A Protocol for the Diagnosis of Autism Spectrum Disorder Structured in Machine Learning and Verbal Decision Analysis

Abstract

Autism Spectrum Disorder is a mental disorder that afflicts millions of people worldwide. It is estimated that one in 160 children has traces of autism, with five times the higher prevalence in boys. The protocols for detecting symptoms are diverse. However, the following are among the most used: the Diagnostic and Statistical Manual of Mental Disorders, 5th Edition (DSM-5), of the American Psychiatric Association; the Revised Autistic Diagnostic Observation Schedule (ADOS-R); the Autistic Diagnostic Interview (ADI); and the International Classification of Diseases, 10th edition (ICD-10), published by the World Health Organization (WHO) and adopted in Brazil by the Unified Health System (SUS). The application of machine learning models helps make the diagnostic process of Autism Spectrum Disorder more precise, reducing, in many cases, the number of criteria necessary for evaluation, denoting a form of attribute engineering (feature engineering) efficiency. This work proposes a hybrid approach based on machine learning algorithms’ composition to discover knowledge and concepts associated with the multicriteria method of decision support based on Verbal Decision Analysis to refine the results. Therefore, the study has the general objective of evaluating how the mentioned hybrid methodology proposal can make the protocol derived from ICD-10 more efficient, providing agility to diagnosing Autism Spectrum Disorder by observing a minor symptom. The study database covers thousands of cases of people who, once diagnosed, obtained government assistance in Brazil.

Application of artificial intelligence tools in diagnosis and treatmentof mental disorders

“…Wall et al [30] applied machine learning algorithms with data collected from multiple databases of information on ASD, including the Autism Genetic Resource Exchange (AGRE) and the Autism Consortium (AC). The authors indicated that artificial intelligence tools make it possible to differentiate between autism spectrum disorders and similar diseases with 100% accuracy [31].…”

“…[30] zastosowali algorytmy uczenia maszynowego z danymi zgromadzonymi w wielu bazach informacji na temat ASD, w tym Autism Genetic Resource Exchange (AGRE) i Autism Consortium (AC). Autorzy wskazali, że narzędzia sztucznej inteligencji umożliwiają różnicowanie zaburzeń spektrum autyzmu oraz podobnych chorób ze 100% dokładnością [31].…”

An Intelligent Multicriteria Model for Diagnosing Dementia in People Infected with Human Immunodeficiency Virus

“…Logistic Regression is one of the most popular Machine Learning algorithms for binary classification, given a set of independent variables, and is used to predict a binary result (1 or 0, Yes or No, True or False) [32]. It has been applied successfully in various areas, such as Medicine [37], Finance [38], and Economics [39]. In this model, the probabilities describing the possible outcomes of a single trial are modeled using a logistic function, namely the logical relationship between a dichotomous response variable and a series of numerical (continuous, discrete) or categorical explanatory variables.…”

“…In this model, the probabilities describing the possible outcomes of a single trial are modeled using a logistic function, namely the logical relationship between a dichotomous response variable and a series of numerical (continuous, discrete) or categorical explanatory variables. [37][38][39][40].…”

Hybrid model for early identification post-Covid-19 sequelae

“…The choice for ML was due to its great potential in generating knowledge from large databases (Andrade et al 2021b ). In turn, about the MCDA methodology, the study was based on Verbal Decision Analysis methods, such as Ordinal Classification (ORCLASS) and ZAPROS-IIIi (Andrade et al 2021a ). The use of VDA is related to the need for decisions that involve subjective knowledge used in qualitative choices.…”