Development of an evaluation methodology based on criteria for the successful implementation of AI systems in Radiology with 'lato sensu' quality.

• Grant number: 24/14707-3
• Support Opportunities: Scholarships in Brazil - Doctorate
• Start date: October 01, 2024
• End date: March 31, 2027
• Field of knowledge: Health Sciences - Medicine - Medical Radiology
• Principal Investigator: Giovanni Guido Cerri
• Grantee: Carmem Lúcia Ralo e Borges
• Host Institution: Faculdade de Medicina (FM). Universidade de São Paulo (USP). São Paulo , SP, Brazil
• Associated research grant: 21/11905-0 - Center of Science, Technology and Development for innovation in Medicine and Health: inLab.iNova, AP.CCD

Abstract

The challenge in implementing AI technology today is not in its creative development, but in the degree of efficiency, clinical and physical quality, safety, accessibility and portability to different environments. Specifically, in applications in Radiology, what we currently have in AI is an opportunity, still little taken advantage of, to offer quality in its broadest aspect - quality lato sensu: clinical efficiency with productivity and safety, reduction of technical inequity and social and geographic availability. In a very similar way to the implementation of image management system solutions - Picture Archiving and Communication System (PACS), the success of the expected results in AI solutions is directly proportional to the prior and dynamic evaluation of certain criteria, with the need for standardization and regulation. This research for the defense of a doctoral thesis consists of developing a prior evaluation methodology based on criteria for the successful implementation of AI systems in Radiology with 'lato sensu' quality.