Multifactor data analysis to forecast an individual's severity over novel COVID-19 pandemic using extreme gradient boosting and random forest classifier algorithms

AI and machine learning are increasingly often applied in the medical industry. The COVID-19 epidemic will start to spread quickly over the planet around the start of 2020. At hospitals, there were more patients than there were beds. It was challenging for medical personnel to identify the patient who needed treatment right away. A machine learning approach is used to predict COVID-19 pandemic patients at high risk. To provide input data and output results that execute the machine learning model on the backend, a straightforward Python Flask web application is employed. Here, the XGBoost algorithm, a supervised machine learning method, is applied. In order to predict high-risk patients based on their current underlying health issues, the model uses patient characteristics as well as criteria like age, sex, health issues including diabetes, asthma, hypertension, and smoking, among others. The XGBoost model predicts the patient's severity with an accuracy of about 98% after data pre-processing and training. The most important factors to the models are chosen to be age, diabetes, sex, and obesity. Patients and hospital personnel will benefit from this project's assistance in making timely choices and taking appropriate action. This will let medical personnel decide how much time and space to devote to the COVID-19 high-risk patients. providing a treatment that is both efficient and ideal. With this programme and the necessary patient data, hospitals may decide whether a patient need immediate care or not.

Molnupiravir, Nirmatrelvir/Ritonavir, or Sotrovimab for High-Risk COVID-19 Patients Infected by the Omicron Variant: Hospitalization, Mortality, and Time until Negative Swab Test in Real Life.

Background. Several drugs which are easy to administer in outpatient settings have been authorized and endorsed for high-risk COVID-19 patients with mild-moderate disease to prevent hospital admission and death, complementing COVID-19 vaccines. However, the evidence on the efficacy of COVID-19 antivirals during the Omicron wave is scanty or conflicting. Methods. This retrospective controlled study investigated the efficacy of Molnupiravir or Nirmatrelvir/Ritonavir (Paxlovid®) or Sotrovimab against standard of care (controls) on three different endpoints among 386 high-risk COVID-19 outpatients: hospital admission at 30 days; death at 30 days; and time between COVID-19 diagnosis and first negative swab test result. Multivariable logistic regression was employed to investigate the determinants of hospitalization due to COVID-19-associated pneumonia, whereas time to first negative swab test result was investigated by means of multinomial logistic analysis as well as Cox regression analysis. Results. Only 11 patients (overall rate of 2.8%) developed severe COVID-19-associated pneumonia requiring admission to hospital: 8 controls (7.2%); 2 patients on Nirmatrelvir/Ritonavir (2.0%); and 1 on Sotrovimab (1.8%). No patient on Molnupiravir was institutionalized. Compared to controls, hospitalization was less likely for patients on Nirmatrelvir/Ritonavir (aOR = 0.16; 95% CI: 0.03; 0.89) or Molnupiravir (omitted estimate); drug efficacy was 84% for Nirmatrelvir/Ritonavir against 100% for Molnupiravir. Only two patients died of COVID-19 (rate of 0.5%), both were controls, one (a woman aged 96 years) was unvaccinated and the other (a woman aged 72 years) had adequate vaccination status. At Cox regression analysis, the negativization rate was significantly higher in patients treated with both antivirals-Nirmatrelvir/Ritonavir (aHR = 1.68; 95% CI: 1.25; 2.26) or Molnupiravir (aHR = 1.45; 95% CI: 1.08; 1.94). However, COVID-19 vaccination with three (aHR = 2.03; 95% CI: 1.51; 2.73) or four (aHR = 2.48; 95% CI: 1.32; 4.68) doses had a slightly stronger effect size on viral clearance. In contrast, the negativization rate reduced significantly in patients who were immune-depressed (aHR = 0.70; 95% CI: 0.52; 0.93) or those with a Charlson index ≥5 (aHR = 0.63; 0.41; 0.95) or those who had started the respective treatment course 3+ days after COVID-19 diagnosis (aOR = 0.56; 95% CI: 0.38; 0.82). Likewise, at internal analysis (excluding patients on standard of care), patients on Molnupiravir (aHR = 1.74; 95% CI: 1.21; 2.50) or Nirmatrelvir/Ritonavir (aHR = 1.96; 95% CI: 1.32; 2.93) were more likely to turn negative earlier than those on Sotrovimab (reference category). Nonetheless, three (aHR = 1.91; 95% CI: 1.33; 2.74) or four (aHR = 2.20; 95% CI: 1.06; 4.59) doses of COVID-19 vaccine were again associated with a faster negativization rate. Again, the negativization rate was significantly lower if treatment started 3+ days after COVID-19 diagnosis (aHR = 0.54; 95% CI: 0.32; 0.92). Conclusions. Molnupiravir, Nirmatrelvir/Ritonavir, and Sotrovimab were all effective in preventing hospital admission and/or mortality attributable to COVID-19. However, hospitalizations also decreased with higher number of doses of COVID-19 vaccines. Although they are effective against severe disease and mortality, the prescription of COVID-19 antivirals should be carefully scrutinized by double opinion, not only to contain health care costs but also to reduce the risk of generating resistant SARS-CoV-2 strains. Only 64.7% of patients were in fact immunized with 3+ doses of COVID-19 vaccines in the present study. High-risk patients should prioritize COVID-19 vaccination, which is a more cost-effective approach than antivirals against severe SARS-CoV-2 pneumonia. Likewise, although both antivirals, especially Nirmatrelvir/Ritonavir, were more likely than standard of care and Sotrovimab to reduce viral shedding time (VST) in high-risk SARS-CoV-2 patients, vaccination had an independent and stronger effect on viral clearance. However, the effect of antivirals or COVID-19 vaccination on VST should be considered a secondary benefit. Indeed, recommending Nirmatrelvir/Ritonavir in order to control VST in high-risk COVID-19 patients is rather questionable since other cheap, large spectrum and harmless nasal disinfectants such as hypertonic saline solutions are available on the market with proven efficacy in containing VST.

