Objective
To evaluate whether the initial chest X-ray (CXR) severity assessed by an AI system may have prognostic utility in patients with COVID-19.
Methods
This retrospective single-center study ...included adult patients presenting to the emergency department (ED) between February 25 and April 9, 2020, with SARS-CoV-2 infection confirmed on real-time reverse transcriptase polymerase chain reaction (RT-PCR). Initial CXRs obtained on ED presentation were evaluated by a deep learning artificial intelligence (AI) system and compared with the Radiographic Assessment of Lung Edema (RALE) score, calculated by two experienced radiologists. Death and critical COVID-19 (admission to intensive care unit (ICU) or deaths occurring before ICU admission) were identified as clinical outcomes. Independent predictors of adverse outcomes were evaluated by multivariate analyses.
Results
Six hundred ninety-seven 697 patients were included in the study: 465 males (66.7%), median age of 62 years (IQR 52–75). Multivariate analyses adjusting for demographics and comorbidities showed that an AI system-based score ≥ 30 on the initial CXR was an independent predictor both for mortality (HR 2.60 (95% CI 1.69 − 3.99;
p
< 0.001)) and critical COVID-19 (HR 3.40 (95% CI 2.35–4.94;
p
< 0.001)). Other independent predictors were RALE score, older age, male sex, coronary artery disease, COPD, and neurodegenerative disease.
Conclusion
AI- and radiologist-assessed disease severity scores on CXRs obtained on ED presentation were independent and comparable predictors of adverse outcomes in patients with COVID-19.
Trial registration
ClinicalTrials.gov
NCT04318366 (
https://clinicaltrials.gov/ct2/show/NCT04318366
).
Key Points
• AI system–based score ≥ 30 and a RALE score ≥ 12 at CXRs performed at ED presentation are independent and comparable predictors of death and/or ICU admission in COVID-19 patients.
• Other independent predictors are older age, male sex, coronary artery disease, COPD, and neurodegenerative disease.
• The comparable performance of the AI system in relation to a radiologist-assessed score in predicting adverse outcomes may represent a game-changer in resource-constrained settings.
We suggest the use of MicroCLOTS (microvascular COVID-19 lung vessels obstructive thromboinflammatory syndrome) as a new name for severe pulmonary coronavirus disease 2019 (COVID-19). We hypothesise ...that, in predisposed individuals, alveolar viral damage is followed by an inflammatory reaction and by microvascular pulmonary thrombosis. This progressive endothelial thromboinflammatory syndrome may also involve the microvascular bed of the brain and other vital organs, leading to multiple organ failure and death. Future steps in the understanding of the disease and in the identification of treatments may benefit from this definition and hypothesised sequence of events.
Data on residual clinical damage after Coronavirus disease-2019 (COVID-19) are lacking. The aims of this study were to investigate whether COVID-19 leaves behind residual dysfunction, and identify ...patients who might benefit from post-discharge monitoring. All patients aged ≥18 years admitted to the Emergency Department (ED) for COVID-19, and evaluated at post-discharge follow-up between 7 April and 7 May, 2020, were enrolled. Primary outcome was need of follow-up, defined as the presence at follow-up of at least one among: respiratory rate (RR) >20 breaths/min, uncontrolled blood pressure (BP) requiring therapeutic change, moderate to very severe dyspnoea, malnutrition, or new-onset cognitive impairment, according to validated scores. Post-traumatic stress disorder (PTSD) served as secondary outcome. 185 patients were included. Median interquartile range time from hospital discharge to follow-up was 23 20-29 days. 109 (58.9%) patients needed follow-up. At follow-up evaluation, 58 (31.3%) patients were dyspnoeic, 41 (22.2%) tachypnoeic, 10 (5.4%) malnourished, 106 (57.3%) at risk for malnutrition. Forty (21.6%) patients had uncontrolled BP requiring therapeutic change, and 47 (25.4%) new-onset cognitive impairment. PTSD was observed in 41 (22.2%) patients. At regression tree analysis, the ratio of arterial oxygen partial pressure to fractional inspired oxygen (PaO2/FiO2) and body mass index (BMI) at ED presentation, and age emerged as independent predictors of the need of follow-up. Patients with PaO2/FiO2 <324 and BMI ≥33 Kg/m2 had the highest odds to require follow-up. Among hospitalised patients, age ≥63 years, or age <63 plus non-invasive ventilation or diabetes identified those with the highest probability to need follow-up. PTSD was independently predicted by female gender and hospitalisation, the latter being protective (odds ratio, OR, 4.03, 95% confidence interval, CI, 1.76 to 9.47, p 0.0011; OR 0.37, 95% CI 0.14 to 0.92, p 0.033, respectively). COVID-19 leaves behind physical and psychological dysfunctions. Follow-up programmes should be implemented for selected patients.
In addition to the directly attributed mortality, COVID-19 is also likely to increase mortality indirectly. In this systematic review, we investigate the direct and indirect effects of COVID-19 on ...out-of-hospital cardiac arrests.
