Predicting responders to prone positioning in mechanically ventilated patients with COVID-19 using machine learning.

BACKGROUND: For mechanically ventilated critically ill COVID-19 patients, prone positioning has quickly become an important treatment strategy, however, prone positioning is labor intensive and comes with potential adverse effects. Therefore, identifying which critically ill intubated COVID-19 patients will benefit may help allocate labor resources. METHODS: From the multi-center Dutch Data Warehouse of COVID-19 ICU patients from 25 hospitals, we selected all 3619 episodes of prone positioning in 1142 invasively mechanically ventilated patients. We excluded episodes longer than 24 h. Berlin ARDS criteria were not formally documented. We used supervised machine learning algorithms Logistic Regression, Random Forest, Naive Bayes, K-Nearest Neighbors, Support Vector Machine and Extreme Gradient Boosting on readily available and clinically relevant features to predict success of prone positioning after 4 h (window of 1 to 7 h) based on various possible outcomes. These outcomes were defined as improvements of at least 10% in PaO2/FiO2 ratio, ventilatory ratio, respiratory system compliance, or mechanical power. Separate models were created for each of these outcomes. Re-supination within 4 h after pronation was labeled as failure. We also developed models using a 20 mmHg improvement cut-off for PaO2/FiO2 ratio and using a combined outcome parameter. For all models, we evaluated feature importance expressed as contribution to predictive performance based on their relative ranking. RESULTS: The median duration of prone episodes was 17 h (11-20, median and IQR, N = 2632). Despite extensive modeling using a plethora of machine learning techniques and a large number of potentially clinically relevant features, discrimination between responders and non-responders remained poor with an area under the receiver operator characteristic curve of 0.62 for PaO2/FiO2 ratio using Logistic Regression, Random Forest and XGBoost. Feature importance was inconsistent between models for different outcomes. Notably, not even being a previous responder to prone positioning, or PEEP-levels before prone positioning, provided any meaningful contribution to predicting a successful next proning episode. CONCLUSIONS: In mechanically ventilated COVID-19 patients, predicting the success of prone positioning using clinically relevant and readily available parameters from electronic health records is currently not feasible. Given the current evidence base, a liberal approach to proning in all patients with severe COVID-19 ARDS is therefore justified and in particular regardless of previous results of proning.

Right dose, right now: bedside, real-time, data-driven, and personalised antibiotic dosing in critically ill patients with sepsis or septic shock-a two-centre randomised clinical trial.

BACKGROUND: Adequate antibiotic dosing may improve outcomes in critically ill patients but is challenging due to altered and variable pharmacokinetics. To address this challenge, AutoKinetics was developed, a decision support system for bedside, real-time, data-driven and personalised antibiotic dosing. This study evaluates the feasibility, safety and efficacy of its clinical implementation. METHODS: In this two-centre randomised clinical trial, critically ill patients with sepsis or septic shock were randomised to AutoKinetics dosing or standard dosing for four antibiotics: vancomycin, ciprofloxacin, meropenem, and ceftriaxone. Adult patients with a confirmed or suspected infection and either lactate > 2 mmol/L or vasopressor requirement were eligible for inclusion. The primary outcome was pharmacokinetic target attainment in the first 24 h after randomisation. Clinical endpoints included mortality, ICU length of stay and incidence of acute kidney injury. RESULTS: After inclusion of 252 patients, the study was stopped early due to the COVID-19 pandemic. In the ciprofloxacin intervention group, the primary outcome was obtained in 69% compared to 3% in the control group (OR 62.5, CI 11.4-1173.78, p < 0.001). Furthermore, target attainment was faster (26 h, CI 18-42 h, p < 0.001) and better (65% increase, CI 49-84%, p < 0.001). For the other antibiotics, AutoKinetics dosing did not improve target attainment. Clinical endpoints were not significantly different. Importantly, higher dosing did not lead to increased mortality or renal failure. CONCLUSIONS: In critically ill patients, personalised dosing was feasible, safe and significantly improved target attainment for ciprofloxacin. TRIAL REGISTRATION: The trial was prospectively registered at Netherlands Trial Register (NTR), NL6501/NTR6689 on 25 August 2017 and at the European Clinical Trials Database (EudraCT), 2017-002478-37 on 6 November 2017.