Experiences of patients and their caregivers in a Virtual Ward in Singapore: A descriptive qualitative study.

BACKGROUND: The experiences of COVID-19 patients admitted to Virtual Wards and their caregivers are underexplored in Asian communities. A COVID-19 Virtual Ward (CVW) was recently established in Singapore. AIM: This study aims to describe the experiences of high-risk COVID-19 patients admitted to a Virtual Ward and their caregivers in a multi-racial Asian community. METHODS: A descriptive qualitative study was conducted from November 2021 to March 22 among high-risk COVID-19 patients and their caregivers who had been admitted to a CVW. The CVW involved teleconsultation whereby patients submitted their vital signs via a chatbot on their mobile phone and were supported remotely by a team of allied health professionals. In-depth interviews were conducted with patients and their caregivers and analyzed thematically. Findings The findings were supported by three themes. First, CVW admissions were perceived to be safe and effective. The second emerging theme related to the benefits and burdens of receiving care at home. The benefits of CVW were perceived comfort and familiarity with the home environment, while burdens included ensuring discipline in submitting health data and self-isolating from other household members. Last, the role of external factors such as informal support, paid domestic workers, and work arrangements was highlighted by the participants. Overall, key enablers for a successful CVW experience were the availability of social support, timely care from the care team, and 24/7 access to the team. CONCLUSION: In conclusion, CVW was perceived as a safe and effective strategy to manage high-risk patients at home. We recommend that Virtual Wards should be further developed to expand bed capacity in both pandemic and non-pandemic settings.

COVID-19 vaccination hesitancy in people affected by diabetes and strategies to increase vaccine compliance: A systematic narrative review and meta-analysis

