Intubation Timing in COVID-19 Based on ROX Index and Association With Patient Outcomes

Vest, Michael T.; Caplan, Richard; Fawcett, Mitch; Deitchman, Andrew; Valentino, Dominic; Gajera, Mithil; Jurkovitz, Claudine

doi:10.4187/respcare.09937

Cited by 7 publications

(6 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Specifically, our findings suggest that combination therapy with different classes of drugs is more effective than therapy with only a single agent. These models also demonstrate that patient characteristics and comorbidities such as age, kidney, liver, heart disease, and severity of illness at diagnosis have a large impact on disease outcome, confirming previous literature [25][26][27][28][29]. Indeed, the models suggest that for COVID-19 outcomes, patient characteristics are not surprisingly often as influential as the treatments administered.…”

Section: Plos Onesupporting

confidence: 84%

Assessing the effects of therapeutic combinations on SARS-CoV-2 infected patient outcomes: A big data approach

Moradi¹,

Bunnell²,

Price³

et al. 2023

PLoS ONE

View full text Add to dashboard Cite

Background The COVID-19 pandemic has demonstrated the need for efficient and comprehensive, simultaneous assessment of multiple combined novel therapies for viral infection across the range of illness severity. Randomized Controlled Trials (RCT) are the gold standard by which efficacy of therapeutic agents is demonstrated. However, they rarely are designed to assess treatment combinations across all relevant subgroups. A big data approach to analyzing real-world impacts of therapies may confirm or supplement RCT evidence to further assess effectiveness of therapeutic options for rapidly evolving diseases such as COVID-19. Methods Gradient Boosted Decision Tree, Deep and Convolutional Neural Network classifiers were implemented and trained on the National COVID Cohort Collaborative (N3C) data repository to predict the patients’ outcome of death or discharge. Models leveraged the patients’ characteristics, the severity of COVID-19 at diagnosis, and the calculated proportion of days on different treatment combinations after diagnosis as features to predict the outcome. Then, the most accurate model is utilized by eXplainable Artificial Intelligence (XAI) algorithms to provide insights about the learned treatment combination impacts on the model’s final outcome prediction. Results Gradient Boosted Decision Tree classifiers present the highest prediction accuracy in identifying patient outcomes with area under the receiver operator characteristic curve of 0.90 and accuracy of 0.81 for the outcomes of death or sufficient improvement to be discharged. The resulting model predicts the treatment combinations of anticoagulants and steroids are associated with the highest probability of improvement, followed by combined anticoagulants and targeted antivirals. In contrast, monotherapies of single drugs, including use of anticoagulants without steroid or antivirals are associated with poorer outcomes. Conclusions This machine learning model by accurately predicting the mortality provides insights about the treatment combinations associated with clinical improvement in COVID-19 patients. Analysis of the model’s components suggests benefit to treatment with combination of steroids, antivirals, and anticoagulant medication. The approach also provides a framework for simultaneously evaluating multiple real-world therapeutic combinations in future research studies.

show abstract

Section: Plos Onesupporting

confidence: 84%

Assessing the effects of therapeutic combinations on SARS-CoV-2 infected patient outcomes: A big data approach

Moradi¹,

Bunnell²,

Price³

et al. 2023

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…These results were confirmed in a sub-analysis of FLORALI [7]. The ROX score was also retrospectively studied in a cohort of patients with COVID-19, which confirmed that increasing ROX index score at the time of intubation was associated with greater survival [55].…”

Section: Ventilatory Management Of Respiratory Failure Caused By Sars...supporting

confidence: 60%

Ventilatory Management of Patients with Acute Respiratory Distress Syndrome Due to SARS-CoV-2

Jacquier,

Labruyère,

Ecarnot

et al. 2023

JCM

View full text Add to dashboard Cite

The emergence of the new SARS-CoV-2 in December 2019 caused a worldwide pandemic of the resultant disease, COVID-19. There was a massive surge in admissions to intensive care units (ICU), notably of patients with hypoxaemic acute respiratory failure. In these patients, optimal oxygen therapy was crucial. In this article, we discuss tracheal intubation to provide mechanical ventilation in patients with hypoxaemic acute respiratory failure due to SARS-CoV-2. We first describe the pathophysiology of respiratory anomalies leading to acute respiratory distress syndrome (ARDS) due to infection with SARS-CoV-2, and then briefly review management, focusing particularly on the ventilation strategy. Overall, the ventilatory management of ARDS due to SARS-CoV-2 infection is largely the same as that applied in ARDS from other causes, and lung-protective ventilation is recommended. The difference lies in the initial clinical presentation, with profound hypoxaemia often observed concomitantly with near-normal pulmonary compliance.

show abstract

“…The target saturation range of 92%-96% used in practice was derived from data in ARDS patients, in whom both low saturations (<92%) [61] and high saturations (>96%) [204] are detrimental. Reduced peripheral oxygen saturation acts as both a risk factor for intubation [205][206][207] and a guide to the timing of assisted ventilation [208,209]. Moreover, after COVID-19 patients have been intubated, further declines in oxygenation continue to be predictive of mortality risk [210], and improvements in saturation readings can act as a guide to the effectiveness of prone ventilation therapy [211].…”

Section: Peripheral Oxygen Saturationmentioning

confidence: 99%

Effective prognostic and clinical risk stratification in COVID‐19 using multimodality biomarkers

et al. 2023

View full text Add to dashboard Cite

In acute coronavirus disease 19 (COVID‐19) patients, effective clinical risk stratification has important implications on treatment and therapeutic resource distribution. This article reviews the evidence behind a wide range of biomarkers with prognostic value in COVID‐19. Patient characteristics and co‐morbidities, such as cardiovascular and respiratory diseases, are associated with increased mortality risk. Peripheral oxygen saturation and arterial oxygenation are predictive of severe respiratory compromise, whereas risk scores such as the 4C‐score enable multi‐factorial prognostic risk estimation. Blood tests such as markers of inflammation, cardiac injury and d‐dimer and abnormalities on electrocardiogram are linked to inpatient prognosis. Of the imaging modalities, lung ultrasound and echocardiography enable the bedside assessment of prognostic abnormalities in COVID‐19. Chest radiograph (CXR) and computed tomography (CT) can inform about prognostic pulmonary pathologies, whereas cardiovascular CT detects high‐risk features such as coronary artery and aortic calcification. Dynamic changes in biomarkers, such as blood tests, CXR, CT and electrocardiogram findings, can further inform about disease severity and prognosis. Despite the vast volumes of existing evidence, several gaps exist in our understanding of COVID‐19 biomarkers. First, the pathophysiological basis on which these markers can foretell prognosis in COVID‐19 remains poorly understood. Second, certain under‐explored tests such as thoracic impedance assessment and cardiovascular magnetic resonance imaging deserve further investigation. Lastly, the prognostic values of most biomarkers in COVID‐19 are derived from retrospective analyses. Prospective studies are required to validate these markers for guiding clinical decision‐making and to facilitate their translation into clinical management pathways.

show abstract

Intubation Timing in COVID-19 Based on ROX Index and Association With Patient Outcomes

Cited by 7 publications

References 47 publications

Assessing the effects of therapeutic combinations on SARS-CoV-2 infected patient outcomes: A big data approach

Assessing the effects of therapeutic combinations on SARS-CoV-2 infected patient outcomes: A big data approach

Ventilatory Management of Patients with Acute Respiratory Distress Syndrome Due to SARS-CoV-2

Effective prognostic and clinical risk stratification in COVID‐19 using multimodality biomarkers

Contact Info

Product

Resources

About