Lopez‐Jimenez, Francisco

Abstract Aims We aim to determine if our previously validated, diagnostic artificial intelligence (AI) electrocardiogram (ECG) model is prognostic for survival among patients with cardiac amyloidosis (CA). Methods A total of 2533 patients with CA (1834 with light chain amyloidosis (AL), 530 with wild-type transthyretin amyloid protein (ATTRwt) and 169 with hereditary transthyretin amyloid (ATTRv)] were included. An amyloid AI ECG (A2E) score was calculated for each patient reflecting the likelihood of CA. CA stage was calculated using the European modification of the Mayo 2004 criteria for AL and Mayo stage for transthyretin amyloid (ATTR). Risk of death was modelled using Cox proportional hazards, and Kaplan–Meier was used to estimate survival. Results Median age of the cohort was 67 [inter-quartile ratio (IQR) 59, 74], and 71.6% were male. The median overall survival for the cohort was 35.6 months [95% confidence interval (CI) 32.3, 39.5]. For AL, ATTRwt and ATTRv, respectively, median survival was 22.9 (95% CI 19.2, 28.2), 47.2 (95% CI 43.4, 52.3) and 61.4 (95% CI 48.7, 75.9) months. On univariate analysis, an increasing A2E score was associated with more than a two-fold risk of all-cause death. On multivariable analysis, the A2E score retained its importance with a risk ratio of 2.0 (95% CI 1.58, 2.55) in the AL group and 2.7 (95% CI 1.81, 4.24) in the ATTR group. Conclusions Among patients with AL and ATTR amyloidosis, the A2E model helps to stratify risk of CA and adds another dimension of prognostication.

Introduction: LMNA encodes the nuclear envelope proteins lamin A/C that are involved in ageing processes. Mutations in LMNA cause a spectrum of phenotypes which include muscular dystrophy, arrhythmogenic dilated cardiomyopathy, peripheral neuropathy, progeroid syndrome and overlap syndrome. Early diagnosis is crucial to prevent sudden cardiac death. We hypothesized that LMNA mutations result in an ECG biological age older than chronological age. Methods: In this study, we used AI-enabled ECG network to investigate standard digital 12-lead ECGs in genetically characterized LMNA patients. Results: We identified 33 LMNA patients with 331, 12-lead ECG available for analysis. Median age at symptoms onset was 23.5 (range: <1 to 61 years;15 females). Mean follow up time was 86 months (range: <1 to 367 months). Symptoms at onset included muscle weakness (n=10) or cardiac symptoms (n=18) and asymptomatic (n=5). We included a total of 1532 age sex matched controls. We found significant differences in positive age-gap (biologically older than chronological age) comparing LMNA patients (median of 17.5) versus controls (4.9 years; p<0.001, Figure 1 ). AI-ECG age with 10 years or higher age-gap was observed in 73% of LMNA patients compared to 27% in the controls (p<0.001). Consecutive serial analysis for all ECG’s in the study versus predicted age showed faster aging when comparing the rates of age-gap overtime in the LMNA group compared to controls (p<0.0001, Figure 2 ). Moreover, the subset analysis of 23 ECG in the 5 asymptomatic patients versus controls also showed significantly higher AI-ECG age-gap (p=0.004) Conclusions: An AI-ECG algorithm to detect biological age effectively demonstrates accelerated aging in patients with LMNA mutations related to physiological aging. Our findings further validate the role of AI-ECG to detect accelerated aging, expanding previous studies demonstrating higher mortality among individuals with in increased positive age-gap.

Background: Atrial septal defects (ASD) and ventricular septal defects (VSD) are among the most common forms of congenital heart disease (CHD). Early detection and intervention for these defects are crucial to prevent complications. Given advancements in AI technology, the development of AI-enabled ECG models for detecting these defects is of significant interest. Aims: This study aimed to create AI models using pediatric ECG data for the detection of ASD, VSD, and a combined model detecting either ASD or VSD. Methods: We analyzed a dataset of 7,795 pediatric patients from Mayo Clinic who had undergone echocardiography between 2002 and 2022, with corresponding 10-second, 12-lead surface ECGs taken within 14 days of echocardiography. This dataset included 259 patients with ASDs and 139 patients with VSDs (single or multiple). The control group was comprised of 7,397 patients without significant or complex CHD. For cases and controls, we included patients with all forms of electrocardiographic abnormalities and those with valvular lesions who had less than moderate stenosis or regurgitation. The dataset was divided into training, validation, and testing subsets to develop convolutional neural network (CNN) models for ASD, VSD, and either ASD or VSD detection. Results: Our ASD and VSD detection models achieved test AUCs of 0.82 (95% CI 0.76, 0.88) and 0.80 (95% CI 0.70, 0.90), respectively. Meanwhile, a combined model that detected either ASD or VSD demonstrated a test AUC of 0.81 (95% CI, 0.76, 0.86), sensitivity of 0.73, specificity of 0.76, PPV of 0.14, and NPV of 0.98 (Figure 1). Conclusions: AI-enabled ECG models demonstrate promising performance in detecting ASD and VSD in pediatric patients. A combined model that detects either ASD or VSD also shows robust results. Future research should focus on multi-center validation of these models, refining their diagnostic capacities, and investigating their potential for early intervention in CHDs.

