Feature Analysis in Individuals with 22q11.2 Deletion Syndrome using Clustering and Association Rules in Machine Learning

• Grant number: 24/12628-9
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: July 01, 2025
• End date: June 30, 2026
• Field of knowledge: Interdisciplinary Subjects
• Principal Investigator: Ana Estela Antunes da Silva
• Grantee: Lais Azevedo Soares
• Host Institution: Faculdade de Tecnologia (FT). Universidade Estadual de Campinas (UNICAMP). Limeira , SP, Brazil

Abstract

22q11.2 deletion syndrome (22q11.2DS) is themost common chromosomal microdeletion, as reported by the journal Nature.This craniofacial anomaly affects approximately 1 in every 2,000 to 6,000 live births, significantly impacting the quality of life and survival from the embryonic stage to the adult stage. Due to the high phenotypic variability of the syndrome, it is essential to identify characteristics related to it for the detection of individuals with clinical suspicion for carry out laboratory confirmation as early as possible. In addition clinical variability can, expand the possible, and not fully recognized, differential diagnoses, which can impact the choice of the laboratory investigation and its cost. These difficulties can lead to need for further investigation of other patient characteristics unknown so that a more assertive filter can be carried out. This projectaims to carry out an exploratory investigation in the Brazilian Base of Craniofacial Anomalies using clustering techniques in machine learningto organize data into similarity groups based on characteristics observed. The objective is to explore and deepen knowledge about thecharacteristics associated with the presence of chromosome 22 deletion.Additionally, association rules will be applied to each group generated to identify relationships and dependencies between variables in the dataset,aiming to discover relationships not yet known between the characteristics of this anomaly. This approach will allow a better understanding of the behavior of the syndrome and the refinement of clinical protocol criteria, in addition tocontribute to saving resources in the Unified Health System (SUS). (AU)