Position paper ANMCO: Cardio-oncologia in era COVID-19

The COVID-19 pandemic and its impact on patients with cancer and cardiovascular disease have confirmed the particular vulnerability of this population. Indeed, not only a higher risk of contracting the infection has been reported, but also an increased occurrence of a more severe course and unfavorable outcome. Beyond the direct consequences of COVID-19, the pandemic has an enormous impact on global health systems. Screening programs and non-urgent tests have been postponed;clinical trials have suffered a setback. Similarly, in the area of cardiology care, a significant decline in ST-elevation myocardial infarction accesses and an increase in cases of late presenting heart attacks with increased mortality and complication rates have been reported. Health care systems must therefore get ready to tackle the "rebound effect" that will likely show a relative increase in the short and medium term incidence of diseases such as heart failure, myocardial infarction, arrhythmias and cardio- and cerebrovascular complications. Scientific societies are taking action to provide general guidance and recommendations aimed at mitigating the unfavorable outcomes of this pandemic emergency. Cardio-oncology, as an emerging discipline, is more flexible in modulating care pathways and represents a beacon of innovation in the development of multi-specialty patient management. In the era of the COVID-19 pandemic, cardio-oncology has rapidly modified its clinical care pathways and implemented flexible monitoring protocols that include targeted use of cardiac imaging, increased use of biomarkers, and telemedicine systems. The goal of these strategic adjustments is to minimize the risk of infection for providers and patients while maintaining standards of care for the treatment of oncologic and cardiovascular diseases. The aim of this position paper is to evaluate the impact of the COVID-19 pandemic on the management of cardio-oncologic patients with the-state-of-the-art knowledge about SARS-CoV-2 and COVID-19 in order to optimize medical strategies during and after the pandemic.

Effects of Environmental Factors on Severity and Mortality of COVID-19.

Background: Most respiratory viruses show pronounced seasonality, but for SARS-CoV-2, this still needs to be documented. Methods: We examined the disease progression of COVID-19 in 6,914 patients admitted to hospitals in Europe and China. In addition, we evaluated progress of disease symptoms in 37,187 individuals reporting symptoms into the COVID Symptom Study application. Findings: Meta-analysis of the mortality risk in seven European hospitals estimated odds ratios per 1-day increase in the admission date to be 0.981 (0.973-0.988, p < 0.001) and per increase in ambient temperature of 1°C to be 0.854 (0.773-0.944, p = 0.007). Statistically significant decreases of comparable magnitude in median hospital stay, probability of transfer to the intensive care unit, and need for mechanical ventilation were also observed in most, but not all hospitals. The analysis of individually reported symptoms of 37,187 individuals in the UK also showed the decrease in symptom duration and disease severity with time. Interpretation: Severity of COVID-19 in Europe decreased significantly between March and May and the seasonality of COVID-19 is the most likely explanation.

Composition of the immunoglobulin G glycome associates with the severity of COVID-19.

A large variation in the severity of disease symptoms is one of the key open questions in coronavirus disease 2019 (COVID-19) pandemics. The fact that only a small subset of people infected with severe acute respiratory syndrome coronavirus 2 develops severe disease suggests that there have to be some predisposing factors, but biomarkers that reliably predict disease severity have not been found so far. Since overactivation of the immune system is implicated in a severe form of COVID-19 and the immunoglobulin G (IgG) glycosylation is known to be involved in the regulation of different immune processes, we evaluated the association of interindividual variation in IgG N-glycome composition with the severity of COVID-19. The analysis of 166 severe and 167 mild cases from hospitals in Spain, Italy and Portugal revealed statistically significant differences in the composition of the IgG N-glycome. The most notable difference was the decrease in bisecting N-acetylglucosamine in severe patients from all three cohorts. IgG galactosylation was also lower in severe cases in all cohorts, but the difference in galactosylation was not statistically significant after correction for multiple testing.

Effects of environmental factors on severity and mortality of COVID-19 (preprint)

BackgroundMost respiratory viruses show pronounced seasonality, but for SARS-CoV-2 this still needs to be documented. MethodsWe examined the disease progression of COVID-19 in 6,914 patients admitted to hospitals in Europe and China. In addition, we evaluated progress of disease symptoms in 37,187 individuals reporting symptoms into the COVID Symptom Study application. FindingsMeta-analysis of the mortality risk in eight European hospitals estimated odds ratios per one day increase in the admission date to be 0.981 (0.973-0.988, p<0.001) and per increase in ambient temperature of one degree Celsius to be 0.854 (0.773-0.944, p=0.007). Statistically significant decreases of comparable magnitude in median hospital stay, probability of transfer to Intensive Care Unit and need for mechanical ventilation were also observed in most, but not all hospitals. The analysis of individually reported symptoms of 37,187 individuals in the UK also showed the decrease in symptom duration and disease severity with time. InterpretationSeverity of COVID-19 in Europe decreased significantly between March and May and the seasonality of COVID-19 is the most likely explanation. Mucosal barrier and mucociliary clearance can significantly decrease viral load and disease progression, and their inactivation by low relative humidity of indoor air might significantly contribute to severity of the disease.