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

Abstract

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.

Personalized mechanical ventilation in acute respiratory distress syndrome

“…For example, adaptive support ventilation, an automated closed-loop mode of ventilation, provides the best combination of V T and respiratory rate (RR), to achieve the lowest work of breathing combined with the lowest driving pressure (Δ P ) and may outperform healthcare professionals with respect to V T titration [ 13 ]. Finally, the use of artificial intelligence to develop a personalized clinical decision support tool could provide needed support to bedside clinicians [ 14 ].…”

Management of intoxicated patients – a descriptive outcome analysis of 4,267 ICU patients

“…In contrast, significantly more mechanically ventilated patients were found in the "sedatives" and "street drugs" subgroups, with these individuals again contributing the highest numerical proportion of non-survivors. This possibly underlines the need for reversibility of intoxication, as mechanical ventilation per se is a known and relatively invasive ICU measure and independent predictor of ICU mortality [ 24 ].…”

A Survey on Medical Explainable AI (XAI): Recent Progress, Explainability Approach, Human Interaction and Scoring System

“…Machine learning has shown to identify the stage and level of AKI, which has helped to apply proper medication treatment, recovery for the mild and control the severe conditions. In case of comorbidities or critical conditions, the hospital mortality is thought to be an important prediction [ 41 ]. There are more features available for such cases, as it involves distinct ICU parameters.…”