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.

The social distancing imposed by the COVID-19 pandemic has been described as the “greatest psychological experiment in the world”. It has tested the human capacity to extract meaning from suffering and challenged individuals and society in Brazil and abroad to promote cohesion that cushions the impact of borderline experiences on mental life. In this context, a survey was conducted with teachers, administrative technicians, and outsourced employees at the Federal Institute of Piauí (IFPI). This educational institution offers professional and technological education in Piauí, Brazil. This study proposes a system for the early diagnosis of health quality during social distancing in the years 2020 and 2021, over the COVID-19 pandemic, combining multi-criteria decision support methodology, the Analytic Hierarchy Process (AHP) with machine learning algorithms (Random Forest, logistic regression, and Naïve Bayes). The hybrid approach of the machine learning algorithm with the AHP multi-criteria decision method with geometric mean accurately obtained a classification that stood out the most in the characteristics’ performance concerning emotions and feelings. In 2020, the situation was reported as the SAME AS BEFORE, in which the hybrid AHP with Geographical Average with the machine learning Random Forest algorithm stands out, highlighting the atypical situation in the quality of life of the interviewees and the timely manner in which they realized that their mental health remained unchanged. After that, in 2021, the situation was reported as WORSE THAN BEFORE, in which the hybrid AHP with geometric mean with the machine learning Random Forest algorithm provided an absolute result.