kpcczКомплексные проблемы сердечно-сосудистых заболеванийComplex Issues of Cardiovascular Diseases2306-12782587-9537Federal State Budgetary Institution “Research Institute for Complex Issues of Cardiovascular Diseases”10.17802/2306-1278-2026-15-4-153-163kpccz-1877Research ArticleДИСКУССИОННЫЙ РАЗДЕЛ. Искусственный интеллект. Математическое моделированиеПРИМЕНЕНИЕ БОЛЬШИХ ЯЗЫКОВЫХ МОДЕЛЕЙ ДЛЯ ИНФОРМАЦИОННОГО ПОИСКА ПРИ ПОДГОТОВКЕ СИСТЕМАТИЧЕСКИХ ОБЗОРОВ И МЕТААНАЛИЗА В СЕРДЕЧНО-СОСУДИСТОЙ ХИРУРГИИUSING LARGE LANGUAGE MODELS FOR LITERATURE SEARCH IN CARDIOVASCULAR SURGERY SYSTEMATIC REVIEWS AND META-ANALYSEShttps://orcid.org/0009-0003-3654-1618ШацкийАлександр СергеевичShatskiyAlexander S.

Master of Science (University of Bologna), кандидат медицинских наук докторант-соискатель института коронарной и сосудистой хирургии федерального государственного бюджетного учреждения «Национальный медицинский исследовательский центр сердечно-сосудистой хирургии имени А.Н. Бакулева» Министерства здравоохранения Российской Федерации, Москва, Российская Федерация; заместитель директора по научной работе Малого инновационного предприятия «Лаборатория передовых технологий» при Университете Иннополис, Иннополис, Республика Татарстан, Российская Федерация

Master of Science (University of Bologna), PhD, Doctoral Candidate at the Institute of Coronary and Vascular Surgery of the Federal State Budgetary Institution “National Medical Research Center for Cardiovascular Surgery named after A.N. Bakulev” of the Ministry of Health of the Russian Federation, Moscow, Russian Federation; Deputy Director for Research at the Small Innovative Enterprise “Laboratory of Advanced Technologies” at Innopolis University, Innopolis city, Republic of Tatarstan, Russian Federation

alexander.shatsky@gmail.comhttps://orcid.org/0009-0007-2929-4021ДеигхеидиЭхаб МахрусDeigheidyEhab M.

кандидат медицинских наук докторант-соискатель института кардиохирургии им. В.И. Бураковского федерального государственного бюджетного учреждения «Национальный медицинский исследовательский центр сердечно-сосудистой хирургии имени А.Н. Бакулева» Министерства здравоохранения Российской Федерации, Москва, Российская Федерация

PhD, Doctoral Candidate at the V.I. Burakovsky Institute of Cardiac Surgery, Federal State Budgetary Institution “National Medical Research Center for Cardiovascular Surgery named after A. N. Bakulev” of the Ministry of Health of the Russian Federation, Moscow, Russian Federation

drdeigheidy@gmail.comhttps://orcid.org/0009-0005-9668-1211МасютинаСтефания ЕвгеньевнаMasyutinaStefaniya E.

Master of Science (Politecnico di Milano), ведущий научный сотрудник Малого инновационного предприятия «Лаборатория передовых технологий» при Университете Иннополис, Иннополис, Республика Татарстан, Российская Федерация; научный сотрудник Polytechnic University of Milan, Милан, Италия

Master of Science (Politecnico di Milano), Leading Researcher at the Small Innovative Enterprise “Laboratory of Advanced Technologies” at Innopolis University, Innopolis city, Republic of Tatarstan, Russian Federation; Researcher at Polytechnic University of Milan, Milano, Italy

skaydrite@gmail.comhttps://orcid.org/0000-0002-7444-9930МамалыгаМаксим ЛеонидовичMamalygaMaxim L.

доктор медицинских наук ведущий научный сотрудник отдела хирургического лечения ишемической болезни сердца института коронарной и сосудистой хирургии федерального государственного бюджетного учреждения «Национальный медицинский исследовательский центр сердечно-сосудистой хирургии имени А. Н. Бакулева» Министерства здравоохранения Российской Федерации, Москва, Российская Федерация

PhD, MD, Leading Researcher at the Department of Surgical Treatment of Coronary Heart Disease, Institute of Coronary and Vascular Surgery, Federal State Budgetary Institution “National Medical Research Center for Cardiovascular Surgery named after A. N. Bakulev” of the Ministry of Health of the Russian Federation, Moscow, Russian Federation

Федеральное государственное бюджетное учреждение «Национальный медицинский исследовательский центр сердечно-сосудистой хирургии имени А. Н. Бакулева» Министерства здравоохранения Российской Федерации; Малое инновационное предприятие «Лаборатория передовых технологий» при Университете ИннополисРоссияFederal State Budgetary Institution “National Medical Research Center for Cardiovascular Surgery named after A. N. Bakulev” of the Ministry of Health of the Russian Federation; Small Innovative Enterprise “Laboratory of Advanced Technologies” at Innopolis UniversityRussian FederationФедеральное государственное бюджетное учреждение «Национальный медицинский исследовательский центр сердечно-сосудистой хирургии имени А. Н. Бакулева» Министерства здравоохранения Российской ФедерацииРоссияFederal State Budgetary Institution “National Medical Research Center for Cardiovascular Surgery named after A. N. Bakulev” of the Ministry of Health of the Russian FederationRussian FederationМалое инновационное предприятие «Лаборатория передовых технологий» при Университете Иннополис; Polytechnic University of MilanИталияSmall Innovative Enterprise “Laboratory of Advanced Technologies” at Innopolis University; Polytechnic University of MilanItaly202604092026154153163Copyright © Шацкий А.С., Деигхеиди Э.М., Масютина С.Е., Мамалыга М.Л., 20262026Шацкий А.С., Деигхеиди Э.М., Масютина С.Е., Мамалыга М.Л.Shatskiy A.S., Deigheidy E.M., Masyutina S.E., Mamalyga M.L.Данная работа распространяется под лицензией Creative Commons Attribution 4.0.This work is licensed under a Creative Commons Attribution 4.0 License.https://www.nii-kpssz.com/jour/article/view/1877Основные положения

