Using Artificial Intelligence to Predict Heart Failure Risk from Single-lead Electrocardiographic Signals: A Multinational Assessment.

Importance: Despite the availability of disease-modifying therapies, scalable strategies for heart failure (HF) risk stratification remain elusive. Portable devices capable of recording single-lead electrocardiograms (ECGs) can enable large-scale community-based risk assessment. Objective: To evaluate an artificial intelligence (AI) algorithm to predict HF risk from noisy single-lead ECGs. Design: Multicohort study. Setting: Retrospective cohort of individuals with outpatient ECGs in the integrated Yale New Haven Health System (YNHHS) and prospective population-based cohorts of UK Biobank (UKB) and Brazilian Longitudinal Study of Adult Health (ELSA-Brasil). Participants: Individuals without HF at baseline. Exposures: AI-ECG-defined risk of left ventricular systolic dysfunction (LVSD). Main Outcomes and Measures: Among individuals with ECGs, we isolated lead I ECGs and deployed a noise-adapted AI-ECG model trained to identify LVSD. We evaluated the association of the model probability with new-onset HF, defined as the first HF hospitalization. We compared the discrimination of AI-ECG against the pooled cohort equations to prevent HF (PCP-HF) score for new-onset HF using Harrel's C-statistic, integrated discrimination improvement (IDI), and net reclassification improvement (NRI). Results: There were 194,340 YNHHS patients (age 56 years [IQR, 41-69], 112,082 women [58%]), 42,741 UKB participants (65 years [59-71], 21,795 women [52%]), and 13,454 ELSA-Brasil participants (56 years [41-69], 7,348 women [55%]) with baseline ECGs. A total of 3,929 developed HF in YNHHS over 4.5 years (2.6-6.6), 46 in UKB over 3.1 years (2.1-4.5), and 31 in ELSA-Brasil over 4.2 years (3.7-4.5). A positive AI-ECG screen was associated with a 3- to 7-fold higher risk for HF, and each 0.1 increment in the model probability portended a 27-65% higher hazard across cohorts, independent of age, sex, comorbidities, and competing risk of death. AI-ECG's discrimination for new-onset HF was 0.725 in YNHHS, 0.792 in UKB, and 0.833 in ELSA-Brasil. Across cohorts, incorporating AI-ECG predictions in addition to PCP-HF resulted in improved Harrel's C-statistic (Δ=0.112-0.114), with an IDI of 0.078-0.238 and an NRI of 20.1%-48.8% for AI-ECG vs. PCP-HF. Conclusions and Relevance: Across multinational cohorts, a noise-adapted AI model with lead I ECGs as the sole input defined HF risk, representing a scalable portable and wearable device-based HF risk-stratification strategy.

Scalable Risk Stratification for Heart Failure Using Artificial Intelligence applied to 12-lead Electrocardiographic Images: A Multinational Study.

Background: Current risk stratification strategies for heart failure (HF) risk require either specific blood-based biomarkers or comprehensive clinical evaluation. In this study, we evaluated the use of artificial intelligence (AI) applied to images of electrocardiograms (ECGs) to predict HF risk. Methods: Across multinational longitudinal cohorts in the integrated Yale New Haven Health System (YNHHS) and in population-based UK Biobank (UKB) and Brazilian Longitudinal Study of Adult Health (ELSA-Brasil), we identified individuals without HF at baseline. Incident HF was defined based on the first occurrence of an HF hospitalization. We evaluated an AI-ECG model that defines the cross-sectional probability of left ventricular dysfunction from a single image of a 12-lead ECG and its association with incident HF. We accounted for the competing risk of death using the Fine-Gray subdistribution model and evaluated the discrimination using Harrel's c-statistic. The pooled cohort equations to prevent HF (PCP-HF) were used as a comparator for estimating incident HF risk. Results: Among 231,285 individuals at YNHHS, 4472 had a primary HF hospitalization over 4.5 years (IQR 2.5-6.6) of follow-up. In UKB and ELSA-Brasil, among 42,741 and 13,454 people, 46 and 31 developed HF over a follow-up of 3.1 (2.1-4.5) and 4.2 (3.7-4.5) years, respectively. A positive AI-ECG screen portended a 4-fold higher risk of incident HF among YNHHS patients (age-, sex-adjusted HR [aHR] 3.88 [95% CI, 3.63-4.14]). In UKB and ELSA-Brasil, a positive-screen ECG portended 13- and 24-fold higher hazard of incident HF, respectively (aHR: UKBB, 12.85 [6.87-24.02]; ELSA-Brasil, 23.50 [11.09-49.81]). The association was consistent after accounting for comorbidities and the competing risk of death. Higher model output probabilities were progressively associated with a higher risk for HF. The model's discrimination for incident HF was 0.718 in YNHHS, 0.769 in UKB, and 0.810 in ELSA-Brasil. Across cohorts, incorporating model probability with PCP-HF yielded a significant improvement in discrimination over PCP-HF alone. Conclusions: An AI model applied to images of 12-lead ECGs can identify those at elevated risk of HF across multinational cohorts. As a digital biomarker of HF risk that requires just an ECG image, this AI-ECG approach can enable scalable and efficient screening for HF risk.

