A Web-Based Platform for the Automatic Stratification of ARDS Severity

Acute respiratory distress syndrome (ARDS), including severe pulmonary COVID infection, is associated with a high mortality rate. It is crucial to detect ARDS early, as a late diagnosis may lead to serious complications in treatment. One of the challenges in ARDS diagnosis is chest X-ray (CXR) interpretation. ARDS causes diffuse infiltrates through the lungs that must be identified using chest radiography. In this paper, we present a web-based platform leveraging artificial intelligence (AI) to automatically assess pediatric ARDS (PARDS) using CXR images. Our system computes a severity score to identify and grade ARDS in CXR images. Moreover, the platform provides an image highlighting the lung fields, which can be utilized for prospective AI-based systems. A deep learning (DL) approach is employed to analyze the input data. A novel DL model, named Dense-Ynet, is trained using a CXR dataset in which clinical specialists previously labelled the two halves (upper and lower) of each lung. The assessment results show that our platform achieves a recall rate of

A Web-Based Platform for the Automatic Stratification of ARDS Severity.

Acute respiratory distress syndrome (ARDS), including severe pulmonary COVID infection, is associated with a high mortality rate. It is crucial to detect ARDS early, as a late diagnosis may lead to serious complications in treatment. One of the challenges in ARDS diagnosis is chest X-ray (CXR) interpretation. ARDS causes diffuse infiltrates through the lungs that must be identified using chest radiography. In this paper, we present a web-based platform leveraging artificial intelligence (AI) to automatically assess pediatric ARDS (PARDS) using CXR images. Our system computes a severity score to identify and grade ARDS in CXR images. Moreover, the platform provides an image highlighting the lung fields, which can be utilized for prospective AI-based systems. A deep learning (DL) approach is employed to analyze the input data. A novel DL model, named Dense-Ynet, is trained using a CXR dataset in which clinical specialists previously labelled the two halves (upper and lower) of each lung. The assessment results show that our platform achieves a recall rate of 95.25% and a precision of 88.02%. The web platform, named PARDS-CxR, assigns severity scores to input CXR images that are compatible with current definitions of ARDS and PARDS. Once it has undergone external validation, PARDS-CxR will serve as an essential component in a clinical AI framework for diagnosing ARDS.

Situation Awareness-Oriented Dashboard in ICUs in Support of Resource Management in Time of Pandemics.

In a pediatric intensive care unit (PICU) of 32 beds, clinicians manage resources 24 hours a day, 7 days a week, from a large-screen dashboard implemented in 2017. This resource management dashboard efficiently replaces the handwriting information displayed on a whiteboard, offering a synthetic view of the bed's layout and specific information on staff and equipment at bedside. However, in 2020 when COVID-19 hit, the resource management dashboard showed several limitations. Mainly, its visualization offered to the clinicians limited situation awareness (SA) to perceive, understand and predict the impacts on resource management and decision-making of an unusual flow of patients affected by the most severe form of coronavirus. To identify the SA requirements during a pandemic, we conducted goal-oriented interviews with 11 clinicians working in ICUs. The result is the design of an SA-oriented dashboard with 22 key indicators (KIs): 1 on the admission capacity, 15 at bedside and 6 displayed as statistics in the central area. We conducted a usability evaluation of the SA-oriented dashboard compared to the resource management dashboard with 6 clinicians. The results showed five usability improvements of the SA-oriented dashboard and five limitations. Our work contributes to new knowledge on the clinicians' SA requirements to support resource management and decision-making in ICUs in times of pandemics.

Multisystemic Inflammatory Syndrome in Children: a step towards a better understanding of this entity.

