Oxygenation index outperforms the P/F ratio for mortality prediction

Davies, KJ; Bourdeaux, Chris; Peiris, T.S.G.; Gould, T

doi:10.1186/cc13456

Cited by 3 publications

(3 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Different ventilatory parameters were found to be associated with mortality in previous studies. High driving pressures and tidal volumes, as well as low oxygenation indices were shown to be associated with higher mortality in mechanically ventilated patients, especially in individuals with acute respiratory distress syndrome (ARDS) in multiple previous studies [31][32][33][34][35][36]. It therefore seemed reasonable to combine various key ventilation parameters as mortality predictors in our ML model.…”

Section: Discussionmentioning

confidence: 99%

Machine learning predicts mortality based on analysis of ventilation parameters of critically ill patients: multi-centre validation

Mamandipoor

Frutos‐Vivar

Peñuelas

et al. 2021

BMC Med Inform Decis Mak

View full text Add to dashboard Cite

Background Mechanical Ventilation (MV) is a complex and central treatment process in the care of critically ill patients. It influences acid–base balance and can also cause prognostically relevant biotrauma by generating forces and liberating reactive oxygen species, negatively affecting outcomes. In this work we evaluate the use of a Recurrent Neural Network (RNN) modelling to predict outcomes of mechanically ventilated patients, using standard mechanical ventilation parameters. Methods We performed our analysis on VENTILA dataset, an observational, prospective, international, multi-centre study, performed to investigate the effect of baseline characteristics and management changes over time on the all-cause mortality rate in mechanically ventilated patients in ICU. Our cohort includes 12,596 adult patients older than 18, associated with 12,755 distinct admissions in ICUs across 37 countries and receiving invasive and non-invasive mechanical ventilation. We carry out four different analysis. Initially we select typical mechanical ventilation parameters and evaluate the machine learning model on both, the overall cohort and a subgroup of patients admitted with respiratory disorders. Furthermore, we carry out sensitivity analysis to evaluate whether inclusion of variables related to the function of other organs, improve the predictive performance of the model for both the overall cohort as well as the subgroup of patients with respiratory disorders. Results Predictive performance of RNN-based model was higher with Area Under the Receiver Operating Characteristic (ROC) Curve (AUC) of 0.72 (± 0.01) and Average Precision (AP) of 0.57 (± 0.01) in comparison to RF and LR for the overall patient dataset. Higher predictive performance was recorded in the subgroup of patients admitted with respiratory disorders with AUC of 0.75 (± 0.02) and AP of 0.65 (± 0.03). Inclusion of function of other organs further improved the performance to AUC of 0.79 (± 0.01) and AP 0.68 (± 0.02) for the overall patient dataset and AUC of 0.79 (± 0.01) and AP 0.72 (± 0.02) for the subgroup with respiratory disorders. Conclusion The RNN-based model demonstrated better performance than RF and LR in patients in mechanical ventilation and its subgroup admitted with respiratory disorders. Clinical studies are needed to evaluate whether it impacts decision-making and patient outcomes. Trial registration: NCT02731898 (https://clinicaltrials.gov/ct2/show/NCT02731898), prospectively registered on April 8, 2016.

show abstract

Section: Discussionmentioning

confidence: 99%

Machine learning predicts mortality based on analysis of ventilation parameters of critically ill patients: multi-centre validation

Mamandipoor

Frutos‐Vivar

Peñuelas

et al. 2021

BMC Med Inform Decis Mak

View full text Add to dashboard Cite

show abstract

“…K Davies et al [ 12 ] in their study compared the predictive performance of OI and P/F for mortality and found that OI performs better for the prediction of mortality in ventilated patients (area under receiver operating curve 0.840 vs. 0.822). Another study on mechanically ventilated neonates with invasive e identified a significant correlation of 0.91 between the OSI and OI in neonates with hypoxemic respiratory failure, and it has the potential to be used, both in clinical management and research, to quantify the severity of lung disease.…”

Section: Discussionmentioning

confidence: 99%

Correlation of oxygenation indices in invasive mechanical ventilated adult patients

