This study evaluated the effectiveness of two conversational artificial intelligence systems, ChatGPT and GoogleBard, in providing correct, complete and relevant answers to questions related to red flags (RFs) associated with low back pain (LBP). RFs are important indicators of serious medical conditions in LBP cases. The study involved 70 English questions based on the symptoms outlined in LBP guidelines, with 58 focusing on single symptoms and 12 involving multiple symptoms in addition to LBP. Both ChatGPT and GoogleBard demonstrated strong performance in terms of correctness, completeness, and relevance of their responses. The severity of the conditions was effectively conveyed in the majority of responses, and there were no statistically significant differences between the two systems. This research highlights the potential of AI systems like ChatGPT and GoogleBard in providing reliable health information, which is particularly valuable as more individuals turn to online sources for medical guidance.