Table 1 The 30 features that were extracted from the MIMIC-IV database. The full names of all features can be found in Appendix 1 (Supplementary Table 6).

From: Real-time prediction of HFNC treatment failure in acute hypoxemic respiratory failure using machine learning

 

Category

Features

Common features

Demographic features

Age, BMI, gender

Physiological features

Urine output, heart rate, non-invasive systolic blood pressure, non-invasive diastolic blood pressure, non-invasive mean blood pressure, respiration rate, temperature, SpO2

Glasgow scoring

Gcs, Gcs verbal, Gcs motor, Gcs eyes

Laboratory features

Blood gas analysis features

Oxygenation index, A-ado2, Base excess, TotalCO2, PCO2, PH, PO2

Chemical assay features

Creatinine, Glucose, Bun

Complete blood cell count features

Hematocrit, hemoglobin, platelet, Rbc, Wbc