Ge. Berrios et Eyh. Chen, RECOGNIZING PSYCHIATRIC-SYMPTOMS - RELEVANCE TO THE DIAGNOSTIC PROCESS, British Journal of Psychiatry, 163, 1993, pp. 308-314
Current overemphasis on nosological diagnosis has led to a neglect of
the process of symptom recognition. There is evidence, however, that t
he perception of the symptom alone does not guarantee symptom ascertai
nment since a decision-making component is also involved. To achieve t
he latter, additional information must be provided by the contextual c
ues implicit in the ongoing diagnostic hypothesis. Current diagnostic
systems, however, still assume a two-stage model according to which sy
mptom and disease recognition are independent cognitive events. This p
aper suggests that this model is inadequate and that descriptive psych
opathology is not transparent. It then describes a neural network simu
lation to make various aspects of the problem explicit. This takes int
o account the multidimensional and probabilistic aspects of symptom re
cognition and is, from this point of view, superior to traditional alg
orithmic models. It also has the capacity to represent the different c
ognitive styles involved in symptom recognition.