Impact of a large-scale telemedicine network on emergency visits and hospital admissions during the coronavirus disease 2019 pandemic in Brazil: Data from the UNIMED-BH system.

INTRODUCTION: Triage by on-demand telemedicine is a strategy for healthcare surge control in the COVID-19 pandemic. We aimed to assess the impact of a large-scale COVID-19 telemedicine system on emergency department (ED) visits and all-cause and cardiovascular hospital admissions in Brazil. METHODS: From March 18, 2020-May 18, 2020 we evaluated the database of a cooperative private health insurance, with 1.28 million clients. The COVID-19 telemedicine system consisted of: a) mobile app, which redirects to teleconsultations if indicated; b) telemonitoring system, with regular phone calls to suspected/confirmed COVID-19 cases to monitor progression; c) emergency ambulance system (EAS), with internet phone triage and counselling. ED visits and hospital admissions were recorded, with diagnoses assessed by the Diagnosis Related Groups method. COVID-19 diagnosis and deaths were identified from the patients' registries, and outcomes assessed until June 1st. RESULTS: In 60 days, 24,354 patients accessed one of the telemedicine systems. The most frequently utilized was telemonitoring (16,717, 69%), followed by teleconsultation (13,357, 55%) and EAS (687, 3%). The rates of ED and hospital admissions were: telemonitoring 19.7% (3,296) and 4.7% (782); teleconsultation 17.3% (2,313) and 2.4% (318) and EAS: 55.9% (384) and 56.5% (388) patients. At total 4.1% (1,010) had hospital admissions, 36% (363) with respiratory diseases (44 requiring mechanical ventilation) and 4.4% (44) with cardiovascular diagnoses. Overall, 277 (1.1%) patients had confirmed COVID-19 diagnosis, and 160 (0.7%) died, 9 with COVID-19. CONCLUSION: Telemedicine resulted in low rates of ED visits and hospital admissions, suggesting positive impacts on healthcare utilization. Cardiovascular admissions were remarkably rare.

Comparison of cardiovascular health profiles across population surveys from five high- to low-income countries.

Aims: With the greatest burden of cardiovascular disease morbidity and mortality increasingly observed in lower-income countries least prepared for this epidemic, focus is widening from risk factor management alone to primordial prevention to maintain high levels of cardiovascular health (CVH) across the life course. To facilitate this, the American Heart Association (AHA) developed CVH scoring guidelines to evaluate and track CVH. We aimed to compare the prevalence and trajectories of high CVH across the life course using nationally representative adult CVH data from five diverse high- to low-income countries. Methods: Surveys with CVH variables (physical activity, cigarette smoking, body mass, blood pressure, blood glucose, and total cholesterol levels) were identified in Ethiopia, Bangladesh, Brazil, England, and the United States (US). Participants were included if they were 18-69y, not pregnant, and had data for these CVH metrics. Comparable data were harmonized and each of the CVH metrics was scored using AHA guidelines as high (2), moderate (1), or low (0) to create total CVH scores with higher scores representing better CVH. High CVH prevalence by age was compared creating country CVH trajectories. Results: The analysis included 28,092 adults (Ethiopia n=7686, 55.2% male; Bangladesh n=6731, 48.4% male; Brazil n=7241, 47.9 % male; England n=2691, 49.5% male, and the US n=3743, 50.3% male). As country income level increased, prevalence of high CVH decreased (>90% in Ethiopia, >68% in Bangladesh and under 65% in the remaining countries). This pattern remained using either five or all six CVH metrics and following exclusion of underweight participants. While a decline in CVH with age was observed for all countries, higher income countries showed lower prevalence of high CVH already by age 18y. Excess body weight appeared the main driver of poor CVH in higher income countries, while current smoking was highest in Bangladesh. Conclusion: Harmonization of nationally representative survey data on CVH trajectories with age in 5 highly diverse countries supports our hypothesis that CVH decline with age may be universal. Interventions to promote and preserve high CVH throughout the life course are needed in all populations, tailored to country-specific time courses of the decline. In countries where CVH remains relatively high, protection of whole societies from risk factor epidemics may still be feasible.

Reduced protective effect of Plasmodium berghei immunization by concurrent Schistosoma mansoni infection

Studies on concomitant schistosomiasis and human and experimental malaria have shown a variation in the immunospecific response, as well as an increase in the severity of both parasitoses. In the present study, a murine co-infection model was used to determine the effects of a co-infection with Schistosoma mansoni and Plasmodium berghei on the protective immunity acquired by repeated malarial infections and subsequent curative treatment with chloroquine. Our results have demonstrated that, compared to an infection with P. berghei only, the co-infection increases the malarial parasitaemia and decreases the survival rate. Indeed, mice that were immunized by infection and treatment with drug displayed no mortality whereas co-infected mice showed a reduced protective efficacy of immunization against P. berghei (mortality > 60 percent). Interestingly, this high mortality rate was not associated with high levels of parasitaemia. Our findings support the idea of a suppressive effect of a Schistosoma co-infection on the anti-malarial protection by immunization. This result reveals a possible drawback of the development of anti-malarial vaccines, especially considering the wide endemic areas for both parasitoses.