Skip to main content

Table 1 Variables summary

From: Development and validation of a novel blending machine learning model for hospital mortality prediction in ICU patients with Sepsis

Variable type Variable
Demographic characteristics agea,b, gender, ethnicity, BMIa, admission typea,b
Vital signs max HRb, min HRa,b, max RRa, min RRa, max temperatureb, min temperaturea, max SBPb, min SBPa,b, max DBP, min DBP, max MAP, min MAPa,c, max SpO2, min SpO2a
Consciousness min GCSa,b,c
Laboratory tests max pHa, min pHa, max PaO2, min PaO2a, max PaCO2a, min PaCO2, max bicarbonate, min bicarbonateb, min PaO2/FiO2a,b,c, max WBCa,b, min WBCa,b, max hematocrit, min hematocrit, max platelet, min plateleta,c, max hemoglobina, min hemoglobin, max bilirubina,b,c, min bilirubina, max albumina, min albumina, max creatininea,c, min creatinine, max BUNb, min BUNa, max sodiumb, min sodiuma,b, max potassiumb, min potassiuma,b, max glucose, min glucose, max lactatea, min lactatea, max PTa, min PT
Comorbidities AIDSa,b, hematological tumora,b, metastatic cancera,b
Pivotal treatments Mechanical ventilationa,b,c (including invasive and noninvasive ventilation), Renal replacement therapya, Max dose of vasoactive drugs (dopaminec, dobutaminec, epinephrinec, norepinephrinec)
Fluid balance 24 h Urine outputa,b,c
  1. Abbreviations: BMI body mass index, HR heart rate, RR respiratory rate, SBP systolic blood pressure, DBP diastolic blood pressure, MAP mean arterial pressure, GCS Glasgow Coma Scale, WBC white blood cell count, PT prothrombin time
  2. aFirst subset: variables selected by stepwise regression model
  3. bSecond subset: SAPS II related variables
  4. cThird subset: SOFA related variables