Long COVID risk factors in a Portuguese cohort

Introduction: Long COVID is defined as the presence of symptoms that develop during or after COVID-19, continue for more than 12 weeks, and are not explained by an alternative diagnosis. Post-COVID radiological sequelae may occur and could be associated with dyspnea and cough. Decreased DLCO has been described as the main feature of PFTs abnormalities. Aims and objectives: The aim of this study was to identify potentially correlated with long COVID and its association with radiological and lung function sequelae in previously hospitalized patients. Method(s): We conducted a cross-sectional study with 93 patients that were evaluated in an outpatient setting following discharge from the hospital for COVID-19 pneumonia. Result(s): The mean age was 64 (+/-11) years old, 54 (59.1%) were male. The evaluation occurred on average 20 (+/-4) weeks after hospital discharge and 42 (45.2%) patients presented with long COVID. The most common symptoms were fatigue (31.2%) and dyspnea (26.9%). The prevalence of long COVID was higher in females (61%) (P=0.015). Obesity (OR 5.000, P=0.005), admission to ICU (OR 10.276, p=0.006), and the need for NIV (OR 7.85, p=0.01) were associated with long COVID. 65 patients performed CT scan and 43 (66%) had no or mild radiological sequelae. Radiological sequelae were more common in patients with long covid (n= 13, 30%) (p=0.024) and dyspnea/fatigue (p=0.04). Lung function was evaluated in 86 patients;decreased DLCO was the most common altered feature (n=32, 37%) and was associated with the presence of dyspnea/fatigue (p= 0.029). Conclusion(s): Obesity, ICU admission and the need for NIV were associated with a higher incidence of long COVID. The presence of radiological sequalae and/or decreased DLCO were associated with long COVID.

Forecasting COVID-19 Severity by Intelligent Optical Fingerprinting of Blood Samples.

Forecasting COVID-19 disease severity is key to supporting clinical decision making and assisting resource allocation, particularly in intensive care units (ICUs). Here, we investigated the utility of time- and frequency-related features of the backscattered signal of serum patient samples to predict COVID-19 disease severity immediately after diagnosis. ICU admission was the primary outcome used to define disease severity. We developed a stacking ensemble machine learning model including the backscattered signal features (optical fingerprint), patient comorbidities, and age (AUROC = 0.80), which significantly outperformed the predictive value of clinical and laboratory variables available at hospital admission (AUROC = 0.71). The information derived from patient optical fingerprints was not strongly correlated with any clinical/laboratory variable, suggesting that optical fingerprinting brings unique information for COVID-19 severity risk assessment. Optical fingerprinting is a label-free, real-time, and low-cost technology that can be easily integrated as a front-line tool to facilitate the triage and clinical management of COVID-19 patients.