Predicting Length of Mechanical Ventilation in Moderate-to-severe Acute Respiratory Distress Syndrome Using Machine Learning
Predicting Length of Mechanical Ventilation in Moderate-to-severe Acute Respiratory Distress Syndrome Using Machine Learning
The investigators are planning to perform a secondary analysis of an academic dataset of 1,303 patients with moderate-to-severe acute respiratory distress syndrome (ARDS) included in several published cohorts (NCT00736892, NCT022288949, NCT02836444, NCT03145974), aimed to characterize the best early scenario during the first three days of diagnosis to predict duration of mechanical ventilation in the intensive care unit (ICU) using supervised machine learning (ML) approaches.
The acute respiratory distress syndrome (ARDS) is an important cause of morbidity, mortality, and costs in intensive care units (ICUs) worldwide. Most ARDS patients require mechanical ventilation (MV). Few studies have investigated the prediction of MV duration of ARDS.
For model description and testing, the investigators will extract data from he first three ICU days after diagnosis of moderate-to-severe ARDS from patients included in the de-identified database, which includes 1,000 mechanically ventilated patients enrolled in several observational cohorts in Spain, coordinated by the principal investigator (JV), and funded by the Instituto de Salud Carlos III (ISCIII). The investigators will follow the TRIPOD guidelines and machine learning techniques will be implemented [Random Forest (RF), eXtreme Gradient Boosting (XGBoost), and Logistic regression analysis) for the development and accuracy of prediction models. Disease progression will be tracked along those 3 ICU days to assess lung severity according to Berlin criteria. For external validation, the investigators will use 303 patients enrolled in a contemporary observational study (NCT03145974). The investigators will evaluate the accuracy of prediction models by calculation several statistics, such as sensitivity, specificity, positive predictive value, negative value for each model. The investigators will select the best early prediction model with data captured on the 1st, 2nd, or 3rd day.
Inclusion Criteria:
Exclusion Criteria: