The PROVENT-C19 registry: A study protocol for international multicenter SIAARTI registry on the use of prone positioning in mechanically ventilated patients with COVID-19 ARDS.

BACKGROUND: The worldwide use of prone position (PP) for invasively ventilated patients with COVID-19 is progressively increasing from the first pandemic wave in everyday clinical practice. Among the suggested treatments for the management of ARDS patients, PP was recommended in the Surviving Sepsis Campaign COVID-19 guidelines as an adjuvant therapy for improving ventilation. In patients with severe classical ARDS, some authors reported that early application of prolonged PP sessions significantly decreases 28-day and 90-day mortality. METHODS AND ANALYSIS: Since January 2021, the COVID19 Veneto ICU Network research group has developed and implemented nationally and internationally the "PROVENT-C19 Registry", endorsed by the Italian Society of Anesthesia Analgesia Resuscitation and Intensive Care…'(SIAARTI). The PROVENT-C19 Registry wishes to describe 1. The real clinical practice on the use of PP in COVID-19 patients during the pandemic at a National and International level; and 2. Potential baseline and clinical characteristics that identify subpopulations of invasively ventilated patients with COVID-19 that may improve daily from PP therapy. This web-based registry will provide relevant information on how the database research tools may improve our daily clinical practice. CONCLUSIONS: This multicenter, prospective registry is the first to identify and characterize the role of PP on clinical outcome in COVID-19 patients. In recent years, data emerging from large registries have been increasingly used to provide real-world evidence on the effectiveness, quality, and safety of a clinical intervention. Indeed observation-based registries could be effective tools aimed at identifying specific clusters of patients within a large study population with widely heterogeneous clinical characteristics. TRIAL REGISTRATION: The registry was registered (ClinicalTrial.Gov Trials Register NCT04905875) on May 28,2021.

COVID-19 ICU mortality prediction: a machine learning approach using SuperLearner algorithm.

BACKGROUND: Since the beginning of coronavirus disease 2019 (COVID-19), the development of predictive models has sparked relevant interest due to the initial lack of knowledge about diagnosis, treatment, and prognosis. The present study aimed at developing a model, through a machine learning approach, to predict intensive care unit (ICU) mortality in COVID-19 patients based on predefined clinical parameters. RESULTS: Observational multicenter cohort study. All COVID-19 adult patients admitted to 25 ICUs belonging to the VENETO ICU network (February 28th 2020-april 4th 2021) were enrolled. Patients admitted to the ICUs before 4th March 2021 were used for model training ("training set"), while patients admitted after the 5th of March 2021 were used for external validation ("test set 1"). A further group of patients ("test set 2"), admitted to the ICU of IRCCS Ca' Granda Ospedale Maggiore Policlinico of Milan, was used for external validation. A SuperLearner machine learning algorithm was applied for model development, and both internal and external validation was performed. Clinical variables available for the model were (i) age, gender, sequential organ failure assessment score, Charlson Comorbidity Index score (not adjusted for age), Palliative Performance Score; (ii) need of invasive mechanical ventilation, non-invasive mechanical ventilation, O2 therapy, vasoactive agents, extracorporeal membrane oxygenation, continuous venous-venous hemofiltration, tracheostomy, re-intubation, prone position during ICU stay; and (iii) re-admission in ICU. One thousand two hundred ninety-three (80%) patients were included in the "training set", while 124 (8%) and 199 (12%) patients were included in the "test set 1" and "test set 2," respectively. Three different predictive models were developed. Each model included different sets of clinical variables. The three models showed similar predictive performances, with a training balanced accuracy that ranged between 0.72 and 0.90, while the cross-validation performance ranged from 0.75 to 0.85. Age was the leading predictor for all the considered models. CONCLUSIONS: Our study provides a useful and reliable tool, through a machine learning approach, for predicting ICU mortality in COVID-19 patients. In all the estimated models, age was the variable showing the most important impact on mortality.

How to communicate with families living in complete isolation.

IMPORTANCE: During the SARS-CoV-2 pandemic, a complete physical isolation has been worldwide introduced. The impossibility of visiting their loved ones during the hospital stay causes additional distress for families: in addition to the worries about clinical recovery, they may feel exclusion and powerlessness, anxiety, depression, mistrust in the care team and post-traumatic stress disorder. The impossibility of conducting the daily meetings with families poses a challenge for healthcare professionals. OBJECTIVE: This paper aims to delineate and share consensus statements in order to enable healthcare team to provide by telephone or video calls an optimal level of communication with patient's relatives under circumstances of complete isolation. EVIDENCE REVIEW: PubMed, Cochrane Database of Systematic Reviews, Database of Abstracts and Reviews of Effectiveness and the AHCPR Clinical Guidelines and Evidence Reports were explored from 1999 to 2019. Exclusion criteria were: poor or absent relevance regarding the aim of the consensus statements, studies prior to 1999, non-English language. Since the present pandemic context is completely new, unexpected and unexplored, there are not randomised controlled trials regarding clinical communication in a setting of complete isolation. Thus, a multiprofessional taskforce of physicians, nurses, psychologists and legal experts, together with some family members and former intensive care unit patients was established by four Italian national scientific societies. Using an e-Delphi methodology, general and specific questions were posed, relevant topics were argumented, until arriving to delineate position statements and practical checklist, which were set and evaluated through an evidence-based consensus procedure. FINDINGS: Ten statements and two practical checklists for phone or video calls were drafted and evaluated; they are related to who, when, why and how family members must be given clinical information under circumstances of complete isolation. CONCLUSIONS AND RELEVANCE: The statements and the checklists offer a structured methodology in order to ensure a good-quality communication between healthcare team and family members even in isolation, confirming that time dedicated to communication has to be intended as a time of care.