BARRIERS TO THE RELIABILITY OF ARTIFICIAL INTELLIGENCE ADOPTION FOR GLEASON SCORE ASSESSMENT: PATHOLOGISTS' PERCEPTION AND ACCEPTABILITY

• Grant number: 25/09946-1
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: July 01, 2025
• End date: June 30, 2026
• Field of knowledge: Health Sciences - Medicine - Pathological Anatomy and Clinical Pathology
• Principal Investigator: Aguinaldo César Nardi
• Grantee: Gabriel Lages Prest
• Host Institution: Faculdade de Medicina. Universidade de São Paulo (USP). Campus Bauru. Bauru , SP, Brazil

Abstract

Artificial intelligence (AI) has emerged as a promising tool in digital pathology,particularly in the histopathological classification of prostate cancer using the Gleasongrading system. Despite significant technological advances and high accuracydemonstrated by deep learning models, the adoption of AI in clinical practice still facesresistance among professionals. This research project aims to understand the mainbarriers perceived by pathologists regarding the use of AI in this context, consideringtechnical, psychological, technological, and social aspects that impact its acceptance.The study will follow a qualitative methodology, combining a systematic literature review,the application of Likert-type questionnaires, and semi-structured interviews. The datacollected will be analyzed using Bardin's content analysis technique. The expectedresults include the identification of resistance patterns and limiting factors that maysupport a critical reflection on the ethical and effective integration of AI into thediagnostic workflow of pathologists, promoting a more precise and contemporarymedical practice.