Jain,

Jain

et al. 2024

Lung India

View full text Add to dashboard Cite

Background: Mechanical ventilation is essential for managing acute respiratory failure, but traditional methods of assessing oxygenation, like the PaO2/FiO2 ratio, pose challenges due to invasiveness and cost. Objective: This single-centre prospective observational study aimed to assess the potential of the non-invasive Oxygen Saturation Index (OSI), utilising SpO2 measurements, to diagnose hypoxemia in mechanically ventilated adults. The study sought to establish correlations between OSI, oxygenation index (OI), PaO2/FiO2 ratio and SpO2/FiO2 ratio. Methods: From August 2022 to July 2023, data was collected from 1055 mechanically ventilated intensive care unit patients. Statistical analysis included correlation tests, receiver operating curve (ROC) analysis and cut-off value determination for hypoxemia diagnosis. Results: We found that the P/F ratio had a statistically significant negative correlation with OI (correlation coefficient -0.832, P value: 0.000 in hypoxemic group and correlation coefficient -0.888, P value: 0.000 in the non-hypoxemic group), and OSI (correlation coefficient -0.746, P value: 0.000 in hypoxemic group and correlation coefficient -0.629, P value: 0.000 in non-hypoxemic group) and has a positive correlation with P/F ratio (correlation coefficient 0.92, P value: 0.000 in hypoxemic group and correlation coefficient -0.67, P value: 0.000 in non-hypoxemic group). OI and OSI had a statistically significant correlation (correlation coefficient 0.955, P value: 0.000 in hypoxemic group and correlation coefficient 0.815, P value: 0.000 in non-hypoxemic group). on ROC analysis P/F ratio was the most accurate in predicting hypoxia followed by OI and OSI. with a cut-off value, of OI being 7.07, and that for OSI being 3.90, at an 80% sensitivity level to diagnose hypoxemia. Conclusion: OSI can serve as a dependable surrogate for OI, simplifying ARDS severity assessment. The P/F ratio is the most accurate predictor of hypoxia. Further research, especially in larger multicentre studies, is needed to validate these findings and explore the long-term clinical implications of using OSI for oxygenation monitoring in mechanically ventilated patients.

show abstract

“…However, it is independent of the mean airway pressure during mechanical ventilation. In contrast, the OI is considered to be a better index to assess the severity and guide the treatment of hypoxic respiratory failure in children [19][20][21]. All the respiratory parameters studied showed significant improvement in the first few hours after initiation of HFOV, wherein oxygen indices improved while airway pressures decreased.…”

Section: Discussionmentioning

confidence: 99%

High-frequency oscillatory ventilation for respiratory failure after congenital heart surgery: a retrospective analysis

Kumar¹,

Joshi²,

Parikh³

et al. 2023

ait

View full text Add to dashboard Cite

Pulmonary complications are a major cause of morbidity and mortality in children undergoing cardiac surgery [1]. Refractory respiratory failure due to various causes remains challenging to manage as conventional mechanical ventilation fails. Management of patients developing acute respiratory distress syndrome (ARDS) has been researched extensively and keeps changing. The outcome of paediatric ARDS (PARDS) is still disappointing despite implementation of several lung protective techniques [2,3]. Around 3.2-8.4% of paediatric patients undergoing congenital heart surgery are put on extracorporeal membrane oxygenation (ECMO) support due to cardiorespiratory failure. ECMO is often less favoured than conventional therapy due to its high costs and complication rates. Moreover, the decision to institute ECMO is mainly empirical,

show abstract

Oxygenation index outperforms the P/F ratio for mortality prediction

Cited by 3 publications

References 2 publications

Machine learning predicts mortality based on analysis of ventilation parameters of critically ill patients: multi-centre validation

Machine learning predicts mortality based on analysis of ventilation parameters of critically ill patients: multi-centre validation

Correlation of oxygenation indices in invasive mechanical ventilated adult patients

High-frequency oscillatory ventilation for respiratory failure after congenital heart surgery: a retrospective analysis

Contact Info

Product

Resources

About