As pediatricians, we all have to deal with new childhood inflammatory disorder due to COVID 19: the Multisystem Inflammatory Syndrome in Children (MIS-C). The recent article by Savorgnan et al. on the physiologic profiles associated with MIS-C proposed a classification through the "MIS-C severity score" (MSS). The authors also identified a combination of seven variables collected during the first 3 h of admission in the PICU that contributes to stratify MIS-C severity with an area under the receiver operating characteristic curve (AUC) >0.90. This work represents an important first step in the development of a MIS-C severity score and is a call for collaborative groups to validate the prediction model through multicenter studies and thereby refine the management of MIS-C. IMPACT: The recent article by Savorgnan et al. on physiologic profile associated with MIS-C represents an important first step in the development of an MIS-C severity score and is a call for collaborative groups to validate the prediction model through multicenter studies and thereby refine the management of MIS-C. Our manuscript helps in the methodology interpretation of the manuscript by Savorgnan et al. And our manuscript promotes collaborative work on MIS-C.

Prevention of submicron aerosolized particle dispersion: evaluation of an aerosol box using a pediatric simulation model.

Background and Aim: The SplashGuard CG (SG) is a barrier enclosure developed to protect healthcare workers from SARS-CoV-2 transmission during aerosol-generating procedures. Our objective was to evaluate the protection provided by the SG against aerosolized particles (AP), using a pediatric simulation model of spontaneous ventilation (SV) and noninvasive ventilation (NIV). Methods: An aerosol generator was connected to the airways of a pediatric high-fidelity manikin with a breathing simulator. AP concentrations were measured both in SV and NIV in the following conditions: with and without SG, inside and outside the SG, with and without suction applied to the device. Results: In the SV simulated setting, AP peaks were lower with SG: 0.1 × 105 particles/L compared to without: 1.6 × 105, only when the ports were closed and suction applied. In the NIV simulated setting, AP peaks outside the SG were lower than without SG (20.5 × 105 particles/L), whatever the situation, without suction (14.4 × 105particles/L), with suction and ports open or closed: 10.3 and 0.7 × 105 particles/L. In SV and NIV simulated settings, the AP peaks measured within the SG were much higher than the AP peaks measured without SG, even when suction was applied to the device. Conclusions: The SG seems to decrease peak AP exposure in the 2 ventilation contexts, but only with closed port and suction in SV. However, high concentrations of AP remain inside even with suction and SG should be used cautiously.

Consequences of Social Distancing Measures During the COVID-19 Pandemic First Wave on the Epidemiology of Children Admitted to Pediatric Emergency Departments and Pediatric Intensive Care Units: A Systematic Review.

Objectives: To synthesize knowledge describing the impact of social distancing measures (SDM) during the first wave of the COVID-19 pandemic on acute illness in children by focusing on the admission to pediatric emergency departments (PED) and pediatric intensive care units (PICU). Methods: We searched Cochrane Database of Systematic Reviews, Cochrane Controlled Trials Register, EPOC Register, MEDLINE, Evidence-Based Medicine Reviews, EMBASE, WHO database on COVID-19, Cochrane Resources on COVID-19, Oxford COVID-19 Evidence Service, Google Scholar for literature on COVID-19 including pre-print engines such as medRxiv, bioRxiv, Litcovid and SSRN for unpublished studies on COVID-19 in December 2020. We did not apply study design filtering. The primary outcomes of interest were the global incidence of admission to PICU and PED, disease etiologies, and elective/emergency surgeries, compared to the historical cohort in each studied region, country, or hospital. Results: We identified 6,660 records and eighty-seven articles met our inclusion criteria. All the studies were with before and after study design compared with the historical data, with an overall high risk of bias. The median daily PED admissions decreased to 65% in 39 included studies and a 54% reduction in PICU admission in eight studies. A significant decline was reported in acute respiratory illness and LRTI in five studies with a median decrease of 63%. We did not find a consistent trend in the incidence of poisoning, but there was an increasing trend in burns, DKA, and a downward trend in trauma and unplanned surgeries. Conclusions: SDMs in the first wave of the COVID-19 pandemic reduced the global incidence of pediatric acute illnesses. However, some disease groups, such as burns and DKA, showed a tendency to increase and its severity of illness at hospital presentation. Continual effort and research into the subject should be essential for us to better understand the effects of this new phenomenon of SDMs to protect the well-being of children. Systematic Review Registration: Clinicaltrials.gov, identifier: CRD42020221215.

