A hybrid model to guide the consultation of children with autism spectrum disorder

Abstract

Considering that psychological disorders have specific causes and symptoms, the conventional way to establish diagnosis consists of analysing the behavioural reactions of a human being to events in their daily lives. The manifestation of psychological disorders varies from person to person and the degree of severity. Like ‘personality,’ ‘consciousness’ and ‘intelligence,’ the expression ‘abnormal behaviour’ is difficult to define due to sociocultural subjectivities intrinsic to the human being. Social interactions are essential factors in the search for solutions to the problems of the information society. However, neurodevelopmental disorders may affect some people from birth, hampering their healthy growth and consequently their participation in social interactions. In this context, autistic spectrum disorder is one of the primary disorders of neurodevelopment, which manifests itself before the age of three. Despite the existence of diagnostic criteria for autism spectrum disorder, there is a lack of system with models containing algorithms that help the families and health professionals in the early diagnosis of this disorder. The objective of this study is to make proactive the decision-making process for the establishment of the early diagnosis of autism spectrum disorder. For this, the research presents a hybrid model proposal composed of a specialist system structured in decision-making methodologies (Multi-Criteria Decision Analysis) and structured representations of knowledge in production rules and probabilities using Artificial Intelligence. In this context, the research aims to show one of the potentials of information technologies as a way to generate knowledge that adds value and serves as a support in medical decision making.