive values reflect an older than expected age. Results: We included 280,323 subjects (chronological age 59.7±16.4 years, 51% female). The average AI-ECG age was 59.5±13.5 year. Better social connection status correlated with lower delta age (β=-0.33 (95%CI, -0.38 and -0.28, p<0.001, adjusted to chronological age and sex). Conversely, individuals reporting the least social connection were an average of 2 years older than expected whereas those with the most social connection were 2 years younger than expected by AI-ECG (Figure 1). Conclusions: Social connection is strongly associated with slower biological aging compared to chronological aging, independent of the conventional cardiovascular risk factors. This observation underscores the need to address social connection as a healthcare determinant.

Introduction: The physiological changes associated with aging have deleterious effects on cardiovascular function. In addition, increasing evidence showed the effect of exercise on improving cardiovascular health and reducing the aging process. The present study sought to demonstrate the association between exercise and biological age, estimated by our previously reported method using artificial intelligence-enabled electrocardiography (ECG). Methods: This retrospective observational study enrolled adults aged ≥18 years who have been evaluated at Mayo Clinic between 2019-2022 and completed the exercise questionnaire. The total time spent in moderate to strenuous exercise was calculated by multiplying the number of days engaging in exercise per week by the average minutes per day. The biological age was determined by applying our previously developed convolutional neural network model on the 12-lead ECG records (AI-ECG). The ECG records were within one year of subjects’ visits (in case of multiple visits, the closest one to the questionnaire was chosen). Positive Age-Gap (AI-ECG minus chronological age) reflects a person identified as being older by AI-ECG compared to his/her chronological age. Results: A total of 268,002 subjects (51% female) were recruited (mean age 59.7±16.4 years). Of those, 25.7% were not engaged in any exercise. The median day of engaging in exercise was 3 (Interquartile range, 2,5) per week, and the average time of exercising was 31.3±30 minutes/day. Age-Gap diminished progressively with increased duration of moderate to strenuous exercise (Figure 1). Linear regression analysis revealed exercise is an independent predictor of Age-Gap, (β= -0.043, 95%CI, -0.045 and -0.041, p<0.001). Conclusions: Engaging in moderate to strenuous exercise is associated with slower biological aging relative to chronological age as determined by AI-enabled ECG.

Introduction: Recent studies have indicated high rates of future major adverse cardiovascular events in patients with Takotsubo cardiomyopathy (TTC). This study sought to evaluate the prognostic value of our institutional artificial intelligence-augmented electrocardiography (AI-ECG) algorithms in patients with TTC. Methods: This study enrolled consecutive patients in the prospective and observational Mayo Clinic Takotsubo syndrome registry. TTC was diagnosed according to the Mayo Clinic diagnostic. Our clinic’s previously developed and validated AI-ECG algorithms were used for detection of ECG-Age, probability of low ejection fraction, and probability of atrial fibrillation.Multivariable models were constructed to evaluate the association of AI-ECG and other clinical characteristics with major adverse cardiac events (MACE), defined as cardiac death, recurrence of TTC, nonfatal myocardial infarction, hospitalization for congestive heart failure, and stroke. Results: In the final analysis, 305 patients were studied over a median follow-up of 4.8 years. Patients with MACE were more likely to be older, have history of hypertension and chronic heart failure (CHF), worse renal function as well as having high-risk AI-ECG findings compared to those without. In the multivariate Cox proportional hazard analysis, the presence of 3 or 4 high-risk findings detected by AI-ECG, remained a significant predictor of MACE in the patients with TTC after adjusted by conventional risk factors (hazard ratio (HR) 2.17, 95% CI [1.33, 3.53], P=0.002; HR 2.44, 95% CI [1.38, 4.29], P=0.002, respectively). Conclusions: The combined use of developed AI-ECG algorithms derived from a single 12-lead ECG might identify ECG correlates of underlying non-transient myocardial dysfunction and detect subtle underlying patterns associated with worse outcomes in patients with TTC. This approach might be beneficial for stratifying high-risk patients with TTC.

Introduction: Prior AF screening trials demonstrated low yield, highlighting the need for more targeted approaches. An AI algorithm was developed to identify ECG signatures of AF risk during normal sinus rhythm, which has been validated in diverse external populations. Hypothesis: An AI-guided, targeted screening approach could improve the diagnosis of AF. Methods We conducted a pragmatic decentralized trial to prospectively recruit patients with stroke risk factors but no prior AF. The AI algorithm was applied to the ECGs performed in routine practice and divided patients into high- or low-risk groups. The primary endpoint was AF lasting ≥ 30 seconds on a subsequent 30-day continuous cardiac rhythm monitor. In a secondary analysis, trial participants were 1:1 propensity score-matched to real-world controls derived from the eligible but unenrolled population. Results A total of 1,003 patients from 40 U.S. states completed the study, with a mean age of 74 [SD 8.8] years. Over a mean of 22.3 days of continuous monitoring, AF was detected in 6 (1.6%) of low-risk patients and 48 (7.6%) of high-risk patients (OR 4.98 [2.11-11.75], p<0.001). Compared to usual care, AI-guided AF screening was associated with increased detection of AF (high-risk group: 4.2% vs. 11.1%, p<0.001; low-risk group: 0.9% vs. 2.4%, p=0.12) over a median follow-up of 10 months. Conclusions A prospective pragmatic study found that the AI a can risk-stratify a relatively uniform population (i.e., older adults at risk for stroke) to detect AF during short-term cardiac monitoring. Furthermore, when compared with usual care, AI-guided cardiac monitoring was associated with increased AF detection. As such, an AI-guided AF screening approach, leveraging existing EHR data and infrastructure, could be effective, patient-centered, and massively scalable, thereby reducing unnecessary health utilization and diagnosis-related anxiety (Clinicaltrials.gov: NCT04208971).