We searched PubMed, BioMedCentral, Embase and the Cochrane Central Register of Controlled Trials for studies comparing out-of-hospital cardiac arrests occurring during the pandemic and a non-pandemic period. Risk of bias was assessed with the ROBINS-I tool. The primary endpoint was return of spontaneous circulation. Secondary endpoints were bystander-initiated cardiopulmonary resuscitation, survival to hospital discharge, and survival with favourable neurological outcome.
We identified six studies. In two studies, rates of return of spontaneous circulation and survival to hospital discharge decreased significantly during the pandemic. Especially in Europe, bystander-witnessed cases, bystander-initiated cardiopulmonary resuscitation and resuscitation attempted by emergency medical services were reduced during the pandemic. Also, ambulance response times were significantly delayed across all studies and patients presenting with non-shockable rhythms increased in two studies. In 2020, 3.9–5.9% of tested patients were SARS-CoV-2 positive and 4.8–26% had suggestive symptoms (fever and cough or dyspnoea).
Out-of-hospital cardiac arrests had worse short-term outcomes during the pandemic than a non-pandemic period suggesting direct effects of COVID-19 infection and indirect effects from lockdown and disruption of healthcare systems. Patients at high risk of deterioration should be identified outside the hospital to promptly initiate treatment and reduce fatalities.
Study registration PROSPERO CRD42020195794.
Of the various muscles that make up the respiratory system, the diaphragm is the prima donna. In the past, only specialist research centers were able to estimate and challenge the effort of this ...muscle; this was achieved by measuring transdiaphragmatic pressure—an invasive technique involving a double-balloon probe inserted through the esophagus—or by measuring twitch pressure (ie, the pressure generated at the outside tip of the endotracheal tube). However, the prevalence of diaphragm dysfunction in critically ill patients requiring intubation can exceed 60% (at the time of hospital admission) and may rise to as high as 80% in patients requiring prolonged mechanical ventilation and experiencing difficult weaning.
Although still in its infancy, modern ultrasound (US) provides a fascinating way to study the diaphragm, permitting the assessment of its excursion, thickness, and thickening. Furthermore, US enables the course of diaphragmatic function to be followed on a day-to-day basis, from intensive care admission to discharge, and it can help us understand the different causes of underlying disease: trauma, infection (eg, sepsis-induced diaphragm dysfunction), cancer, weaning problems (eg, ventilation-induced diaphragm dysfunction), etc. Today, the assessment of diaphragm dysfunction with US provides an important first step toward improving the detection of diaphragm dysfunction and as a protective and supportive strategy for its management. The purposes of this review are as follows: (1) to explore which US method is best for evaluating diaphragm function in the intensive care unit and how and when it should be used, and (2) to discuss which diseases may involve the diaphragm, and what therapies should be used.
Alarms from monitors, medical devices and staff activities increase noise levels in the Intensive Care Unit (ICU) and may disrupt sleep patterns 1 contributing to the development of delirium and ...post-intensive care syndrome 2. The World Health Organization (WHO) recommend that hospital noise levels should not exceed 35 A-weighted decibels (dBA) during the day and 30 dBA at night 3. ...we exported Health data from the personal Apple Watch of a nurse working in a 14 beds referral cardiothoracic ICU managing patients after cardiac surgery and those with cardiogenic shock, refractory cardiac arrest, and respiratory failure.
Mechanical ventilation contributes to diaphragmatic atrophy and dysfunction, and few techniques exist to assess diaphragmatic function: the purpose of this study was to quantify diaphragm atrophy in ...a population of critically ill mechanically ventilated patients with ultrasound and to identify risk factors that can worsen diaphragmatic activity.
Prospective observational study.
ICU of a 1,200-bed university hospital.
Newly intubated adult critically ill patients.
Diaphragm thickness in the zone of apposition was measured daily with ultrasound, from the first day of mechanical ventilation till discharge to the main ward.
Daily atrophy rate (ΔTdi/d) was calculated as the reduction in percentage from the previous measurement. To analyze the difference in atrophy rate (ΔTdi/d), ventilation was categorized into four classes: spontaneous breathing or continuous positive airway pressure; pressure support ventilation 5-12 cm H2O (low pressure support ventilation); pressure support ventilation greater than 12 cm H2O (high pressure support ventilation); and controlled mechanical ventilation. Multivariate analysis with ventilation support and other clinical variables was performed to identify risk factors for atrophy. Forty patients underwent a total of 153 ultrasonographic evaluations. Mean (SD) ΔTdi/d was -7.5% (12.3) during controlled mechanical ventilation, -5.3% (12.9) at high pressure support ventilation, -1.5% (10.9) at low pressure support ventilation, +2.3% (9.5) during spontaneous breathing or continuous positive airway pressure. At multivariate analysis, only the ventilation support was predictive of diaphragm atrophy rate. Pressure support predicted diaphragm thickness with coefficient -0.006 (95% CI, -0.010 to -0.002; p = 0.006).
In critically ill mechanically ventilated patients, there is a linear relationship between ventilator support and diaphragmatic atrophy rate.