Fig. 2

Pilot FFT chosen by the algorithm. The top panels show the number of observations and outcome (4-h hospital blood administration). SBP_min – minimal SBP (mmHg), nlacven – prehospital lactate concentration (mmol/L), si_min – minimum SI (bpm/mmHg), ais_ab – AIS for abdomen (0/1, equal to 1 if the AIS is greater than 2). “Hits” (green triangles) refer to correct blood administrations; “misses” (red triangles) – to incorrect rejections. Sensitivity (triangles) = Hits / (Hits + Misses). Correct rejections (green circles) refer to correct decisions to not give blood, false alarms (red circles) – to false positives, or incorrect decisions to give blood. Specificity (circles) = Correct Rejections / (Correct Rejections + False Alarms). A pilot FFT was obtained using training and testing datasets (the testing dataset N = 1,121) and selected from a “fan” of possible trees as having the best balance between sensitivity and specificity. A default sensitivity weight of 0.5 resulted in a “zig-zag” shape with alternating decisions. The ROC panel shows a comparison of parameters for the resulting FFT and other common model-building approaches: CART (C, red), Logistic Regression (LR, blue), Random Forest (RF, purple) and Support Vector Machine (SVM, yellow)