The use of the pulse oximetric saturation to fraction of inspired oxygen ratio in an automated acute respiratory distress syndrome screening tool

Pulse oximetry for the diagnosis and management of acute respiratory distress syndrome

The diagnosis of acute respiratory distress syndrome (ARDS) traditionally requires calculation of the ratio of partial pressure of arterial oxygen to fraction of inspired oxygen (PaO2/FiO2) using arterial blood, which can be costly and is not possible in many resource-limited settings. By contrast, pulse oximetry is continuously available, accurate, inexpensive, and non-invasive. Pulse oximetry-based indices, such as the ratio of pulse-oximetric oxygen saturation to FiO2 (SpO2/FiO2), have been validated in clinical studies for the diagnosis and risk stratification of patients with ARDS. Limitations of the SpO2/FiO2 ratio include reduced accuracy in poor perfusion states or above oxygen saturations of 97%, and the potential for reduced accuracy in patients with darker skin pigmentation. Application of pulse oximetry to the diagnosis and management of ARDS, including formal adoption of the SpO2/FiO2 ratio as an alternative to PaO2/FiO2 to meet the diagnostic criterion for hypoxaemia in ARDS, could facilitate increased and earlier recognition of ARDS worldwide to advance both clinical practice and research.

Development of a severity of disease score and classification model by machine learning for hospitalized COVID-19 patients

BACKGROUND

Efficient and early triage of hospitalized Covid-19 patients to detect those with higher risk of severe disease is essential for appropriate case management.

METHODS

We trained, validated, and externally tested a machine-learning model to early identify patients who will die or require mechanical ventilation during hospitalization from clinical and laboratory features obtained at admission. A development cohort with 918 Covid-19 patients was used for training and internal validation, and 352 patients from another hospital were used for external testing. Performance of the model was evaluated by calculating the area under the receiver-operating-characteristic curve (AUC), sensitivity and specificity.

RESULTS

A total of 363 of 918 (39.5%) and 128 of 352 (36.4%) Covid-19 patients from the development and external testing cohort, respectively, required mechanical ventilation or died during hospitalization. In the development cohort, the model obtained an AUC of 0.85 (95% confidence interval [CI], 0.82 to 0.87) for predicting severity of disease progression. Variables ranked according to their contribution to the model were the peripheral blood oxygen saturation (SpO2)/fraction of inspired oxygen (FiO2) ratio, age, estimated glomerular filtration rate, procalcitonin, C-reactive protein, updated Charlson comorbidity index and lymphocytes. In the external testing cohort, the model performed an AUC of 0.83 (95% CI, 0.81 to 0.85). This model is deployed in an open source calculator, in which Covid-19 patients at admission are individually stratified as being at high or non-high risk for severe disease progression.

CONCLUSIONS

This machine-learning model, applied at hospital admission, predicts risk of severe disease progression in Covid-19 patients.

Biomarkers of acute respiratory distress syndrome in adults hospitalised for severe SARS-CoV-2 infection in Tenerife Island, Spain

OBJECTIVE

The dramatic spread of SARS-CoV-2 infections calls for reliable, inexpensive tools to quickly identify patients with a poor prognosis. In this study, acute respiratory distress syndrome (ARDS) was assessed within 72 h after admission of each of 153 consecutive, SARS-CoV-2 infected, adult patients to either of two hospitals in Tenerife, Spain, using suitable routine laboratory tests for lymphocyte counts, as well as ferritin, lactate dehydrogenase (LDH), and C-reactive protein levels. Results were correlated with the patients' respiratory function, defined through their pulse oximetric saturation/fraction of inspired oxygen (SpO2/FiO2) ratio.

RESULTS

Within 72 h from admission, criteria matched ARDS (SpO2/FiO2 < 235) in 13.1% of cases. We found a significant, negative correlation between SpO2/FiO2 ratios and D-dimer, ferritin, and LDH levels (- 0.31, - 0.32, and - 0.41; p = 0.004, 0.004, and < 0.0001, respectively). In patients with ARDS, the mean LDH was 373 U/L (CI95%: 300.6-445.3), but only 298 U/L (CI95%: 274.7-323.1) when they did not develop the syndrome (p = 0.015). None of the additionally evaluated biomarkers correlated with the SpO2/FiO2 ratios. Serum LDH levels in patients hospitalised for COVID-19 correlate with ARDS, as defined by their SpO2/FiO2 ratio, and might help to predict said complication.

External Validity of Electronic Sniffers for Automated Recognition of Acute Respiratory Distress Syndrome

INTRODUCTION

Automated electronic sniffers may be useful for early detection of acute respiratory distress syndrome (ARDS) for institution of treatment or clinical trial screening.

METHODS

In a prospective cohort of 2929 critically ill patients, we retrospectively applied published sniffer algorithms for automated detection of acute lung injury to assess their utility in diagnosis of ARDS in the first 4 ICU days. Radiographic full-text reports were searched for "edema" OR ("bilateral" AND "infiltrate") and a more detailed algorithm for descriptions consistent with ARDS. Patients were flagged as possible ARDS if a radiograph met search criteria and had a PaO₂/FiO₂ or SpO₂/FiO₂ of 300 or 315, respectively. Test characteristics of the electronic sniffers and clinical suspicion of ARDS were compared to a gold standard of 2-physician adjudicated ARDS.

RESULTS

Thirty percent of 2841 patients included in the analysis had gold standard diagnosis of ARDS. The simpler algorithm had sensitivity for ARDS of 78.9%, specificity of 52%, positive predictive value (PPV) of 41%, and negative predictive value (NPV) of 85.3% over the 4-day study period. The more detailed algorithm had sensitivity of 88.2%, specificity of 55.4%, PPV of 45.6%, and NPV of 91.7%. Both algorithms were more sensitive but less specific than clinician suspicion, which had sensitivity of 40.7%, specificity of 94.8%, PPV of 78.2%, and NPV of 77.7%.

CONCLUSIONS

Published electronic sniffer algorithms for ARDS may be useful automated screening tools for ARDS and improve on clinical recognition, but they are limited to screening rather than diagnosis because their specificity is poor.