Citations

Background: Patients with peripheral artery disease (PAD) are at increased risk for major adverse limb and cardiac events including mortality. Developing screening tools capable of accurate PAD identification is a necessary first step for strategies of adverse outcome prevention. This study aimed to determine whether machine analysis of a resting Doppler waveform using deep neural networks can accurately identify patients with PAD. Methods: Consecutive patients (4/8/2015 – 12/31/2020) undergoing rest and postexercise ankle–brachial index (ABI) testing were included. Patients were randomly allocated to training, validation, and testing subsets (70%/15%/15%). Deep neural networks were trained on resting posterior tibial arterial Doppler waveforms to predict normal (> 0.9) or PAD (⩽ 0.9) using rest and postexercise ABI. A separate dataset of 151 patients who underwent testing during a period after the model had been created and validated (1/1/2021 – 3/31/2021) was used for secondary validation. Area under the receiver operating characteristic curves (AUC) were constructed to evaluate test performance. Results: Among 11,748 total patients, 3432 patients met study criteria: 1941 with PAD (mean age 69 ± 12 years) and 1491 without PAD (64 ± 14 years). The predictive model with highest performance identified PAD with an AUC 0.94 (CI = 0.92–0.96), sensitivity 0.83, specificity 0.88, accuracy 0.85, and positive predictive value (PPV) 0.90. Results were similar for the validation dataset: AUC 0.94 (CI = 0.91–0.98), sensitivity 0.91, specificity 0.85, accuracy 0.89, and PPV 0.89 (postexercise ABI comparison). Conclusion: An artificial intelligence-enabled analysis of a resting Doppler arterial waveform permits identification of PAD at a clinically relevant performance level.

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.

Introduction: Transthyretin cardiac amyloidosis (TTR-CA) can cause heart failure with preserved EF (HFpEF). We previously reported a clinical/echo-based score (TCAS) and defined a cut-off that predicted risk of TTR-CA in HFpEF. Herein, we assess the comparative performance of an artificial-intelligence ECG-based screening tool (AI-ECG). Hypothesis: AI-ECG successfully identifies TTR-CA in HFpEF cohorts across a range of TTR-CA prevalence Methods: Referral HFpEF cohort was constructed from a referral population of HFpEF patients (EF ≥ 40%) undergoing 99m Tc-pyrophosphate scintigraphy (PYP) at Mayo Clinic (2013-2020, n=484, 38% with TTR-CA). Community HFpEF cohort was prospectively screened with PYP (n=275; age ≥ 60, LV wall thickness (WT) ≥ 12 mm, 4% with TTR-CA). TCAS was built using a multivariable logistic regression model and converted to a simple point score comprised of age (60-69, 70-79, ≥ 80: +2, +3, +4 points respectively), male sex (+2), relative WT > 0.57 (+2), posterior WT ≥ 12 mm (+1), EF < 60% (+1), and hypertension diagnosis (-1). TCAS was validated in the community cohort. A deep neural network trained to predict cardiac amyloidosis from a single 12-lead ECG, was applied to both referral and community cohorts. Patients were excluded if ECG was not available ≤ 12 months before PYP or if used in development of the AI-ECG. Standard ROC methods were applied. Youden’s index was used to define optimal cut-off. Results: Predictive characteristics of AI-ECG were strong and compared favorably with TCAS across a range of true TTR-CA prevalence (Table). Conclusions: Using a single ECG, AI-ECG effectively predicts TTR-CA with an excellent negative predictive value to rule out TTR-CA and a positive predictive value sufficient to warrant specific TTR-CA testing. This was particularly evident in the community. AI-ECG holds promise for simple, cost-effective global screening of at-risk populations, especially those with limited access to advanced cardiac imaging.

Background: Artificial intelligence (AI)-based analysis of the electrocardiogram (ECG) can estimate the probability of having atrial fibrillation (AF) while in sinus rhythm. We evaluated the association between the probability of AF using AI-ECG and incident ischemic stroke (I-Stroke) and cardiovascular (CV) mortality. Methods: We evaluated a community-based cohort of consecutive patients that sought primary care in Olmsted County, MN, from the years 1998 to 2000 followed-up through March 2016. Inclusion criteria were ages 40-79, an electrocardiogram within 2 years and complete CHA2DS2-VASc data. We excluded those with known atherosclerotic CV disease or AF. The AI network was developed in 180,000 patients (649,931 ECG). The primary endpoint was incident I-Stroke; secondary endpoint was I-Stroke or CV mortality; validated in duplicate. Multivariate cox models adjusted for age, sex, history of hypertension, diabetes, heart failure, and in CHA2DS2-VASc Score subgroups (categorized as low=0, moderate=1, and high risk ≥2). Results: We included 14,601 patients, mean age 53.2±13.08 (51% women, 95% whites), CHA2DS2-VASc score 1.3±1.2, median follow-up of 16.3 years, IQR 14.5-17.5, 727 (4.9%) had an I-Stroke and 1309 (8.9%) had I-Stroke or died from CV causes. When comparing the 5 th vs the 1 st quintile, those with high AI-ECG AF probability had increased risk for I-Stroke (HR 3.25, 95%CI 2.55-4.14, P-for trend <.0001 Figure-A ) and ischemic stroke or CV mortality (HR 5.73, 95%CI 4.69-6.99, P-for trend <.0001 Figure-B ). This remained significant after adjustments. Furthermore, AI-ECG AF probability was associated with I-Stroke across CHA2DS2-VASc risk levels (HR 2.43 for high, 2.33 for moderate, 1.98 for low CHA2DS2-VASc risk, all P<0.01). Conclusion: The AI-ECG AF algorithm predicts long-term I-Stroke and CV mortality and may refine CHA2DS2-VASc. These results highlight the utility of the AI enabled ECG when estimating I-Stroke or CV mortality risk.

