Artificial-Intelligence-Driven Algorithms for Predicting Response to Corticosteroid Treatment in Patients with Post-Acute COVID-19.

Pulmonary fibrosis is one of the most severe long-term consequences of COVID-19. Corticosteroid treatment increases the chances of recovery; unfortunately, it can also have side effects. Therefore, we aimed to develop prediction models for a personalized selection of patients benefiting from corticotherapy. The experiment utilized various algorithms, including Logistic Regression, k-NN, Decision Tree, XGBoost, Random Forest, SVM, MLP, AdaBoost, and LGBM. In addition easily human-interpretable model is presented. All algorithms were trained on a dataset consisting of a total of 281 patients. Every patient conducted an examination at the start and three months after the post-COVID treatment. The examination comprised a physical examination, blood tests, functional lung tests, and an assessment of health state based on X-ray and HRCT. The Decision tree algorithm achieved balanced accuracy (BA) of 73.52%, ROC-AUC of 74.69%, and 71.70% F1 score. Other algorithms achieving high accuracy included Random Forest (BA 70.00%, ROC-AUC 70.62%, 67.92% F1 score) and AdaBoost (BA 70.37%, ROC-AUC 63.58%, 70.18% F1 score). The experiments prove that information obtained during the initiation of the post-COVID-19 treatment can be used to predict whether the patient will benefit from corticotherapy. The presented predictive models can be used by clinicians to make personalized treatment decisions.

Long-Term Follow-Up of Patients Needing Extracorporeal Membrane Oxygenation Following a Critical Course of COVID-19.

INTRODUCTION: Severe respiratory failure is one of the most serious complications of coronavirus disease 2019 (COVID-19). In a small proportion of patients, mechanical ventilation fails to provide adequate oxygenation and extracorporeal membrane oxygenation (ECMO) is needed. The surviving individuals need long-term follow-up as it is not clear what their prognosis is. AIM: To provide a complex clinical picture of patients during follow-up exceeding one year after the ECMO therapy due to severe COVID-19. METHODS: All subjects involved in the study required ECMO in the acute stage of COVID-19. The survivors were followed-up for over one year at a specialized respiratory medical center. RESULTS: Of the 41 patients indicated for ECMO, 17 patients (64.7% males) survived. The average age of survivors was 47.8 years, and the average BMI was 34.7 kg·m-2. The duration of ECMO support was 9.4 days. A mild decrease in vital capacity (VC) and transfer factor (DLCO) was observed on the initial follow-up visit (82.1% and 60%, respectively). VC improved by 6.2% and by an additional 7.5% after 6 months and 1 year, respectively. DLCO improved by 21.1% after 6 months and remained stable after 1 year. Post-intensive care consequences included psychological problems and neurological impairment in 29% of patients; 64.7% of the survivors got vaccinated against SARS-CoV-2 within 12 months of hospitalization and 17.6% experienced reinfection with a mild course. CONCLUSION: The COVID-19 pandemic has significantly increased the need for ECMO. Patients' quality of life after ECMO is temporarily significantly reduced but most patients do not experience permanent disability.

The use of extracorporeal membrane oxygenation in the treatment of critical course of pneumonia.

Extracorporeal membrane oxygenation is the highest form of resuscitation care in management of patients with respiratory failure. In the case of acute respiratory distress syndrome, the veno-venous setting is more often used. ECMO support enables, in case of lung function failure, to obtain the necessary time for the onset of the causal treatment effect or is used as a bridge to transplantation Mortality of the patients varies according to the underlying cause and presence of risk factors (e.g., age, complications or comorbid diseases). The onset of the COVID-19 pandemic has led to a significant increase in the need for ECMO. The quality of life of patients after ECMO is significantly reduced, but most patients do not experience permanent disability.

Post-COVID Syndrome and Cardiorespiratory Fitness-26-Month Experience of Single Center.

INTRODUCTION: Persistent post-COVID syndrome, also referred to as long COVID, is a pathologic entity that involves persistent physical, medical, and cognitive sequelae following COVID-19. Decreased fitness has repeatedly been reported in numerous studies dealing with post-COVID syndrome, however, it is still not fully clear which groups of patients may be more susceptible for persisting symptoms. AIM: The aim of our study was to evaluate the number of post-COVID patients with cardiac symptoms, where these patients were evaluated by CPET and the results compared with a control group of patients. METHODS: Follow-up of patients in post-COVID outpatient clinic from 1 March 2020 to 31 May 2022. Inclusion criteria were positive PCR test for SARS-CoV-2 and age 18-100. The initial examination was performed 4-12 weeks after the disease onset. All patients with possible cardiac symptoms had completed cardiopulmonary exercise testing. The control group was randomly selected from a database of clients in 2019, with the preventive reason for evaluation. RESULTS: From 1 March 2020 to 31 May 2022, 2732 patients (45.7% males) were evaluated with a mean age of 54.6 ± 14.7. CPET was indicated only in 97 patients (3.5%). Seventy-four patients (26 male) achieved the exercise maximum and a comparison were made with a control group (same age (p = 0.801), BMI (p = 0.721), and sex ratio). No significant dependence between the parameter VO2 max mL/kg/min and post-COVID disability was demonstrated (p = 0.412). Spearman's correlation analysis did not show a significant relationship between the parameter VO2 max mL/kg/min and the severity of COVID-19 (p = 0.285). CONCLUSIONS: Cardiac symptoms occurred in only a small percentage of patients in our study. There is a need for further studies that would objectively evaluate the effect of COVID-19 disease on the patient's health.

Risk of Severe COVID-19 in Non-Adherent OSA Patients.

