The formulation of literature retrieval strategies is one of the important steps in systematic review and Meta-analysis. A good retrieval strategy can help researchers accurately retrieve relevant literature, minimize the occurrence of missed detections and false detections, and thereby enhance the reliability and effectiveness of research. Currently, the multidisciplinary integration of large language models provides new possibilities for the formulation of retrieval strategies. This article introduces the formulation methods of various retrieval strategies from PICO to large language models, discusses the application of these methods, points out the deficiencies and challenges of current retrieval strategy generation, and looks forward to the future development direction.

1.The Cochrane Collaboration. Cochrane handbook for systematic reviews of interventions Version 5.1.0[EB/OL]. (2011-03) [2024-10-10]. http://www.cochrane-handbook.org

2.Stevens KR. Systematic reviews: the heart of evidence-based practice[J]. AACN Clin Issues, 2001, 12(4): 529-538. DOI: 10.1097/00044067-200111000-00009.

3.Lamé G. Systematic literature reviews: an introduction[C]//Proceedings of the Design Society: International Conference on Engineering Design, 2019, 1(1): 1633-1642. DOI: 10.1017/dsi.2019.169.

4.Nussbaumer-Streit B, Klerings I, Wagner G, et al. Abbreviated literature searches were viable alternatives to comprehensive searches: a meta-epidemiological study[J]. J Clin Epidemiol, 2018, 102: 1-11. DOI: 10.1016/j.jclinepi.2018.05.022.

5.Levay P, Craven J. Systematic searching: practical ideas for improving results[M]. London: Facet Publishing, 2019: 73-94.

6.Sampson M, Zhang L, Morrison A, et al. An alternative to the hand searching gold standard: validating methodological search filters using relative recall[J]. BMC Med Res Methodol, 2006, 6: 33. DOI: 10.1186/1471-2288-6-33.

7.Rethlefsen ML, Kirtley S, Waffenschmidt S, et al. PRISMA-S: an extension to the PRISMA Statement for Reporting Literature Searches in Systematic Reviews[J]. Systematic reviews, 2021, 10(1): 39. DOI: 10.1186/s13643-020-01542-z.

8.Shokraneh F. PICO framework: two decades of variation and application[EB/OL]. (2019-08-12) [2024-10-17]. https://doi.org/10.7490/f1000research.1117334.1

9.Hausner E, Waffenschmidt S, Kaiser T, et al. Routine development of objectively derived search strategies[J]. Syst Rev, 2012, 1: 19. DOI: 10.1186/2046-4053-1-19.

10.Scells H, Zuccon G, Koopman B. A comparison of automatic Boolean query formulation for systematic reviews[J]. Information Retrieval Journal, 2021, 24(1): 3-28. DOI: 10.1007/s10791-020-09381-1.

11.Bramer WM, de Jonge GB, Rethlefsen ML, et al. A systematic approach to searching: an efficient and complete method to develop literature searches[J]. J Med Libr Assoc, 2018, 106(4): 531-541. DOI: 10.5195/jmla.2018.283.

12.Carrera-Rivera A, Ochoa W, Larrinaga F, et al. How-to conduct a systematic literature review: a quick guide for computer science research[J]. MethodsX, 2022, 9: 101895. DOI: 10.1016/j.mex.2022.101895.

13.陈耀龙, 孙雅佳, 罗旭飞, 等. 循证医学的核心方法与主要模型[J]. 协和医学杂志, 2023, 14(1): 1-8. [Chen YL, Sun YJ, Luo XF, et al. The core methods and key models in evidence-based medicine[J]. Medical Journal of Peking Union Medical College Hospital, 2023, 14(1): 1-8.] DOI: 10.12290/xhyxzz.2022-0686.

14.朱政, 胡雁, 邢唯杰, 等. 不同类型循证问题的构成[J]. 护士进修杂志, 2017, 32(21): 1991-1994. [Zhu Z, Hu Y, Xing WJ, et al. The composition of different types of evidence based problems[J]. Journal of Nurses Training, 2017, 32(21): 1991-1994.] DOI: 10.16821/j.cnki.hsjx.2017.21.025.

15.Huang X, Lin J, Demner-Fushman D. Evaluation of PICO as a knowledge representation for clinical questions[J]. AMIA Annu Symp Proc, 2006, 2006: 359-363. https://pubmed.ncbi.nlm.nih.gov/17238363/

16.Dhrangadhariya A, Manzo G, Müller H. PICO to PICOS: weak supervision to extend datasets with new labels[J]. Stud Health Technol Inform, 2024, 316: 1775-1779. DOI: 10.3233/SHTI240775.

17.Tacconelli E. Systematic reviews: CRD's guidance for undertaking reviews in health care[J]. The Lancet Infectious Diseases, 2010, 10(4): 226. DOI: 10.1016/S1473-3099(10)70065-7.

18.Methley AM, Campbell S, Chew-Graham C, et al. PICO, PICOS and SPIDER: a comparison study of specificity and sensitivity in three search tools for qualitative systematic reviews[J]. BMC Health Serv Res, 2014, 14: 579. DOI: 10.1186/s12913-014-0579-0.

19.Saaiq M, Ashraf B. Modifying "Pico" question into "Picos" model for more robust and reproducible presentation of the methodology employed in a scientific study[J]. World J Plast Surg, 2017, 6(3): 390-392. https://pubmed.ncbi.nlm.nih.gov/29218294/

20.Anderson LM, Oliver SR, Michie S, et al. Investigating complexity in systematic reviews of interventions by using a spectrum of methods[J]. J Clin Epidemiol, 2013, 66(11): 1223-1229. DOI: 10.1016/j.jclinepi.2013.06.014.