Characteristics and outcomes of patients with COVID-19 admitted to hospital and intensive care in the first phase of the pandemic in Canada: a national cohort study.

BACKGROUND: Clinical data on patients admitted to hospital with coronavirus disease 2019 (COVID-19) provide clinicians and public health officials with information to guide practice and policy. The aims of this study were to describe patients with COVID-19 admitted to hospital and intensive care, and to investigate predictors of outcome to characterize severe acute respiratory infection. METHODS: This observational cohort study used Canadian data from 32 selected hospitals included in a global multisite cohort between Jan. 24 and July 7, 2020. Adult and pediatric patients with a confirmed diagnosis of COVID-19 who received care in an intensive care unit (ICU) and a sampling of up to the first 60 patients receiving care on hospital wards were included. We performed descriptive analyses of characteristics, interventions and outcomes. The primary analyses examined in-hospital mortality, with secondary analyses of the length of hospital and ICU stay. RESULTS: Between January and July 2020, among 811 patients admitted to hospital with a diagnosis of COVID-19, the median age was 64 (interquartile range [IQR] 53-75) years, 495 (61.0%) were men, 46 (5.7%) were health care workers, 9 (1.1%) were pregnant, 26 (3.2%) were younger than 18 years and 9 (1.1%) were younger than 5 years. The median time from symptom onset to hospital admission was 7 (IQR 3-10) days. The most common symptoms on admission were fever, shortness of breath, cough and malaise. Diabetes, hypertension and cardiac, kidney and respiratory disease were the most common comorbidities. Among all patients, 328 received care in an ICU, admitted a median of 0 (IQR 0-1) days after hospital admission. Critically ill patients received treatment with invasive mechanical ventilation (88.8%), renal replacement therapy (14.9%) and extracorporeal membrane oxygenation (4.0%); 26.2% died. Among those receiving mechanical ventilation, 31.2% died. Age was an influential predictor of mortality (odds ratio per additional year of life 1.06, 95% confidence interval 1.03-1.09). INTERPRETATION: Patients admitted to hospital with COVID-19 commonly had fever, respiratory symptoms and comorbid conditions. Increasing age was associated with the development of critical illness and death; however, most critically ill patients in Canada, including those requiring mechanical ventilation, survived and were discharged from hospital.

Positive no-touch surfaces and undetectable SARS-CoV-2 aerosols in long-term care facilities: An attempt to understand the contributing factors and the importance of timing in air sampling campaigns.

BACKGROUND: Long-term care facilities (LTCF) are environments particularly favorable to coronavirus disease (SARS-CoV-2) pandemic outbreaks, due to the at-risk population they welcome and the close proximity of residents. Yet, the transmission dynamics of the disease in these establishments remain unclear. METHODS: Air and no-touch surfaces of 31 rooms from 7 LTCFs were sampled and SARS-CoV-2 was quantified by real-time reverse transcription polymerase chain reaction (RT-qPCR). RESULTS: Air samples were negative but viral genomes were recovered from 20 of 62 surface samples at concentrations ranging from 13 to 36,612 genomes/surface. Virus isolation (culture) from surface samples (n = 7) was negative. CONCLUSIONS: The presence of viral RNA on no-touch surfaces is evidence of viral dissemination through air, but the lack of airborne viral particles in air samples suggests that they were not aerosolized in a significant manner during air sampling sessions. The air samples were collected 8 to 30 days after the residents' symptom onset, which could indicate that viruses are aerosolized early in the infection process. Additional research is needed to evaluate viral viability conservation and the potential role of direct contact and aerosols in SARS-CoV-2 transmission in these institutions.

