Confiabilidade das recomendações de tratamento para dor lombar crônica em sites e IAs

Abstract

Chronic low back pain (CLBP) is one of the most prevalent and disabling musculoskeletal conditions worldwide, significantly affecting quality of life and functional capacity. Concurrently, there has been a substantial increase in the use of the internet, including search engines such as Google, Yahoo, and Bing, as well as Artificial Intelligence (AI) platforms, raising concerns about the credibility and reliability of the health-related information accessed through these sources. In this context, the present study aimed to analyze the quality and reliability of information available on the Google search engine and popular AI systems, using evidence-based practice as the gold standard for the treatment of CLBP. This was an observational, descriptive, and comparative study of digital content sources, with data collection conducted through validated community prompts. The findings indicate partial alignment between recommendations provided by conventional websites and AI systems and those supported by the scientific literature, particularly regarding isolated interventions such as therapeutic exercises, walking, yoga, Pilates, and stretching. However, these recommendations are generally presented in a simplified and non-specific manner, lacking clinical depth and contextualization. The results highlight the need for improved alignment between digital health content and current evidence-based guidelines. It is concluded that information obtained from conventional websites and artificial intelligence platforms has limitations in terms of reliability and quality when compared to evidence-based practice and should therefore be used cautiously and critically as a complementary resource, as it cannot address individual patient needs nor replace personalized therapeutic prescription on CLBP.