Background: Our team has previously developed convolutional neural networks (CNNs) to estimate age and sex from a 10-second, 12-lead ECG as indicators of patient wellness. Here, we develop an additional wellness network to estimate body mass index (BMI) from the ECG input signal. Aims: To evaluate the performance of neural networks trained to classify and directly estimate BMI. Methods: We identified all adult patients in the Mayo Clinic system who had a 10-second, 12-lead ECG within 15 days of a BMI measurement. Of the&nbsp;174,863 patients in the cohort, 2,895 were underweight (BMI < 18.5), 42,387 were of normal weight (BMI 18.5-24.9), and 57,939 were overweight only (BMI 25.0-29.9). Among patients categorized as obese, 39,788 had class I obesity (BMI 30.0-34.9), 18,978 had class II obesity (BMI 35.0-39.9), and 12,876 had class III obesity (BMI ≥ 40.0). The cohort was split into training, validation, and testing datasets in an 8:1:1 ratio to develop networks for BMI classification and a direct&nbsp;estimation of BMI. Results: In detecting overweight in the testing set, the model achieved an AUC of 0.86 (95% CI 0.85, 0.87). In detecting class I, class II, and class III obesity, the model yielded AUCs of 0.84 (95% CI 0.83, 0.85), 0.84 (95% CI 0.83, 0.85), and 0.85 (95% CI 0.85, 0.86), respectively. The model to estimate BMI achieved a mean absolute error of 3.70. Conclusions: AI-enabled ECGs demonstrate efficient detection of overweight patients and all classes of obesity. Further research is needed to determine if discrepancies between the traditionally measured BMI and the AI-ECG BMI reflect the presence or lack of metabolic abnormalities.

Background: Diagnosis of heart failure with preserved ejection fraction (HFpEF) is challenging due to non-diagnostic imaging outputs and discordant clinical features. Using only a single videoclip from a standard transthoracic echocardiogram (TTE), we developed an artificial intelligence (AI) model to differentiate patients with HFpEF from those without HFpEF. In a separate test population, we assessed the model’s ability to predict cardiac mortality. Methods: A 3-dimensional convolutional neural network was developed and trained on apical 4-chamber videoclips to classify patients with HFpEF (cases) versus without HFpEF (controls). Overall and cardiac mortality were obtained from the National Death Index. Results: The model was independently tested in 646 cases and 638 controls from 8 centers in 4 states. Sensitivity (87.8%; 84.5-90.9%) and specificity (81.9%; 78.2-85.6%) were high and sustained in various subgroups, including increased left atrial volume index, average E/e’ ≥15, and pulmonary artery systolic pressure >35 mm Hg. During follow-up (median [IQR] 3.4 [1.7-6.5] years), 540 patients died. There were 135 cardiac deaths attributable to heart failure (47%), coronary artery disease (41%), valve disease (4%), arrhythmia (4%), and others (5%). Compared to a negative output, all-cause mortality was higher in patients with a positive (HR 2.9 [2.4-3.5]) or uncertain output (HR 1.8 [1.2-2.5]), and cardiac mortality (Figure) was also higher in patients with a positive (HR 7.7 [4.5-13.3]) or uncertain output (HR 3.4 [1.4-8.1]). Cardiac mortality differences according to AI model prediction remained after age adjustment (positive: HR 5.9 [3.3-10.4], p<0.001; uncertain: HR 2.8 [1.2-6.8], p=0.02). Conclusion: A novel AI model to detect HFpEF based on a single routinely acquired TTE videoclip also identifies those at increased risk of cardiac mortality.

Background: The body Mass Index (BMI) is commonly used in clinical practice to screen for obesity and resulting cardiometabolic conditions. Nonetheless, BMI has limited utility as it cannot differentiate body fat (BF). Hypothesis: We tested the hypothesis that BF content measured by air displacement plethysmography (Bod-Pod®) had a stronger association with prevalent hypertension (HTN), diabetes mellitus (DM) and dyslipidemia (DLP) when compared to BMI. Methods: We performed a community-based cross-sectional study on adults attending an employee wellness center from January 2007-December 2011 who had had a body composition assessment with Bod-Pod®. We excluded subjects with history of myocardial infarction, coronary artery disease, congestive heart failure, stroke at baseline. The prevalence of HTN, DM and DLP was assessed across quartiles of BF% and BMI categories. Their association with BF% and BMI was evaluated using linear regression models that adjusted for age, sex, and white race. Results: We included 3,052 individuals; 68 % were women, and the mean age ± SD was 42.09±12.8, BMI was 27.9±6.2; BF% 31.88±10.69, 892 (29.2%) were obese by BMI. Cardiometabolic conditions were prevalent in 496 (16.2%) with HTN, 378 (12.4%) with DM and 743 (24.4%) with DLP. While the prevalence of DM, HTN and DLP increased across BF% quartiles (all p for linearity>0.01), this was not always the case across BMI categories (p for linearity<0.05 for HTN and DLP, and 0.04 for DM) see Figure A . Elevated BF %, better identified individuals with HTN (AUC 0.766 vs 0.625; p<0.001), DM (AUC 0.643 vs. 0.568; p<0.001), DLP (AUC 0.758 vs. 0.593; p<0.001). Conclusion: BF content is better associated with a higher prevalence of HTN, DM, and DLP. Highlighting the role of body composition assessment in primary prevention. Dyslipidemia.

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.

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.