ABSTRACT
Background: COVID-19 can cause cardiopulmonary involvement. Physical activity and cardiac complications can worsen prognosis, while pulmonary complications can reduce performance. Aims: To determine the prevalence and clinical implications of SARS-CoV-2 cardiopulmonary involvement in elite athletes. Methods: An observational study between 1 July 2020 and 30 June 2021 with the assessment of coronary biomarkers, electrocardiogram, echocardiography, Holter-monitoring, spirometry, and chest X-ray in Danish elite athletes showed that PCR-tested positive for SARS-CoV-2. The cohort consisted of male football players screened weekly (cohort I) and elite athletes on an international level only tested if they had symptoms, were near-contact, or participated in international competitions (cohort II). All athletes were categorized into two groups based on symptoms and duration of COVID-19: Group 1 had no cardiopulmonary symptoms and duration ≤7 days, and; Group 2 had cardiopulmonary symptoms or disease duration >7 days. Results: In total 121 athletes who tested positive for SARS-CoV-2 were investigated. Cardiac involvement was identified in 2/121 (2%) and pulmonary involvement in 15/121 (12%) participants. In group 1, 87 (72%), no athletes presented with signs of cardiac involvement, and 8 (7%) were diagnosed with radiological COVID-19-related findings or obstructive lung function. In group 2, 34 (28%), two had myocarditis (6%), and 8 (24%) were diagnosed with radiological COVID-19-related findings or obstructive lung function. Conclusions: These clinically-driven data show no signs of cardiac involvement among athletes who tested positive for SARS-CoV-2 infection without cardiopulmonary symptoms and duration <7 days. Athletes with cardiopulmonary symptoms or prolonged duration of COVID-19 display, exercise-limiting cardiopulmonary involvement.
ABSTRACT
Epidemics of infectious diseases can pose a serious threat to public health and the global economy. Despite scientific advances, containment and mitigation of infectious diseases remain a challenging task. In this paper, we investigate the potential of reinforcement learning as a decision making tool for epidemic control by constructing a deep Reinforcement Learning simulator, called EpidRLearn, composed of a contact-based, age-structured extension of the SEIR compartmental model, referred to as C-SEIR. We evaluate EpidRLearn by comparing the learned policies to two deterministic policy baselines. We further assess our reward function by integrating an alternative reward into our deep RL model. The experimental evaluation indicates that deep reinforcement learning has the potential of learning useful policies under complex epidemiological models and large state spaces for the mitigation of infectious diseases, with a focus on COVID-19. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.