Prediction of Non-invasive Mechanical Ventilation Response. Moving from Art to Science?

Predicting the outcome from NIV is important and the study by Martin-Gonzalez and colleagues applies data mining techniques to improve our understanding of the field. Nevertheless, the predictor variables must be robust and reliably available before NIV is applied. A predictive model must be generalisable in other clinical settings. Until models such as this are extremely robust in their predictive ability and have been shown to positively influence patient centered outcomes, they may be able to assist decision making but cannot replace clinical judgement by an experienced bedside clinician.