Introduction: People affected by diabetes are at higher risk for complications from certain vaccine-preventable diseases. Suboptimal vaccination coverages are reported in this population sub-group. The purpose of this study is to estimate the proportion of diabetic patients who express hesitation to the COVID-19 vaccine worldwide.Methods: Seven studies were included in the meta-analysis and systematic review, selected from scientific articles available in the MEDLINE/PubMed, Google Scholar and Scopus databases from 2020 to 2022. The following terms were used for the search strategy: (adherence OR hesitancy OR compliance OR attitude) AND (covid* OR SARS*) AND (vaccin* OR immun*) AND (diabet*).Results: The vaccine hesitation rate among persons with diabetes was 27.8 % (95 %CI = 15.6-41.9 %). In the comparison of vaccine hesitancy between sexes and educational status, the RRs were 0.90 (95 %CI = 0.71-1.15) and 0.88 (95 %CI = 0.76-1.02), respectively. The main reasons of unwillingness were lack of information, opinion that the vaccine was unsafe or not efficient, and fear of adverse events.Conclusions: In order to achieve a high vaccination coverage, multifactorial approach is needed, which requires major social, scientific and health efforts. The success of the vaccination campaign in this population depends on the capillarity and consistency of the interventions implemented.

Proteomics reveals antiviral host response and NETosis during acute COVID-19 in high-risk patients.

SARS-CoV-2 remains an acute threat to human health, endangering hospital capacities worldwide. Previous studies have aimed at informing pathophysiologic understanding and identification of disease indicators for risk assessment, monitoring, and therapeutic guidance. While findings start to emerge in the general population, observations in high-risk patients with complex pre-existing conditions are limited. We addressed the gap of existing knowledge with regard to a differentiated understanding of disease dynamics in SARS-CoV-2 infection while specifically considering disease stage and severity. We biomedically characterized quantitative proteomics in a hospitalized cohort of COVID-19 patients with mild to severe symptoms suffering from different (co)-morbidities in comparison to both healthy individuals and patients with non-COVID related inflammation. Deep clinical phenotyping enabled the identification of individual disease trajectories in COVID-19 patients. By the use of the individualized disease phase assignment, proteome analysis revealed a severity dependent general type-2-centered host response side-by-side with a disease specific antiviral immune reaction in early disease. The identification of phenomena such as neutrophil extracellular trap (NET) formation and a pro-coagulatory response characterizing severe disease was successfully validated in a second cohort. Together with the regulation of proteins related to SARS-CoV-2-specific symptoms identified by proteome screening, we not only confirmed results from previous studies but provide novel information for biomarker and therapy development.

Association of nirmatrelvir/ritonavir treatment on upper respiratory SARS-CoV-2 RT-PCR negative conversion rates among high-risk patients with COVID-19.

BACKGROUND: Acceleration of negative respiratory conversion of SARS-CoV-2 in patients with coronavirus disease 2019 (COVID-19) might reduce viral transmission. Nirmatrelvir/ritonavir is a new antiviral agent recently approved for treatment of COVID-19 that has the potential to facilitate negative conversion. METHODS: A cohort of hospitalized adult patients with mild-to-moderate COVID-19 who had a high-risk for progression to severe disease were studied. These patients presented with COVID-19 symptoms between March 5 and April 5, 2022. The time from positive to negative upper respiratory RT-PCR conversion was assessed by Kaplan-Meier plots and Cox proportional hazards regression with the adjustment for patients baseline demographic and clinical characteristics. RESULTS: There were 258 patients treated with nirmatrelvir/ritonavir and 224 non-treated patients who had mild-to-moderate COVID-19. The median (interquartile range) time for patients who converted from positive to negative RT-PCR was 10 days (7-12 days) in patients treated ≤5 days after symptom onset and 17 days (12-21 days) in non-treated patients, respectively. The proportions of patients with a negative conversion at day 15 were 89.7% and 42.0% in treated patients and non-treated patients, corresponding to a hazard ratio of 4.33 (95% CI, 3.31-5.65). Adjustment for baseline differences between the groups had little effect on the association. Subgroup analysis on treated patients suggests that time to negative conversion did not vary with the patients' baseline characteristics. CONCLUSION: This cohort study of high-risk patients with mild-to-moderate COVID-19 found an association between nirmatrelvir/ritonavir treatment and accelerated negative RT-PCR respiratory SARS-CoV-2 conversion that might reduce the risk of viral shedding and disease transmission.

COVID-19 vaccination hesitancy in people affected by diabetes and strategies to increase vaccine compliance: A systematic narrative review and meta-analysis.

INTRODUCTION: People affected by diabetes are at higher risk for complications from certain vaccine-preventable diseases. Suboptimal vaccination coverages are reported in this population sub-group. The purpose of this study is to estimate the proportion of diabetic patients who express hesitation to the COVID-19 vaccine worldwide. METHODS: Seven studies were included in the meta-analysis and systematic review, selected from scientific articles available in the MEDLINE/PubMed, Google Scholar and Scopus databases from 2020 to 2022. The following terms were used for the search strategy: (adherence OR hesitancy OR compliance OR attitude) AND (covid* OR SARS*) AND (vaccin* OR immun*) AND (diabet*). RESULTS: The vaccine hesitation rate among persons with diabetes was 27.8 % (95 %CI = 15.6-41.9 %). In the comparison of vaccine hesitancy between sexes and educational status, the RRs were 0.90 (95 %CI = 0.71-1.15) and 0.88 (95 %CI = 0.76-1.02), respectively. The main reasons of unwillingness were lack of information, opinion that the vaccine was unsafe or not efficient, and fear of adverse events. CONCLUSIONS: In order to achieve a high vaccination coverage, multifactorial approach is needed, which requires major social, scientific and health efforts. The success of the vaccination campaign in this population depends on the capillarity and consistency of the interventions implemented.

Enhanced Monitoring System to Better Monitor High-Risk COVID-19 Patients.

Telemedicine (TM) is a useful tool to extend medical care during a pandemic. TM was extensively utilized in Singapore during the COVID-19 pandemic as part of the Nation's COVID-19 healthcare strategy. Patients were risk stratified to prioritize limited healthcare resources and the Telemedicine Allocation Reconciliation System (TMARS) was adapted to monitor and manage limited TM resources. High-Risk patients (Protocol 1) had an escalation rate of 4.87%, compared to the non-High-Risk patients' 0.002% and TM doctors spent an average of six hours to complete one tele-consultation. In order to optimize the efficiency of the TM system, an enhanced monitoring system was implemented in March 2022. The intent was to focus monitoring efforts on the High-Risk patients. High-Risk patients reporting sick for the first time were prioritized to receive tele-consultations through this system. With the aid of a data-driven dashboard, the Operations Control and Monitoring team (OCM) was able to closely monitor the performance of the various TM providers (TMPs), sent them timely reminders and re-assigned patients to other TMPs when the requisite turnaround time was not met. Implementing the enhanced monitoring system resulted in a significant reduction in the average time taken to provide tele-consultations. After 3 months of implementation, the percentages of consultations completed within two hours were raised from 75.7% (February 2022) to 96.8% (May 2022), greatly increasing productivity and efficiency.

Clinical considerations for the delivery of virtual dialectical behavior therapy to high-risk patients

This article discusses the clinical considerations for the delivery of virtual dialectical behavior therapy to high-risk patients. The COVID-19 pandemic has required rapid recalibration of behavioral health services, which has been challenging across all sectors of healthcare, but particularly so for high-risk patients for whom the use of telehealth has raised concerns. The telehealth model for DBT can be successfully implemented, but requires careful planning to mitigate potential risks and the use of particular strategies to facilitate relationship building and communication. Furthermore, virtual Dialectical behavior therapy (vDBT) requires a specific technological infrastructure, as well as unique policies to govern patient behavior in the presence of increased distractions found in the home environment. The dropout rates were on the lower end for comprehensive DBT programs, suggesting that the virtual modality may improve convenience for patients, thus improving retention. Although vDBT presents some unique challenges, the authors were able to overcome many of these challenges by using them as opportunities for patients to practice DBT skills, emphasizing the dialectical perspective that challenging experiences and opportunities can co-exist. vDBT provides a promising model for improving access to appropriate, high-quality care while simultaneously reducing healthcare costs. However, the understanding of vDBT is still in its infancy and work is needed to optimize clinical processes for the virtual delivery of DBT as well as evaluate clinical outcomes among patients receiving vDBT, and determine the impact of vDBT on medical expenditure associated with comorbid chronic conditions. (PsycInfo Database Record (c) 2022 APA, all rights reserved)

Ramadan fasting outcome among high-risk patients.

