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

Summary

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.

Keywords

Non-invasive ventilation (NIV) - failure - predictive models - multiclassifiers

• References

• 1 Moreno Garcia MN, Martin-González F, González-Robledo J, Sánchez-Hernández F, MorenoGarcía MN. Success/Failure Prediction of Noninvasive Mechanical Ventilation in Intensive Care Units*. Using Multiclassifiers and Feature Selection Methods. Methods Inf Med 2015; 30: 54 (20150430). [Epub ahead of print] PubMed PMID: 25925616.
• 2 Ambrosino N, Vagheggini G. Noninvasive positive pressure ventilation in the acute care setting: where are we?. Eur Respir J 2008; 31: 874-886.
• 3 Thille AW, Contou D, Fragnoli C. et al. Non invasive ventilation for acute hypoxemic respiratory failure: intubation rate and risk factors. Critical Care 2013; 17: R269.
• 4 Ozyilmaz E, Ugurlu AO, Nava S. Timing of noninvasive ventilation failure: causes, risk factors, and potential remedies. BMC Pulm Med 2014; 14: 19.
• 5 Esteban A, Frutos-Vivar F, Ferguson ND, Arabi Y, Apezteguía C, González M, Epstein SK, Hill NS, Nava S, Soares MA, D’Empaire G, Alía I, Anzueto A. Noninvasive positive pressure ventilation for respiratory failure after extubation. N Engl J Med 2004; 350: 2452-2460.
• 6 Adams ST, Leveson SH. Clinical Prediction Rules. BMJ 2012; 344: d8312.
• 7 Vincent J-L, Opal S, Marshall JC. Ten reasons why we should NOT use severity scores as entry criteria for clinical trials or in our treatment decisions. Crit Care Med 2010; 38: 283-287.