**2. Model issues**

Various pattern recognition approaches can be used to design models for separating and classifying patients into the two independent classes of adverse or favourable health outcome, AHE and FHE. The approaches fall into two main categories.

1. Probability models estimate a class-conditional probability, P(AHE|x), of developing the adverse outcome AHE, given a set of chosen predictor variables or features x (Bishop, 1995; Dreiseitl & Ohno-Machado, 2002; Fukunaga, 1990; Lee, 2004). A probability threshold value, Pt, is identified for classification, over which AHE is recognized to occur, that is when P(AHE|x)>Pt ; the choice of Pt depends on the clinical cost of a wrong decision and influences model classification performance (E. Barbini et al., 2007).

2. Score models evaluate risk by a discrete scale of n positive integer values si (i = 0, 1, 2, ..., n) which includes zero to represent null risk, but rarely provides a threshold value for classification purposes (Cevenini & P. Barbini, 2010; Vincent & Moreno, 2010).