BACKGROUND: There is a growing literature on guidelines regarding Ramadan fasting for chronic kidney disease (CKD) patients. However, most studies only consider the impact of fasting on renal function. This study additionally aims to assess factors influencing Ramadan fasting in patients with CKD. METHOD: This is a prospective before and after cohort study. CKD patients were counseled regarding fasting and followed-up post-Ramadan for renal function status, actual fasting behavior, and other relevant outcomes. RESULTS: Of the 360 patients who attended the pre-Ramadan consultation, 306 were reachable after Ramadan of whom 55.3% were female. Of these 306 67.1% reported that they had fasted, 4.9% had attempted to fast but stopped, and 28% did not fast at all. Of these 74 has a post-fasting kidney test. Of the patients, 68.1% had stage 3A CKD, 21.7% had stage 3B, 7.9% stage 4, and only 2% stage 5. Of those who fasted, 11.1% had a drop in Glomerular Filtration Rate (eGFR) of 20% or more. Those who did not fast (16.7%) presented a similar drop. Conversely, among the few who attempted to fast and had to stop, half showed a drop in eGFR of more than 20%. In linear regression, fasting was not associated with post-Ramadan eGFR, when controlling for age and baseline eGRF. There were 17 (5.6%) significant events, including one death. More significant events occurred among the group who fasted some of Ramadan days, 26.7% of the subjects experienced an adverse event-while 4.7% of the group who did not fast had a significant adverse event compared to 4.4% among those who fasted all Ramadan. CONCLUSION: Fasting was not a significant determining factor in renal function deterioration in the study's population, nor did it have any significant association with adverse events.

mRNA or ChAd0x1 COVID-19 Vaccination of Adolescents Induces Robust Antibody and Cellular Responses With Continued Recognition of Omicron Following mRNA-1273.

Children and adolescents generally experience mild COVID-19. However, those with underlying physical health conditions are at a significantly increased risk of severe disease. Here, we present a comprehensive analysis of antibody and cellular responses in adolescents with severe neuro-disabilities who received COVID-19 vaccination with either ChAdOx1 (n=6) or an mRNA vaccine (mRNA-1273, n=8, BNT162b2, n=1). Strong immune responses were observed after vaccination and antibody levels and neutralisation titres were both higher after two doses. Both measures were also higher after mRNA vaccination and were further enhanced by prior natural infection where one vaccine dose was sufficient to generate peak antibody response. Robust T-cell responses were generated after dual vaccination and were also higher following mRNA vaccination. Early T-cells were characterised by a dominant effector-memory CD4+ T-cell population with a type-1 cytokine signature with additional production of IL-10. Antibody levels were well-maintained for at least 3 months after vaccination and 3 of 4 donors showed measurable neutralisation titres against the Omicron variant. T-cell responses also remained robust, with generation of a central/stem cell memory pool and showed strong reactivity against Omicron spike. These data demonstrate that COVID-19 vaccines display strong immunogenicity in adolescents and that dual vaccination, or single vaccination following prior infection, generate higher immune responses than seen after natural infection and develop activity against Omicron. Initial evidence suggests that mRNA vaccination elicits stronger immune responses than adenoviral delivery, although the latter is also higher than seen in adult populations. COVID-19 vaccines are therefore highly immunogenic in high-risk adolescents and dual vaccination might be able to provide relative protection against the Omicron variant that is currently globally dominant.

Enhancing a Telemedicine Platform with Global Navigation Satellite System Technology and Clustering Algorithms for Supporting Epidemiological Analysis

Telemedicine platforms have been largely used to manage multiple problems during the Covid-19 pandemic. In fact, they have given the possibility of remotely monitoring infected and high-risk patients, reducing hospitalisations. Telemonitoring systems with Global Navigation Satellite System technology allow to geo-localise all patients' measurements and enable the tracking of positions. These data can be used for contact tracing or to support doctors in epidemiological analysis. This paper presents the integration of satellite technologies in an existing telemedicine system (E@syCare), during the current outbreak. In particular, the platform has been enhanced with GPS, to geo-tag all vital parameters collected by the tablet gateway and the smartwatch. Geographical data are processed, after a request through the improved web-based medical interface based on some filters (e.g., vital parameters and their thresholds, considered period of time, and maximum cluster radius), with two sequential clustering algorithms. Agglomerative Clustering is used to find the optimal number of clusters given a maximum radius, and K-Means to effectively generate the predefined number of clusters. Resulting clusters are shown on an interactive epidemiological map in the webbased medical interface. This additional feature gives the possibility to healthcare authorities to correlate the spread of a disease or a virus with specific geographical areas or environmental conditions, to monitor fitness/movement habits of patients (also when the pandemic is over), and to track contact among patients. ©2021 IEEE.

