EVALUATION OF PROGNOSTIC FACTORS IN MENINGIOMAS: APPLICATION OF SUPERVISED MACHINE LEARNING IN A CROSS-SECTIONAL STUDY

• Grant number: 23/13832-6
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: April 01, 2024
• End date: March 31, 2025
• Field of knowledge: Health Sciences - Medicine - Surgery
• Principal Investigator: Ricardo Santos de Oliveira
• Grantee: Amanda Lima Leite
• Host Institution: Hospital das Clínicas da Faculdade de Medicina de Ribeirão Preto da USP (HCMRP). Secretaria da Saúde (São Paulo - Estado). Ribeirão Preto , SP, Brazil

Abstract

Meningiomas are brain tumors originating from meningoendothelial cells, usually benign that can present varied signs and symptoms, depending on the size and location. The study and use of Artificial Intelligence (AI) in medicine is growing exponentially. Computational systems that use AI are being used in oncology and radiology in the search for faster and more accurate diagnoses, consequently generating more efficient treatments, helping to select the best strategy for each case, through the analysis of clinical and image data. This project aims to evaluate the epidemiology of individuals diagnosed with meningioma in a reference service in neurosurgery and to identify factors associated with unfavorable surgical outcomes of these individuals using XGBoost, a recent machine learning model that has shown excellent results. This is a cross-sectional study, collecting information from subjects diagnosed with meningiomas treated at the Hospital das Clínicas de Ribeirão Preto since 2011. Data will be collected from the hospital's database and will include epidemiological, clinical and neurological outcome information of patients who will be inserted into predictive models to identify factors associated with postoperative prognosis using the machine learning method.