Friedman, Paul A.

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.

Introduction: OAC are recommended for AF patients with CHA 2 DS 2 -VASc ≥2 in men or ≥3 in women (high-risk group), may be considered in patients with CHA 2 DS 2 -VASc 1 in men or 2 in women (medium-risk group), and are reasonable to omit in patients with CHA 2 DS 2 -VASc 0 in men or 1 in women (low-risk group). Furthermore, NOACs are recommended over warfarin in most AF patients. This study aimed to investigate AF stroke prevention treatment patterns in patients managed in routine practice, in particular, the under-use of OAC in the high-risk group and over-use in the low-risk group. Methods: Adult patients with AF were identified using de-identified claims for commercial and Medicare Advantage enrollees in the OptumLabs Data Warehouse. Prescription fills were assessed within 90 days of a patient’s AF encounter between 1/1/2016-12/31/2020. Patients with other indications for OAC, such as VTE, recent joint replacement, prior mechanical or bioprosthetic valve replacement, rheumatic mitral stenosis, and patients who underwent LAAO were excluded. Results: Among the 339,197 AF patients, 4.4%, 8.0%, and 87.6% were in the low-, medium-, and high-risk groups, respectively. The mean age was 51.2 ±10.5 yr, 59.9 ±9.4 yr, and 75.1 ±8.8 yr. In the low-risk group, 29.6% were treated with OAC, whereas in the high-risk group, 40.3% were not treated with any antithrombotic therapy and 7.5% used thienopyridine only. Although 71% of patients on OAC were on a NOAC, the proportion of patients on NOAC decreased from 91% in the low-risk group to 69% in the high-risk group. Conclusions: There are potentially both under-use of guideline-recommended stroke prevention therapies in the high-risk patients and over-use in the low-risk group. Because patients at a high risk of stroke are also at a high risk of major and intracranial bleeding who might benefit from NOACs, the decreased use of NOAC in high-risk patients might highlight the need for future quality improvement efforts.

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.

AbstractIntroductionThe extravascular implantable cardioverter‐defibrillator (EV ICD) system with substernal lead placement is a novel nontransvenous alternative to current commercially available ICD systems. The EV ICD provides defibrillation and pacing therapies without the potential long‐term complications of endovascular lead placement but requires a new procedure for implantation with a safety profile under evaluation.MethodsThis paper summarizes the development of the EV ICD, including the preclinical and clinical evaluations that have contributed to the system and procedural refinements to date.ResultsExtensive preclinical research evaluations and four human clinical studies with >140 combined acute and chronic implants have enabled the development and refinement of the EV ICD system, currently in worldwide pivotal study.ConclusionThe EV ICD may represent a clinically valuable solution in protecting patients from sudden cardiac death while avoiding the long‐term consequences of transvenous hardware. The EV ICD offers advantages over transvenous and subcutaneous systems by avoiding placement in the heart and vasculature; relative to subcutaneous systems, EV ICD requires less energy for defibrillation, enabling a smaller device, and provides pacing features such as antitachycardia and asystole pacing in a single system.

Abstract Digital technology is now an integral part of medicine. Tools for detecting, screening, diagnosis, and monitoring health-related parameters have improved patient care and enabled individuals to identify issues leading to better management of their own health. Wearable technologies have integrated sensors and can measure physical activity, heart rate and rhythm, and glucose and electrolytes. For individuals at risk, wearables or other devices may be useful for early detection of atrial fibrillation or sub-clinical states of cardiovascular disease, disease management of cardiovascular diseases such as hypertension and heart failure, and lifestyle modification. Health data are available from a multitude of sources, namely clinical, laboratory and imaging data, genetic profiles, wearables, implantable devices, patient-generated measurements, and social and environmental data. Artificial intelligence is needed to efficiently extract value from this constantly increasing volume and variety of data and to help in its interpretation. Indeed, it is not the acquisition of digital information, but rather the smart handling and analysis that is challenging. There are multiple stakeholder groups involved in the development and effective implementation of digital tools. While the needs of these groups may vary, they also have many commonalities, including the following: a desire for data privacy and security; the need for understandable, trustworthy, and transparent systems; standardized processes for regulatory and reimbursement assessments; and better ways of rapidly assessing value.

Background: Whether a significant proportion of cryptogenic stroke (CS) is caused by under-detected paroxysmal atrial fibrillation (PAF) is not known. Prolonged ambulatory cardiac monitoring may detect episodes of PAF in patients with stroke of unknown cause (cryptogenic stroke, CS). However, it is unclear whether PAF is more common in patients wtih CS compared with patients with stroke of known cause (SKC). We performed a case control study to compare the rates of detection of PAF in CS vs SKC using prolonged ambulatory cardiac rhythm monitoring. Methods and Results: We prospectively enrolled 132 patients within 3 months of a stroke (66 with CS and 66 with SKC) to undergo 3-week ambulatory cardiac rhythm monitoring using the CardioNet MCOT system. Stroke group was assigned by consensus between two vascular neurologists upon enrollment based on the Causative Classification of Stroke system. Primary endpoint was detection of PAF of any duration independently confirmed by two cardiologists blinded to the stroke group. The groups were well balanced except that patients with CS tended to be older and to have less hypertension and diabetes. Four patients (2 in each group) were excluded because of insufficient stroke evaluation or early discontinuation of monitoring. Episodes of PAF were detected in 16/64 (25%) patients with CS and 9/64 (14%) patients with SKC (p=0.12). Only 5 patients had episodes of PAF lasting > 30 seconds (3 with CS and 2 with SKC). Six of the 9 patients from the SKC group with PAF had small subcortical infarctions; the other 3 had cortical strokes ascribed to artery-to-artery embolism (2 with complex aortic plaques, 1 with severe vertebrobasilar stenosis). In patients under age 65, episodes of PAF were more common in the CS group (22% vs 3; p=0.07) while in patients age 65 or older the rates of detection were very similar (29% in CS vs 28% in SKC; p=0.9). Conclusions: Very short episodes of PAF are relatively common in patients with CS and with SKC, and their pathogenic significance is unclear. However, considering only patients under 65, a greater proportion of cryptogenic stroke patients had PAF, suggesting it might be pathogenic.

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.