GPT meets PubMed: a novel approach to literature review using a large language model to crowdsource migraine medication reviews

• Published in: BMC neurology Vol. 25; no. 1; pp. 69 - 8
• Main Authors: Mackenzie, Elyse, Cheng, Roger, Zhang, Pengfei
• Format: Journal Article
• Language: English
• Published: England BioMed Central Ltd 19.02.2025; BioMed Central; BMC
• Subjects: Analysis; Application programming interface; Artificial intelligence; Biological products; Bupivacaine; Clinical trials; Crowdsourcing; Crowdsourcing - methods; Drug therapy; Drugs; Evidence-based medicine; FDA approval; Headache; Headaches; Homeopathy; Humans; Large language model; Large Language Models; Levetiracetam; Literature review; Literature reviews; Materia medica and therapeutics; Medical Subject Headings-MeSH; Migraine; Migraine Disorders - drug therapy; Monoclonal antibodies; Pharmaceuticals; PubMed; Python; Quality of life; Sentiment analysis; Technology application; Therapeutics; United States; Headaches; Literature review; Large language model; Artificial intelligence; Migraine
• DOI: 10.1186/s12883-025-04071-1
• ISSN: 1471-2377

To evaluate the potential of two large language models (LLMs), GPT-4 (OpenAI) and PaLM2 (Google), in automating migraine literature analysis by conducting sentiment analysis of migraine medications in clinical trial abstracts. Migraine affects over one billion individuals worldwide, significantly impacting their quality of life. A vast amount of scientific literature on novel migraine therapeutics continues to emerge, but an efficient method by which to perform ongoing analysis and integration of this information poses a challenge. "Sentiment analysis" is a data science technique used to ascertain whether a text has positive, negative, or neutral emotional tone. Migraine medication names were extracted from lists of licensed biological products from the FDA, and relevant abstracts were identified using the MeSH term "migraine disorders" on PubMed and filtered for clinical trials. Standardized prompts were provided to the APIs of both GPT-4 and PaLM2 to request an article sentiment as to the efficacy of each medication found in the abstract text. The resulting sentiment outputs were classified using both a binary and a distribution-based model to determine the efficacy of a given medication. In both the binary and distribution-based models, the most favorable migraine medications identified by GPT-4 and PaLM2 aligned with evidence-based guidelines for migraine treatment. LLMs have potential as complementary tools in migraine literature analysis. Despite some inconsistencies in output and methodological limitations, the results highlight the utility of LLMs in enhancing the efficiency of literature review through sentiment analysis.