Search

Background The benefit of tocilizumab on mortality and time to recovery in people with severe COVID pneumonia may depend on appropriate timing. The objective was to estimate the impact of tocilizumab administration on switching respiratory support states, mortality and time to recovery. Methods In an observational study, a continuous-time Markov multi-state model was used to describe the sequence of respiratory support states including: no respiratory support (NRS), oxygen therapy (OT), non-invasive ventilation (NIV) or invasive mechanical ventilation (IMV), OT in recovery, NRS in recovery. Results Two hundred seventy-one consecutive adult patients were included in the analyses contributing to 695 transitions across states. The prevalence of patients in each respiratory support state was estimated with stack probability plots, comparing people treated with and without tocilizumab since the beginning of the OT state. A positive effect of tocilizumab on the probability of moving from the invasive and non-invasive mechanical NIV/IMV state to the OT in recovery state (HR = 2.6, 95% CI = 1.2–5.2) was observed. Furthermore, a reduced risk of death was observed in patients in NIV/IMV (HR = 0.3, 95% CI = 0.1–0.7) or in OT (HR = 0.1, 95% CI = 0.0–0.8) treated with tocilizumab. Conclusion To conclude, we were able to show the positive impact of tocilizumab used in different disease stages depicted by respiratory support states. The use of the multi-state Markov model allowed to harmonize the heterogeneous mortality and recovery endpoints and summarize results with stack probability plots. This approach could inform randomized clinical trials regarding tocilizumab, support disease management and hospital decision making.

Aims The aim of this study was to estimate a 48 hour prediction of moderate to severe respiratory failure, requiring mechanical ventilation, in hospitalized patients with COVID-19 pneumonia. Methods This was an observational prospective study that comprised consecutive patients with COVID-19 pneumonia admitted to hospital from 21 February to 6 April 2020. The patients’ medical history, demographic, epidemiologic and clinical data were collected in an electronic patient chart. The dataset was used to train predictive models using an established machine learning framework leveraging a hybrid approach where clinical expertise is applied alongside a data-driven analysis. The study outcome was the onset of moderate to severe respiratory failure defined as PaO2/FiO2 ratio Results A total of 198 patients contributed to generate 1068 usable observations which allowed to build 3 predictive models based respectively on 31-variables signs and symptoms, 39-variables laboratory biomarkers and 91-variables as a composition of the two. A fourth “boosted mixed model” included 20 variables was selected from the model 3, achieved the best predictive performance (AUC = 0.84) without worsening the FN rate. Its clinical performance was applied in a narrative case report as an example. Conclusion This study developed a machine model with 84% prediction accuracy, which is able to assist clinicians in decision making process and contribute to develop new analytics to improve care at high technology readiness levels.