Skip to main content
Fig. 3 | Critical Care

Fig. 3

From: A clinical prediction model to identify patients at high risk of hemodynamic instability in the pediatric intensive care unit

Fig. 3

Schematic of algorithm. The algorithm receives as input 21 features from vital signs, laboratory, ventilator measurements, normalized urine output, and age. The algorithm first filters input values in valid ranges, secondly determines feature value thresholds that depend on the age of the patient, thirdly determines feature contribution prediction scores, and finally aggregates the individual feature contribution prediction scores to determine a hemodynamic instability indicator (HII). The HII is a score, on a scale from 0 to 1, representing the probability of a patient to be hemodynamically unstable. This score is mapped to three colors to indicate the risk level of deterioration (i.e., green for low risk, yellow for medium risk, and red for high risk). aBE arterial base excess, BUN blood urea nitrogen, FiO fraction of inspired oxygen, HR heart rate, iMBP invasive mean blood pressure, INR international normalized ratio, iSBP invasive systolic blood pressure, iSI invasive shock index, nMBP noninvasive mean blood pressure, nSBP noninvasive systolic blood pressure, nSI noninvasive shock index, PaO2 arterial partial pressure of oxygen, RBC red blood cells, RR Respiratory rate, SpO2 oxygen saturation

Back to article page