Prevalence and diagnostic significance of novel 12-lead ECG patterns following COVID-19 infection in elite soccer players

Background: Identification of athletes with cardiac inflammation following COVID-19 can prevent exercise fatalities. The efficacy of pre and post COVID-19 infection electrocardiograms (ECGs) for detecting athletes with myopericarditis has never been reported. We aimed to assess the prevalence and diagnostic significance of novel 12-lead ECG patterns following COVID-19 infection in elite soccer players. Method(s): We conducted a multicentre study over a 2-year period involving 5 centres and 34 clubs and compared pre COVID and post COVID ECG changes in 455 consecutive athletes. ECGs were reported in accordance with the International recommendations for ECG interpretation in athletes. The following patterns were considered abnormal if they were not detected on the pre COVID-19 infection ECG: (a) biphasic T-waves;(b) reduction in T-wave amplitude by 50% in contiguous leads;(c) ST-segment depression;(d) J-point and ST-segment elevation >0.2 mV in the precordial leads and >0.1 mV in the limb leads;(e) tall T-waves >=1.0 mV (f) low QRS-amplitude in >3 limb leads and (g) complete right bundle branch block. Athletes exhibiting novel ECG changes underwent cardiovascular magnetic resonance (CMR) scans. One club mandated CMR scans for all 28 (6%) athletes, despite the absence of cardiac symptoms or ECG changes. Result(s): Athletes were aged 22+/-5 years (89% male and 57% white). 65 (14%) athletes reported cardiac symptoms. The mean duration of illness was 3+/-4 days. The post COVID ECG was performed 14+/-16 days following a positive PCR. 440 (97%) athletes had an unchanged post COVID- 19 ECG. Of these, 3 (0.6%) had cardiac symptoms and CMRs resulted in a diagnosis of pericarditis. 15 (3%) athletes demonstrated novel ECG changes following COVID-19 infection. Among athletes who demonstrated novel ECG changes, 10 (67%) reported cardiac symptoms. 13 (87%) athletes with novel ECG changes were diagnosed with inflammatory cardiac sequelae;pericarditis (n=6), healed myocarditis (n=3), definitive myocarditis (n=2), and possible/probable myocarditis (n=2). The overall prevalence of inflammatory cardiac sequelae based on novel ECG changes was 2.8%. None of the 28 (6%) athletes, who underwent a CMR, in the absence of cardiac symptoms or novel ECG changes revealed any abnormalities. Athletes revealing novel ECG changes, had a higher prevalence of cardiac symptoms (67% v 12% p<0.0001) and longer symptom duration (8+/-8 days v 2+/-4 days;p<0.0001) compared with athletes without novel ECG changes. Among athletes without cardiac symptoms, the additional yield of novel ECG changes to detect cardiac inflammation was 20% (n=3). Conclusion(s): 3% of elite soccer players demonstrated novel ECG changes post COVID-19 infection, of which almost 90% were diagnosed with cardiac inflammation during subsequent investigation. Most athletes with novel ECG changes exhibited cardiac symptoms. Novel ECGs changes contributed to a diagnosis of cardiac inflammation in 20% of athletes without cardiac symptoms.

Data-driven Simulation and Optimization for Covid-19 Exit Strategies

The rapid spread of the Coronavirus SARS-2 is a major challenge that led almost all governments worldwide to take drastic measures to respond to the tragedy. Chief among those measures is the massive lockdown of entire countries and cities, which beyond its global economic impact has created some deep social and psychological tensions within populations. While the adopted mitigation measures (including the lockdown) have generally proven useful, policymakers are now facing a critical question: how and when to lift the mitigation measures? A carefully-planned exit strategy is indeed necessary to recover from the pandemic without risking a new outbreak. Classically, exit strategies rely on mathematical modeling to predict the effect of public health interventions. Such models are unfortunately known to be sensitive to some key parameters, which are usually set based on rules-of-thumb. In this paper, we propose to augment epidemiological forecasting with actual data-driven models that will learn to fine-tune predictions for different contexts (e.g., per country). We have therefore built a pandemic simulation and forecasting toolkit that combines a deep learning estimation of the epidemiological parameters of the disease in order to predict the cases and deaths, and a genetic algorithm component searching for optimal trade-offs/policies between constraints and objectives set by decision-makers. Replaying pandemic evolution in various countries, we experimentally show that our approach yields predictions with much lower error rates than pure epidemiological models in 75% of the cases and achieves a 95% R2 score when the learning is transferred and tested on unseen countries. When used for forecasting, this approach provides actionable insights into the impact of individual measures and strategies. © 2020 Owner/Author.