PubMed vs Artificial Intelligence: Comparison of Search Results

Introduction: Medical and nursing students are using artificial intelligence (AI) search tools to conduct scholarly research. How does this process compare to using PubMed? This research will compare the results of a PubMed search to those from several AI search queries. Results will be analyzed to gauge the quality and accuracy of the returned results. Background: Artificial intelligence is affecting the searching habits of students, researchers, faculty, physicians, and other patron groups. As medical librarians, how do we guide patrons in using these tools? This poster offers a data-based comparison of four popular AI tools (Elicit, Consensus.ai, SciSpace, and OpenEvidence) and PubMed to begin to answer that question. Description: Several clinical questions will be entered into the AI search engines. Data will be collected and results will be evaluated and compared. Program Conclusion: PubMed’s detailed search format allows researchers to fine-tune their search for a deeper, more refined set of results. AI offers a surface-level set of results for users who are pressed for time or don’t have the skill set to create a proper search strategy. The AI search engines returned results in paragraphs with linked citations. PubMed returns individual citations without summaries, requiring researchers to use and develop skills to evaluate and assimilate information. The question of “PubMed vs AI” is much larger than can be addressed in a poster, but this preliminary exploration provides interesting insights.