Introduction: Coronavirus disease 2019 (COVID-19) is a systemic disease characterized by a disproportionate inflammatory response in the acute phase. This study sought to identify clinical sequelae and their potential mechanism. Methods: We conducted a prospective single-center study (NCT04689490) of previously hospitalized COVID-19 patients with and without dyspnea during mid-term follow-up. An outpatient group was also evaluated. They underwent serial testing with a cardiopulmonary exercise test (CPET), transthoracic echocardiogram, pulmonary lung test, six-minute walking test, serum biomarker analysis, and quality of life questionaries. Results: Patients with dyspnea (n = 41, 58.6%), compared with asymptomatic patients (n = 29, 41.4%), had a higher proportion of females (73.2 vs. 51.7%; p = 0.065) with comparable age and prevalence of cardiovascular risk factors. There were no significant differences in the transthoracic echocardiogram and pulmonary function test. Patients who complained of persistent dyspnea had a significant decline in predicted peak VO₂ consumption (77.8 (64–92.5) vs. 99 (88–105); p < 0.00; p < 0.001), total distance in the six-minute walking test (535 (467–600) vs. 611 (550–650) meters; p = 0.001), and quality of life (KCCQ-23 60.1 ± 18.6 vs. 82.8 ± 11.3; p < 0.001). Additionally, abnormalities in CPET were suggestive of an impaired ventilatory efficiency (VE/VC_O2 slope 32 (28.1–37.4) vs. 29.4 (26.9–31.4); p = 0.022) and high PET_CO2 (34.5 (32–39) vs. 38 (36–40); p = 0.025). Interpretation: In this study, >50% of COVID-19 survivors present a symptomatic functional impairment irrespective of age or prior hospitalization. Our findings suggest a potential ventilation/perfusion mismatch or hyperventilation syndrome.

Background/Objectives: Vegetation length is a guideline-endorsed criterion for surgery in left-sided infective endocarditis (LSIE). However, its measurement is highly variable with crucial implications for decision making. A standardized measurement system would not only facilitate decision making in these patients, but also cutoff-point optimization for improving clinical guidelines. For this purpose, this work introduces an Artificial Intelligence (AI)-based system capable of extracting vegetation length from standard transesophageal echocardiography (TEE). Methods: Five echocardiographers independently measured the vegetation length of 76 vegetations from 67 consecutive patients with LSIE using offline TEE images. The AI-based system was trained on a multicenter registry with 353 patients with LSIE, comprising 282,096 echocardiographic frames annotated by an independent expert. This system was applied to measure vegetation length as an independent observer. The variability and correlation between operators and the system were assessed. Results: Lin’s concordance correlation coefficient between the AI-based system and the mean of the measurements obtained by the echocardiographers was 0.74, comparable to the coefficient obtained between the echocardiographers themselves. Bland–Altman analysis showed a mean difference of −1.0 mm between the AI-based system and the mean of the measurements obtained by the echocardiographers. Conclusions: The AI-based system for vegetation measurement demonstrates a high level of correlation and agreement with experts, similar to the concordance between human operators themselves. This level of agreement suggests that the method has the potential to reduce inter-operator variability in the measurement process. Whether AI-based vegetation size improves embolism prediction has to be further investigated.