Learning from heterogeneous data via contrastive learning: An application in multi-source covid-19 radiography

The ongoing COVID-19 pandemic has overloaded current healthcare systems, including radiology systems and departments. Machine learning-based medical imaging diagnostic approaches play an important role in tracking the spread of this virus, identifying high-risk patients, and controlling infections in real-time. Researchers aggregate radiographic samples from different data sources to establish a multi-source learning scheme to mitigate the insufficiency of COVID-19 samples from individual hospitals, especially in the early stage of the disease. However, data heterogeneity across different clinical centers with various imaging conditions is considered a significant limitation in model performance. This paper proposes a contrastive learning scheme for the automatic diagnosis of COVID-19 to effectively mitigate data heterogeneity in multi-source data and learn a robust and generalizable model. Inspired by advances in domain adaptation, we employ contrastive training objectives to promote intra-class cohesion across different data sources and inter-class separation of infected and non-infected cases. Extensive experiments on two public COVID-19 CT datasets demonstrate the effectiveness of the proposed method for tackling data heterogeneity problems with boosted diagnosis performance. Moreover, benefiting from the contrastive learning framework, our method can be generalized to solve data heterogeneity problems under a broader multi-source learning setting. © 2021 IEEE

A Randomized Open label Phase-II Clinical Trial with or without Infusion of Plasma from Subjects after Convalescence of SARS-CoV-2 Infection in High-Risk Patients with Confirmed Severe SARS-CoV-2 Disease (RECOVER): A structured summary of a study protocol for a randomised controlled trial.