Simulation-Based Rapid Development and Implementation of a Novel Barrier Enclosure for Use in COVID-19 Patients: The SplashGuard CG.

BACKGROUND: The current COVID-19 pandemic has resulted in over 54,800,000 SARS-CoV-2 infections worldwide with a mortality rate of around 2.5%. As observed in other airborne viral infections such as influenza and SARS-CoV-1, healthcare workers are at high risk for infection when performing aerosol-generating medical procedures (AGMP). Additionally, the threats of a global shortage of standard personal protective equipment (PPE) prompted many healthcare workers to explore alternative protective enclosures, such as the "aerosol box" invented by a Taiwanese anesthetist. Our study includes the design process of a protective barrier enclosure and its subsequent clinical implementation in the management of critically ill adults and children infected with SARS-CoV-2. METHODS AND RESULTS: The barrier enclosure was designed for use in our tertiary care facility and named "SplashGuard CG" (CG for Care Givers). The device has been adapted using a multi- and interdisciplinary approach, with collaboration between physicians, respiratory therapists, nurses, and biomechanical engineers. Computer-aided design and simulation sessions throughout the entire process facilitated the rapid and safe implementation of the SplashGuard CG in different settings (intensive care unit, emergency department, and the operating room) during AGMPs such as bag-valve-mask ventilation, nasopharyngeal suctioning, intubation and extubation, and noninvasive ventilation. Indications for use and anticipatory precautions were communicated to all healthcare workers using the SplashGuard CG. The entire process was completed within one month. CONCLUSION: The rapid design, development, and clinical implementation of a new barrier enclosure, the "SplashGuard CG," was feasible in this time of crisis thanks to close collaboration between medical and engineering teams and the use of recurring simulation sessions to test and improve the initial prototypes. Following this accelerated process, it is necessary to maintain team skills, monitor any undesirable effects, and evaluate and continuously improve this new device.

Low incidence of airborne SARS-CoV-2 in acute care hospital rooms with optimized ventilation.

The worldwide repercussions of COVID-19 sparked important research efforts, yet the detailed contribution of aerosols in the transmission of SARS-CoV-2 has not been elucidated. In an attempt to quantify viral aerosols in the environment of infected patients, we collected 100 air samples in acute care hospital rooms hosting 22 patients over the course of nearly two months using three different air sampling protocols. Quantification by RT-qPCR (ORF1b) led to 11 positive samples from 6 patient rooms (Ct < 40). Viral cultures were negative. No correlation was observed between particular symptoms, length of hospital stay, clinical parameters, and time since symptom onset and the detection of airborne viral RNA. Low detection rates in the hospital rooms may be attributable to the appropriate application of mitigation methods according to the risk control hierarchy, such as increased ventilation to 4.85 air changes per hour to create negative pressure rooms. Our work estimates the mean emission rate of patients and potential airborne concentration in the absence of ventilation. Additional research is needed understand aerosolization events occur, contributing factors, and how best to prevent them.

Video Laryngoscope Intubation With an Aerosol Barrier Device: A Randomized Sequential Crossover Pilot Study.

