PERFORMANCE EVALUATION OF AN ALGORITHM BASED ON INTERPRETATION OF FACIAL EXPRESSIONS (EGO2SAVE) IN IDENTIFYING DEPRESSIVE SYMPTOMS

• Grant number: 25/02275-4
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: May 01, 2025
• End date: April 30, 2026
• Field of knowledge: Health Sciences - Medicine - Psychiatry
• Principal Investigator: Paulo Rossi Menezes
• Grantee: Letícia de Cássia Basseto
• Host Institution: Faculdade de Medicina (FM). Universidade de São Paulo (USP). São Paulo , SP, Brazil
• Associated research grant: 21/12901-9 - National Center for Research and Innovation in Mental Health (CISM), AP.ESP

Abstract

Depressive Disorder is one of the most prevalent mental disorders, characterized by episodes and periods of mood fluctuations over time, which hinders the implementation of effective care. The project, conducted by the National Center for Research and Innovation in Mental Health (CISM) at the University of São Paulo (USP), aims to evaluate the effectiveness of the Ego2Save application, an algorithm based on facial expression interpretation for identifying depressive symptoms. To achieve this, the correlation between the Dysthymic Index (DI), obtained from captured images, and the scores of the Patient Health Questionnaire-9 (PHQ-9) will be analyzed.This is an observational and longitudinal study, lasting three months (90 days), which will be conducted with patients diagnosed with moderate or severe depression, treated at the Psychosocial Care Center (CAPS) in Jaguariúna. Participants will be invited to join the research during their regular consultations and, after signing the Informed Consent Form (ICF), they will be required to complete a sociodemographic questionnaire, record daily selfies at random times (morning, afternoon, and evening), and complete the PHQ-9 weekly.The student will play a fundamental role in the development of the study, maintaining close contact with CAPS, making regular visits to monitor participants' adherence, and ensuring proper compliance with research protocols. Additionally, she will support the team in analyzing the collected data, assisting in verifying the relationship between the Dysthymic Index and depressive symptoms. To do so, DI values will be assessed through accuracy analyses, calculation of the area under the ROC curve (AUC), and Pearson correlation, allowing the evaluation of its effectiveness as a biomarker for depressive symptoms.Throughout the 90-day period, participants and the CAPS team will receive continuous support from researchers, with weekly meetings to monitor study progress. The student will also contribute weekly reports on the research's progress, ensuring that the collected data is organized rigorously and systematically.It is expected that the Ego2Save application will enable more accurate monitoring of depressive symptoms, promoting greater adherence to treatment and allowing for more effective clinical interventions. Thus, the project could represent a significant advancement in the application of digital technologies for mental health, facilitating the identification and tracking of depressive symptoms in an innovative and accessible manner.