HPHye Won Park

Hye Won Park

*This is an algorithmically generated author record based on publicly available information.

Hye Won Park has a total of 13 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Quality Evaluation of Generative AI–Based Search Strategies in Systematic Reviews and Comparison of Search Performance with Human Expert (Medical Librarian)

    by Hye Won Park, Dong Won Shin, Na Jin Kim

    Reproducible and sensitive literature search strategies are essential to the methodological rigor of systematic reviews (SRs). Recently, generative artificial intelligence (AI) tools such as ChatGPT and Gemini have been explored as aids for search strategy development; however, concerns remain regarding logical errors, limited understanding of controlled vocabularies, and reproducibility. This study evaluates the quality of search strategies generated by generative AI for a specific clinical topic and compares their retrieval performance with those developed by professional medical librarians. The research topic was defined as the effectiveness of psychotherapy for patients with obesity. Relevant Cochrane Reviews were identified in the Cochrane Library database using a search strategy incorporating both MeSH terms and text word keywords. Based on the final reference lists of the included reviews, a gold standard comprising a total of 139 studies was constructed. The comparative experiment involved generative AI models (ChatGPT-5, Gemini 2.5) and a human expert (medical librarian). The AI group operated in a zero-shot environment using three levels of prompts based on researcher proficiency, while the human expert formulated strategies adhering to the Cochrane Handbook and PRISMA-S guidelines. The derived search strategy was applied to three major academic databases (PubMed, EMBASE, and the Cochrane Library). Its performance was evaluated qualitatively using the PRESS 2015 Evidence-Based Guideline Checklist and quantitatively by calculating sensitivity (recall) and precision. As prompt levels advanced, generative AI showed improved structural systematicity in search strategies; however, limitations persisted in the accurate application of database-specific syntax (truncation, field tags) and controlled vocabularies (MeSH/Emtree). In the performance evaluation, the human expert achieved the highest sensitivity (54.7%), followed by Gemini 2.5 (advanced prompt) at 49.6% and ChatGPT-5 (intermediate prompt) at 46.8%. Precision was low (less than 1%) for all groups. The analysis of missing studies revealed that human expert omitted some recent intervention-related literature, such as digital health studies, due to relying on traditional conceptual boundaries of “psychotherapy.” Generative AI is a useful auxiliary tool for deriving initial search concepts and expanding natural language terms; however, verification by medical librarians remains essential to ensure appropriate controlled vocabulary use and syntactic accuracy. Medical librarians, in contrast, developed comprehensive and reproducible high-sensitivity search strategies for systematic reviews, though further refinement is required to improve precision. Accordingly, this study proposes a Human–AI Collaboration model that integrates generative AI automation with the methodological expertise of medical librarians, highlighting the continued importance of medical librarians in high-quality evidence synthesis in the AI era. Future research should encompass diverse clinical questions beyond a single topic and continuously evaluate the performance of rapidly evolving AI models. [J Korean Med Libr Assoc 2025;52(1):28-47]


  • Open Access

    Adjuvant radiotherapy for ypN0 breast cancer patients receiving neoadjuvant chemotherapy: a systematic review and meta-analysis

    by Hyung-Sik Lee, Sungmin Kim, Hyunjung Kim, Ki-Jung Ahn, Hye Won Park, Yunseon Choi

    Lee HS, et al. Ann Surg Treat Res. 2025 Nov;109(5):286-292. https://doi.org/10.4174/astr.2025.109.5.286


  • Open Access

    Effect of perioperative intravenous ibuprofen versus acetaminophen on postoperative opioid consumption and pain after general anesthesia: a systematic review and meta-analysis with trial sequential analysis of randomized controlled trials

    by Sung Hye Kim, Hyun Kang, In-Jung Jun, Hye Won Park, Byung Hoon Yoo, Yun-Hee Lim, Kye-Min Kim

    Background: Ibuprofen and acetaminophen are widely used as adjuvant analgesics for postoperative pain. This meta-analysis compared the effects of intravenous (IV) ibuprofen and acetaminophen on postoperative opioid consumption and pain intensity after general anesthesia.Methods: PubMed/MEDLINE, EMBASE, and Cochrane Library databases were searched to identify relevant studies published up to May 2023. Randomized controlled trials comparing the effects of perioperative IV ibuprofen and acetaminophen on postoperative opioid consumption and pain after general anesthesia were included in the meta-analysis and trial sequential analysis (TSA).Results: Eight studies with 494 participants were included. Compared to IV acetaminophen, IV ibuprofen significantly reduced 24 h opioid consumption, presented as morphine equivalents (mean difference [MD]: –6.01 mg, 95% CI [–8.60, –3.42], P < 0.00001, I2 = 55%), and pain scores (on a scale of 0–10) at 4–6 h (MD: –0.83, 95% CI [–1.29, –0.37], P = 0.0004, I2 = 65%) and 12 h (MD: –0.38, 95% CI [–0.68, –0.08], P = 0.01, I2 = 11%) postoperatively. These results were statistically significant in TSA. Pain scores at 24 h postoperatively and side effects were not significantly different between the two groups in the meta-analysis, and TSA revealed that the sample size was too small to adequately evaluate the effects, requiring further studies for conclusive results.Conclusions: Perioperative IV ibuprofen reduced 24 h opioid consumption and pain severity up to 12 h postoperatively compared to acetaminophen. Additional research is required to assess pain intensity beyond 12 h and side effects.