Abstract Background and purpose A heart age biomarker has been developed using deep neural networks applied to electrocardiograms. Whether this biomarker is associated with cognitive function was investigated. Methods Using 12‐lead electrocardiograms, heart age was estimated for a population‐based sample ( N = 7779, age 40–85 years, 45.3% men). Associations between heart delta age (HDA) and cognitive test scores were studied adjusted for cardiovascular risk factors. In addition, the relationship between HDA, brain delta age (BDA) and cognitive test scores was investigated in mediation analysis. Results Significant associations between HDA and the Word test, Digit Symbol Coding Test and tapping test scores were found. HDA was correlated with BDA (Pearson's r = 0.12, p = 0.0001). Moreover, 13% (95% confidence interval 3–36) of the HDA effect on the tapping test score was mediated through BDA. Discussion Heart delta age, representing the cumulative effects of life‐long exposures, was associated with brain age. HDA was associated with cognitive function that was minimally explained through BDA.

Background: We developed a deep learning algorithm that detects coronary artery calcium (CAC) score using 12-lead electrocardiograms (CAC- ECG). We tested the hypothesis that the output from the CAC-ECG algorithm would be associated with incident atherosclerotic cardiovascular disease (ASCVD) events and that the CAC- ECG would refine the AHA/ACC Pooled Cohort Equation’s (PCE) predictive capabilities. Methods: A community-based cohort of consecutive patients seeking primary care in Olmsted County, MN, between 1998-2000 with passive follow-up via record linkage. Inclusion was identical to the PCE. The original CAC-ECG was developed in 43,210 subjects yielding an AUC of 0.83. Herein, we used the CAC-ECG output to predict a high CAC (≥ 300). Primary outcome was ASCVD defined as fatal and non-fatal myocardial infarction and ischemic stroke, secondary outcome was Major Adverse Cardiovascular Events (MACE) further including PCI, CABG, and mortality. Events were validated in duplicate. Cox proportional hazard models adjusted for variables included in the PCE and were stratified to evaluate the effect of the CAC-ECG on PCE-predicted risk. Follow-up was truncated at 10 years for PCE analyses. Results: We included 24,793 subjects, mean ± SD age 53.9 ± 12.1, 52% women, 95% white. After 16.7±3.7 yrs follow-up, 2,366 (9.5%) had ASCVD and 3,401 (13.7%) had MACE. Risk of ASCVD and MACE increased with CAC-ECG probability quintiles, independent of risk factors, p for trend <0.001 ( Fig. A-B ). The CAC-ECG enhanced the predicted capabilities of the PCE across all ASCVD risk groups ( Fig. C ). Net reclassification improved 13.7% with comparable C-statistic from 0.77 vs. 0.78 for PCE and CAC-ECG. Conclusions: CAC-ECG was associated with ASCVD and MACE and improved PCE predicted risk. The CAC-ECG algorithm could identify individuals at risk in primary prevention; Unlike the PCE, the CAC-ECG can be applied without chart review or performing a computer tomography and may be reliably used retrospectively in cohorts with digitally stored ECGs.

Background. Mortality risk assessment before kidney transplantation (KT) is imperfect. An emerging risk factor for death in nontransplant populations is physiological age as determined by the application of artificial intelligence to the electrocardiogram (ECG). The aim of this study was to examine the relationship between ECG age and KT waitlist mortality. Methods. We applied a previously developed convolutional neural network to the ECGs of KT candidates evaluated 2014 to 2019 to determine ECG age. We used a Cox proportional hazard model to examine whether ECG age was associated with waitlist mortality. Results. Of the 2183 patients evaluated, 59.1% were male, 81.4% were white, and 11.4% died during follow-up. Mean ECG age was 59.0 ± 12.0 y and mean chronological age at ECG was 53.3 ± 13.6 y. After adjusting for chronological age, comorbidities, and other characteristics associated with mortality, each increase in ECG age of >10 y than the average ECG age for patients of a similar chronological age was associated with an increase in mortality risk (hazard ratio 3.59 per 10-y increase; 95% confidence interval, 2.06-5.72; P < 0.0001). Conclusions. ECG age is a risk factor for KT waitlist mortality. Determining ECG age through artificial intelligence may help guide risk-benefit assessment when evaluating candidates for KT.