Predicting the Risk of Mortality in Children using a Fuzzy-Probabilistic Hybrid Model

Figure 2

Prediction of survival accuracy for the Oviedo, Riga, and whole dataset using subjective (MID) and objective (PIM2) estimations, and the combination of both. Note that these estimations were performed using an approximation of 70% preset prediction of mortality accuracy (see Table 5). MID: logistic model using MID as explanatory variable; PIM2: logistic model using PIM2 as explanatory variable. MID+PIM2: logistic model using MID and PIM2 as explanatory variables.