21.Cooke A, Smith D, Booth A. Beyond PICO: the SPIDER tool for qualitative evidence synthesis[J]. Qual Health Res, 2012, 22(10): 1435-1443. DOI: 10.1177/1049732312452938.

22.Jenkins M. Evaluation of methodological search filters--a review[J]. Health Info Libr J, 2004, 21(3): 148-163. DOI: 10.1111/j.1471-1842.2004.00511.x.

23.Borah R, Brown AW, Capers PL, et al. Analysis of the time and workers needed to conduct systematic reviews of medical interventions using data from the PROSPERO registry[J]. BMJ Open, 2017, 7(2): e012545. DOI: 10.1136/bmjopen-2016-012545.

24.Garritty C, Nussbaumer-Streit B, Hamel C, et al. Rapid reviews methods series: assessing the appropriateness of conducting a rapid review[J]. BMJ Evid Based Med, 2025, 30(1): 55-60. DOI: 10.1136/bmjebm-2023-112722.

25.Hausner E, Guddat C, Hermanns T, et al. Development of search strategies for systematic reviews: validation showed the noninferiority of the objective approach[J]. J Clin Epidemiol, 2015, 68(2): 191-199. DOI: 10.1016/j.jclinepi.2014.09.016.

26.O'Mara-Eves A, Thomas J, McNaught J, et al. Using text mining for study identification in systematic reviews: a systematic review of current approaches[J]. Syst Rev, 2015, 4(1): 5. DOI: 10.1186/2046-4053-4-5.

27.Choong MK, Galgani F, Dunn AG, et al. Automatic evidence retrieval for systematic reviews[J]. J Med Internet Res, 2014, 16(10): e223. DOI: 10.2196/jmir.3369.

28.Paynter R, Bañez LL, Berliner E, et al. EPC methods: an exploration of the use of text-mining software in systematic reviews[M]. Rockville (MD): Agency for Healthcare Research and Quality (US), 2016: 14-16. https://pubmed.ncbi.nlm.nih.gov/27195359/

29.Mergel GD, Silveira MS, da Silva TS. A method to support search string building in systematic literature reviews through visual text mining[C]//Proceedings of the 30th Annual ACM Symposium on Applied Computing, 2015: 1594-1601. DOI: 10.1145/2695664.2695902.

30.黄衍楠, 桑浩然, 刘宇, 等. 大语言模型辅助医学系统综述：方法、发展方向和应用[J]. 广西医科大学学报, 2025, 42(3): 323-331. [Huang YN, Sang HR, Liu Y, et al. Empowering medical systematic reviews with large language models: methods, development directions, and applications[J]. Journal of Guangxi Medical University, 2025, 42(3): 323-331.] DOI: 10.16190/j.cnki.45-1211/r.2025.03.001.

31.Li M, Sun J, Tan X. Evaluating the effectiveness of large language models in abstract screening: a comparative analysis[J]. Syst Rev, 2024, 13(1): 219. DOI: 10.1186/s13643-024-02609-x.

32.Adiga A, Wang L, Hurt B, et al. All models are useful: bayesian ensembling for robust high resolution COVID-19 forecasting[J]. medRxiv, 2021: 2021.03.12.21253495. DOI: 10.1101/2021.03.12.21253495.

33.Wei J, Wang X, Schuurmans D, et al. Chain-of-thought prompting elicits reasoning in large language models[J]. arXiv e-prints, 2022: arXiv:2201.11903. DOI: 10.48550/arXiv.2201.11903.

34.DeepSeek-AI, Guo D, Yang D, et al. DeepSeek-R1: incentivizing reasoning capability in LLMs via reinforcement learning[J]. arXiv e-prints, 2025: arXiv:2501.12948. DOI: 10.48550/arXiv.2501.12948.

35.Alshami A, Elsayed M, Ali E, et al. Harnessing the power of ChatGPT for automating systematic review process: methodology, case study, limitations, and future directions[J]. Systems, 2023, 11(7): 351. https://doi.org/10.3390/systems11070351

36.Matsui K, Utsumi T, Aoki Y, et al. Human-comparable sensitivity of large language models in identifying eligible studies through title and abstract screening: 3-layer strategy using GPT-3.5 and GPT-4 for systematic reviews[J]. J Med Internet Res, 2024, 26: e52758. DOI: 10.2196/52758.

37.Mahuli SA, Rai A, Mahuli AV, et al. Application ChatGPT in conducting systematic reviews and meta-analyses[J]. Br Dent J, 2023, 235(2): 90-92. DOI: 10.1038/s41415-023-6132-y.

38.Wang S, Scells H, Koopman B, et al. Can ChatGPT write a good boolean query for systematic review literature search?[J]. arXiv preprint, 2023, arXiv:2302.03495. DOI: 10.48550/arXiv.2302.03495.

39.MacFarlane A, Russell-Rose T, Shokraneh F. Search strategy formulation for systematic reviews: Issues, challenges and opportunities[J]. Intelligent Systems with Applications, 2022, 15(c): 200091. DOI: 10.1016/j.iswa.2022.200091.

40.Rethlefsen ML, Brigham TJ, Price C, et al. Systematic review search strategies are poorly reported and not reproducible: a cross-sectional metaresearch study[J]. J Clin Epidemiol, 2024, 166: 111229. DOI: 10.1016/j.jclinepi.2023.111229.