INTRODUCTION: Cirrhosis is associated with cardiac dysfunction and distinct electrocardiogram (ECG) abnormalities. This study aimed to develop a proof-of-concept deep learning-based artificial intelligence (AI) model that could detect cirrhosis-related signals on ECG and generate an AI-Cirrhosis-ECG (ACE) score that would correlate with disease severity. METHODS: A review of Mayo Clinic's electronic health records identified 5,212 patients with advanced cirrhosis ≥18 years who underwent liver transplantation at the 3 Mayo Clinic transplant centers between 1988 and 2019. The patients were matched by age and sex in a 1:4 ratio to controls without liver disease and then divided into training, validation, and test sets using a 70%-10%-20% split. The primary outcome was the performance of the model in distinguishing patients with cirrhosis from controls using their ECGs. In addition, the association between the ACE score and the severity of patients' liver disease was assessed. RESULTS: The model's area under the curve in the test set was 0.908 with 84.9% sensitivity and 83.2% specificity, and this performance remained consistent after additional matching for medical comorbidities. Significant elevations in the ACE scores were seen with increasing model for end-stage liver disease-sodium score. Longitudinal trends in the ACE scores before and after liver transplantation mirrored the progression and resolution of liver disease. DISCUSSION: The ACE score, a deep learning model, can accurately discriminate ECGs from patients with and without cirrhosis. This novel relationship between AI-enabled ECG analysis and cirrhosis holds promise as the basis for future low-cost tools and applications in the care of patients with liver disease.

Abstract Background Cardiovascular disease (CVD) has been identified as a major threat to maternal health in the US and UK with cardiomyopathy being one of the most common acquired CVD in the pregnant and postpartum period. Diagnosing cardiomyopathy in pregnancy is challenging due to an overlap of cardiovascular symptoms with normal pregnancy symptoms. Purpose The purpose of this study was to evaluate the effectiveness of an ECG based deep learning model in identifying cardiomyopathy among pregnant and postpartum women. Methods We utilized an ECG based deep learning model to detect cardiomyopathy in a cohort of pregnant or postpartum women seen at multiple hospital sites. Model performance was evaluated using area under the 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. Results 1,807 women were included. 7%, 10% and 13% had LVEF ≤35%, &lt;45% and &lt;50% respectively. The ECG based deep learning model identified cardiomyopathy with an AUC of 0.92 for left ventricular ejection fraction (LVEF) ≤35%, 0.89 for LVEF &lt;45% and 0.87 for LVEF &lt;50%. For LVEF ≤35%, 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 and 0.72 respectively. Conclusions A deep learning model effectively identifies cardiomyopathy in pregnant or postpartum women, outperforms natriuretic peptides and traditional clinical parameters with the potential to become a powerful initial screening tool for cardiomyopathy in the obstetric care setting. Funding Acknowledgement Type of funding sources: Other. Main funding source(s): This study was made possible using resources supported by the Mayo Clinic Women's Health Research Center and the Mayo Clinic Building Interdisciplinary Research Careers in Women's Health (BIRCWH) Program funded by the National Institutes of Health (NIH), grant number K12 HD065987. The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health.

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.

Abstract Background An artificial intelligence (AI) algorithm detecting age from 12-lead ECG has been suggested to signal “physiological age” of the individual. Importantly, increased physiological age gauged by an increased difference between ECG-age and chronological age has been associated with higher risk of cardiac events in non-transplant population. Purpose We sought to investigate the validity of the AI-derived ECG-age algorithm in patients who underwent heart transplantation and its relationship to major adverse cardiovascular events (MACE). Methods A total of 489 consecutive patients who had undergone heart transplantation in our institution between 1994 and 2018 were studied. AI-ECG age was calculated by a previously-trained artificial intelligence (AI) algorithm using a 12-lead ECG per patient. ECGs used in the training process of the algorithm were excluded. The average of the ECG-ages within one year before and one year after heart transplantation was used to represent pre- and post-transplant ECG-ages. MACE was defined as any incidence of revascularization, re-transplantation, and death. Results Pre-transplant ECG-age (mean 63±10 years) correlated significantly with recipient chronological age (mean 50±13 years, r=0.57, p&lt;0.0001), but this correlation between recipient and ECG-ages was weakened after transplantation (mean post-transplant ECG age of 55±10 years, r=0.34, p&lt;0.0001). Interestingly, post-transplant ECG-age correlated significantly with donor age (mean ECG age of 55±10 years vs. mean donor age of 32±13 years, r=0.42, p&lt;0.0001). During a median (IQR) follow-up of 9 (5, 14) years, 251 patients had MACE. Mean change in ECG age after transplantation compared to before was −8.8±12.7 years. Patients who had an increase in ECG-age after compared to before transplantation showed increased risk of MACE (HR: 1.53 [1.16, 2.01], p=0.002), independent of recipient and donor ages (adjusted HR: 1.68 [1.26, 2.25], p=0.001); whereas there were no significant differences in risk of MACE in patients who were transplanted with an older donor heart (HR: 1.07 [0.77, 1.50], p=0.66). In a Kaplan Meier survival analysis, those with increased ECG-age after transplantation had significantly lower MACE-free survival compared to those with decreased ECG-age. (Log-rank P=0.002; Wilcoxon P=0.001) (Figure) Conclusion Post-transplant ECG-age correlates more faithfully with the donor's than the recipient's chronological age, suggesting that ECG-age more closely reflects cardiac age than the patient age. Furthermore, ECG-age derived cardiac aging after transplantation is associated with higher risk of MACE. Funding Acknowledgement Type of funding sources: None.