Background: Patients with obstructive sleep apnoea (OSA) are at increased risk of severe course of COVID-19. Vaccination remains to be the most effective prevention of complicated courses of infection. The best contemporary conservative treatment of OSA is continuous positive airway pressure (CPAP) therapy. Purpose: To compare vaccination acceptance and outcomes of COVID-19 infection between OSA patients adhering to the CPAP therapy and those who rejected CPAP and surgical therapy. Patients and Methods: Subjects were divided into two groups: group A (N = 167) were individuals with sufficient CPAP adherence (more than 4 hours per night on average) over the last 10 years. Group B (N = 106) were individuals who did not use the CPAP therapy at all and had no indications to surgical therapy. Results: Three patients in group B died, and one had a severe course of COVID-19. None of the patients in group A died or experienced a severe course of COVID-19. Group A had a significantly higher proportion of males (77.8% compared to 66% in group B) and all parameters of OSA severity. The vaccination status was similar among both groups, with a complete triple dose vaccination rate of 69.5% and 67.9% in groups A and B, respectively. Conclusion: The results show that the patients with OSA adherent to CPAP therapy were less likely to experience a severe course of COVID-19 or death than the OSA patients non-compliant with therapy, despite the former group having more severe OSA. This result underlines the importance of adherence to CPAP therapy in OSA.

Prevalence of Burnout in Healthcare Workers of Tertiary-Care Hospitals during the COVID-19 Pandemic: A Cross-Sectional Survey from Two Central European Countries.

COVID-19 has led to an unprecedented strain on healthcare workers (HCWs). This study aimed to determine the prevalence of burnout in hospital employees during a prolonged pandemic-induced burden on healthcare systems. An online survey among employees of a Czech and Slovak university hospital was conducted between November 2021 and January 2022, approximately when the incidence rates peaked in both countries. The Maslach Burnout Inventory-Human Services Survey was applied. We obtained 807 completed questionnaires (75.1% from Czech employees, 91.2% from HCWs, 76.2% from women; mean age of 42.1 ± 11 years). Burnout in emotional exhaustion (EE) was found in 53.2%, depersonalization (DP) in 33%, and personal accomplishment (PA) in 47.8% of respondents. In total, 148 (18.3%) participants showed burnout in all dimensions, 184 (22.8%) in two, and 269 (33.3%) in at least one dimension. Burnout in EE and DP (65% and 43.7%) prevailed in physicians compared to other HCWs (48.6% and 28.8%). Respondents from COVID-19-dedicated units achieved burnout in the EE and DP dimensions with higher rates than non-frontline HCWs (58.1% and 40.9% vs. 49.9% and 27.7%). Almost two years of the previous overloading of healthcare services, caused by the COVID-19 pandemic, resulted in the relatively high prevalence of burnout in HCWs, especially in physicians and frontline HCWs.

Network Analysis for Uncovering the Relationship between Host Response and Clinical Factors to Virus Pathogen: Lessons from SARS-CoV-2.

Analysing complex datasets while maintaining the interpretability and explainability of outcomes for clinicians and patients is challenging, not only in viral infections. These datasets often include a variety of heterogeneous clinical, demographic, laboratory, and personal data, and it is not a single factor but a combination of multiple factors that contribute to patient characterisation and host response. Therefore, multivariate approaches are needed to analyse these complex patient datasets, which are impossible to analyse with univariate comparisons (e.g., one immune cell subset versus one clinical factor). Using a SARS-CoV-2 infection as an example, we employed a patient similarity network (PSN) approach to assess the relationship between host immune factors and the clinical course of infection and performed visualisation and data interpretation. A PSN analysis of ~85 immunological (cellular and humoral) and ~70 clinical factors in 250 recruited patients with coronavirus disease (COVID-19) who were sampled four to eight weeks after a PCR-confirmed SARS-CoV-2 infection identified a minimal immune signature, as well as clinical and laboratory factors strongly associated with disease severity. Our study demonstrates the benefits of implementing multivariate network approaches to identify relevant factors and visualise their relationships in a SARS-CoV-2 infection, but the model is generally applicable to any complex dataset.

Clinical presentation and pulmonary function tests in post-acute COVID-19 patients.

AIMS: The study analysed post-acute COVID-19 symptoms and the pulmonary function test (PFT) results in patients surviving the native strain of the virus. METHODS: The study was prospective; the inclusion criteria were positive PCR test for SARS-CoV-2 and age 18-100. Exclusion criteria were active respiratory infection, known or suspicious pre-existing pulmonary disease, cardiac failure, recent or acute pulmonary embolism, anaemia, and neuromuscular diseases. The recruitment period was 1st March 2020 - 25th December 2020. The initial examination was performed 4-12 weeks after the disease onset. All subjects underwent physical examination, anamnesis, chest x-ray and PFT. RESULTS: The study involved 785 subjects (345 male) mean age 53.8 (SD 14.6). The disease severity groups were: mild (G1), moderate (G2) and severe/critical (G3). Anosmia was present in the acute disease phase in 45.2% of G1 patients, but only in 4.5% of G3 patients. Dyspnoea occurred frequently in more severe groups (40%, 51.8% and 63.7% for G1, G2 and G3 respectively), while cough and fatigue showed no relationship to disease severity. Females were more likely to experience persistent symptoms. PFT results were significantly decreased in more severe groups compared to the mild COVID-19 patients, diffusing capacity was 86.3%, 79% and 68% of predicted values in G1, G2 and G3 respectively. CONCLUSION: Anosmia during the acute phase was associated with mild disease, persisting dyspnoea was more frequent after more severe COVID-19. Females tended to have persisting symptoms in post-acute phase more frequently. PFT results showed decrease with disease severity.