OBJECTIVES: To assess the impact of the use of aerosol barrier device, Splashguard-CG, on the endotracheal intubation with different types of laryngoscope. DESIGN: A pilot randomized sequential crossover simulation study. SETTING: A single academic center in Japan. SUBJECTS: Physicians in a single academic university hospital in Japan. INTERVENTIONS: Use of Splashguard-CG. MEASUREMENTS AND MAIN RESULTS: All participants were asked to perform endotracheal intubation to a manikin simulator using three different devices (Macintosh laryngoscope; Airway Scope [Nihon Kohden, Tokyo, Japan]; and McGRATH MAC [Aircraft Medical, Edinburgh, United Kingdom]) with and without Splashguard-CG in place, which required a total of six attempts and measured the intubation time as the primary outcome. Thirty physicians (15 experienced physicians and 15 less-experienced physicians) were included. Intubation time using Macintosh laryngoscope was significantly longer in the group with Macintosh laryngoscope and Splashguard-CG compared with the group without Splashguard-CG by the median difference of 4.3 seconds (interquartile range, 2.6-7.4 s; p < 0.001). There was no significant increase in the intubation time with or without Splashguard-CG for the Airway Scope (0.6 s; interquartile range, -3.7 to 3.2 s; p = 0.97) and the McGRATH MAC (0.5 s; interquartile range, -1.4 to 4.6 s; p = 0.09). This trend was found in both the experienced and less-experienced groups. We observed significant increases of subjective difficulty of the endotracheal intubation evaluated by using a Visual Analog Scale in the Splashguard-CG groups for all three types of devices. CONCLUSIONS: The use of a video laryngoscope with an aerosol barrier device does not impact the time required endotracheal intubation in a simulation environment. This method can be considered as airway management for coronavirus disease 2019.

Comparison of two methods to clear the airways of critically ill children and adults with COVID-19 infection: a structured summary of a study protocol for a pilot randomized controlled trial.

OBJECTIVES: As there is no treatment for COVID-19 with a proven mortality benefit at this moment in the pandemic, supportive management including mechanical ventilation is the core management in an intensive care unit (ICU). It is a challenge to provide consistent care in this situation, highly demanding and leading to potential staff shortages in ICU. We need to reduce unnecessary exposure of healthcare workers to the virus. This study aims to examine the impact of care using a non-invasive oscillating device (NIOD) for chest physiotherapy in the care of mechanically ventilated patients with COVID-19. In particular, we aim to explore if a NIOD performed by non-specialized personnel is not inferior to the standard chest physiotherapy (CPT) undertaken by physiotherapists caring for patients with COVID-19. TRIAL DESIGN: A pilot multicenter prospective crossover noninferiority randomized controlled trial. PARTICIPANTS: All mechanically ventilated patients with COVID-19 admitted to one of the two ICUs, and CPT ordered by the responsible physician. The participants will be recruited from two intensive care units in Canadian Academic Hospitals (one pediatric and one adult ICU). INTERVENTION AND COMPARATOR: We will implement NIOD and CPT alternatingly for 3 h apart over 3 h. We will apply a pragmatic design, so that other procedures including hypertonic saline nebulization, intermittent positive pressure ventilation, suctioning (e.g., oral or nasal), or changing the ventilator settings or modality (i.e., increasing positive end-expiratory pressure or changing the nasal mask to total face continuous positive airway pressure) can be provided at the direction of bedside intensivists in charge. MAIN OUTCOMES: The primary outcome measurement is the oxygenation level before and after the procedure (SpO2/FiO2 ratio). For cases with invasive ventilation (i.e., the use of an endotracheal tube to deliver positive pressure) and non-invasive ventilation, we will also document expiratory tidal volume, vital signs, and any related complications such as vomiting, hypoxemia, or unexpected extubation. We will collect the data before, 10 min after, and 30 min after the procedure. RANDOMIZATION: The order of the procedures (i.e., NIOD or CPT) will be randomly allocated using manual generated random numbers for each case. Randomization will be carried out by the independent research assistant in the study coordinating center by using opaque sealed envelopes, assigning an equal number of cases to each intervention arm. Stratification will be applied for age (> 18 years or ≤ 18 years of age) and the study sites. BLINDING (MASKING): No blinding will be performed. NUMBERS TO BE RANDOMIZED (SAMPLE SIZE): We estimate the necessary sample size as 25 for each arm (total 50 cases), with a power of 0.90 and an alpha of 0.05, with a non-inferiority design. TRIAL STATUS: The protocol version number 1 was approved on 27 March 2020. Currently, recruitment has not yet started, with the start scheduled by the mid-June 2020 and the end anticipated by December 2020. TRIAL REGISTRATION: ClinicalTrials.gov NCT04361435 . Registered on 28 April 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.