OBJECTIVES: Primary objectives • To assess the time from randomisation until an improvement within 84 days defined as two points on a seven point ordinal scale or live discharge from the hospital in high-risk patients (group 1 to group 4) with SARS-CoV-2 infection requiring hospital admission by infusion of plasma from subjects after convalescence of SARS-CoV-2 infection or standard of care. Secondary objectives • To assess overall survival, and the overall survival rate at 28 56 and 84 days. • To assess SARS-CoV-2 viral clearance and load as well as antibody titres. • To assess the percentage of patients that required mechanical ventilation. • To assess time from randomisation until discharge. TRIAL DESIGN: Randomised, open-label, multicenter phase II trial, designed to assess the clinical outcome of SARS-CoV-2 disease in high-risk patients (group 1 to group 4) following treatment with anti-SARS-CoV-2 convalescent plasma or standard of care. PARTICIPANTS: High-risk patients >18 years of age hospitalized with SARS-CoV-2 infection in 10-15 university medical centres will be included. High-risk is defined as SARS-CoV-2 positive infection with Oxygen saturation at ≤ 94% at ambient air with additional risk features as categorised in 4 groups: • Group 1, pre-existing or concurrent hematological malignancy and/or active cancer therapy (incl. chemotherapy, radiotherapy, surgery) within the last 24 months or less. • Group 2, chronic immunosuppression not meeting the criteria of group 1. • Group 3, age ≥ 50 - 75 years meeting neither the criteria of group 1 nor group 2 and at least one of these criteria: Lymphopenia < 0.8 x G/l and/or D-dimer > 1µg/mL. • Group 4, age ≥ 75 years meeting neither the criteria of group 1 nor group 2. Observation time for all patients is expected to be at least 3 months after entry into the study. Patients receive convalescent plasma for two days (day 1 and day 2) or standard of care. For patients in the standard arm, cross over is allowed from day 10 in case of not improving or worsening clinical condition. Nose/throat swabs for determination of viral load are collected at day 0 and day 1 (before first CP administration) and subsequently at day 2, 3, 5, 7, 10, 14, 28 or until discharge. Serum for SARS-Cov-2 diagnostic is collected at baseline and subsequently at day 3, 7, 14 and once during the follow-up period (between day 35 and day 84). There is a regular follow-up of 3 months. All discharged patients are followed by regular phone calls. All visits, time points and study assessments are summarized in the Trial Schedule (see full protocol Table 1). All participating trial sites will be supplied with study specific visit worksheets that list all assessments and procedures to be completed at each visit. All findings including clinical and laboratory data are documented by the investigator or an authorized member of the study team in the patient's medical record and in the electronic case report forms (eCRFs). INTERVENTION AND COMPARATOR: This trial will analyze the effects of convalescent plasma from recovered subjects with SARS-CoV-2 antibodies in high-risk patients with SARS-CoV-2 infection. Patients at high risk for a poor outcome due to underlying disease, age or condition as listed above are eligible for enrollment. In addition, eligible patients have a confirmed SARS-CoV-2 infection and O2 saturation ≤ 94% while breathing ambient air. Patients are randomised to receive (experimental arm) or not receive (standard arm) convalescent plasma in two bags (238 - 337 ml plasma each) from different donors (day 1, day 2). A cross over from the standard arm into the experimental arm is possible after day 10 in case of not improving or worsening clinical condition. MAIN OUTCOMES: Primary endpoints: The main purpose of the study is to assess the time from randomisation until an improvement within 84 days defined as two points on a seven-point ordinal scale or live discharge from the hospital in high-risk patients (group 1 to group 4) with SARS-CoV-2 infection requiring hospital admission by infusion of plasma from subjects after convalescence of a SARS-CoV-2 infection or standard of care. Secondary endpoints: • Overall survival, defined as the time from randomisation until death from any cause 28-day, 56-day and 84-day overall survival rates. • SARS-CoV-2 viral clearance and load as well as antibody titres. • Requirement mechanical ventilation at any time during hospital stay (yes/no). • Time until discharge from randomisation. • Viral load, changes in antibody titers and cytokine profiles are analysed in an exploratory manner using paired non-parametric tests (before - after treatment). RANDOMISATION: Upon confirmation of eligibility (patients must meet all inclusion criteria and must not meet exclusion criteria described in section 5.3 and 5.4 of the full protocol), the clinical site must contact a centralized internet randomization system ( https://randomizer.at/ ). Patients are randomized using block randomisation to one of the two arms, experimental arm or standard arm, in a 1:1 ratio considering a stratification according to the 4 risk groups (see Participants). BLINDING (MASKING): The study is open-label, no blinding will be performed. NUMBERS TO BE RANDOMISED (SAMPLE SIZE): A total number of 174 patients is required for the entire trial, n=87 per group. TRIAL STATUS: Protocol version 1.2 dated 09/07/2020. A recruitment period of approximately 9 months and an overall study duration of approximately 12 months is anticipated. Recruitment of patients starts in the third quarter of 2020. The study duration of an individual patient is planned to be 3 months. After finishing all study-relevant procedures, therapy, and follow-up period, the patient is followed in terms of routine care and treated if necessary. Total trial duration: 18 months Duration of the clinical phase: 12 months First patient first visit (FPFV): 3rd Quarter 2020 Last patient first visit (LPFV): 2nd Quarter 2021 Last patient last visit (LPLV): 3rd Quarter 2021 Trial Report completed: 4th Quarter 2021 TRIAL REGISTRATION: EudraCT Number: 2020-001632-10, https://www.clinicaltrialsregister.eu/ctr-search/trial/2020-001632-10/DE , registered on 04/04/2020. FULL PROTOCOL: The full protocol is attached as an additional file, accessible from the Trials website (Additional file 1). In the interest in expediting dissemination of this material, the familiar formatting has been eliminated; this Letter serves as a summary of the key elements of the full protocol. The study protocol has been reported in accordance with the Standard Protocol Items: Recommendations for Clinical Interventional Trials (SPIRIT) guidelines (Additional file 2). The eCRF is attached (Additional file 3).