Основные положения

 

 

Резюме

Резюме

Большие языковые модели превратились в мощные инструменты автоматизации первичного скрининга аннотаций при проведении систематических обзоров, позволяя существенно снизить ручной труд. В статье представлен всесторонний обзор принципов формирования запросов (промпт-инжиниринга), демонстрирующий, как традиционные критерии для метаанализа можно преобразовать в четкие инструкции для искусственного интеллекта. На примерах тематических исследований в области хирургии ишемической болезни сердца и врожденных пороков сердца мы иллюстрируем влияние составления промптов на полноту охвата, точность и общую эффективность скрининга литературных источников. Кроме того, рассматриваются типичные ошибки, а также подчеркивается сохраняющаяся необходимость экспертного контроля для минимизации галлюцинаций и смещений, присущих выводам искусственного интеллекта. В итоге систематический промпт-инжиниринг в сочетании с экспертной оценкой позволяет исследователям в сердечно-сосудистой хирургии оптимизировать поиск источников для метаанализа на базе больших языковых моделей, обеспечивая более быстрый и всесторонний синтез доказательной базы и методов обработки первичного материала.

Highlights

Highlights

 

 

Abstract

Abstract

Large Language Models have evolved into powerful tools for automating the primary screening of articles’ abstracts in systematic reviews, enabling a significant reduction in manual labor. The article presents a comprehensive review of prompt engineering principles, demonstrating how traditional meta-analysis criteria can be transformed into clear instructions for artificial intelligence. Using case studies in coronary artery bypass grafting and congenital heart disease surgery, we illustrate the impact of prompt formulation on the comprehensiveness, accuracy, and overall efficiency of literature screening. Furthermore, typical errors are discussed, and the ongoing necessity of expert oversight to minimize hallucinations and biases inherent in artificial intelligence conclusions is emphasized. Ultimately, systematic prompt engineering combined with expert evaluation allows researchers in cardiovascular surgery to optimize the search for meta-analysis sources based on Large Language Models, ensuring a faster and more comprehensive synthesis of evidence and methods for processing primary material.

Систематические обзорыИскусственный интеллектСердечно-сосудистая хирургияПромпт-инжинирингСкрининг источников литературыSystematic reviewsArtificial intelligenceCardiovascular surgeryPrompt engineeringLiterature screeningАвторы заявляют об отсутствии финансирования исследования.ReferencesParums, D. V. Review Articles, Systematic Reviews, Meta-Analysis, and the Updated Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020 Guidelines // Medical Science Monitor. 2021. Vol. 27. P. e934475.Parums, D. V. Review Articles, Systematic Reviews, Meta-Analysis, and the Updated Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020 Guidelines // Medical Science Monitor. 2021. Vol. 27. P. e934475.Waffenschmidt S., Knelangen M., Sieben W., Bühn S., Pieper D. Single Screening versus Conventional Double Screening for Study Selection in Systematic Reviews: A Methodological Systematic Review // BMC Medical Research Methodology. 2019. Vol. 19. Art. No. 132.Waffenschmidt S., Knelangen M., Sieben W., Bühn S., Pieper D. Single Screening versus Conventional Double Screening for Study Selection in Systematic Reviews: A Methodological Systematic Review // BMC Medical Research Methodology. 2019. Vol. 19. Art. No. 132.Bramer W. M., Rethlefsen M. L., Kleijnen J., Franco O. H. Optimal Database Combinations for Literature Searches in Systematic Reviews: A Prospective Exploratory Study // Systematic Reviews. 2017. Vol. 6. Art. No. 245.Bramer W. M., Rethlefsen M. L., Kleijnen J., Franco O. H. Optimal Database Combinations for Literature Searches in Systematic Reviews: A Prospective Exploratory Study // Systematic Reviews. 2017. Vol. 6. Art. No. 245.Cooper C., Booth A., Varley-Campbell J., Britten N., Garside R. Defining the Process to Literature Searching in Systematic Reviews: A Literature Review of Guidance and Supporting Studies // BMC Medical Research Methodology. 2018. Vol. 18. Art. No. 85.Cooper C., Booth A., Varley-Campbell J., Britten N., Garside R. Defining the Process to Literature Searching in Systematic Reviews: A Literature Review of Guidance and Supporting Studies // BMC Medical Research Methodology. 2018. Vol. 18. Art. No. 85.Chai K. E. K., Lines R. L. J., Gucciardi D. F., Ng L. Research Screener: A Machine Learning Tool to Semi-Automate Abstract Screening for Systematic Reviews // Systematic Reviews. 2021. Vol. 10. Art. No. 93.Chai K. E. K., Lines R. L. J., Gucciardi D. F., Ng L. Research Screener: A Machine Learning Tool to Semi-Automate Abstract Screening for Systematic Reviews // Systematic Reviews. 2021. Vol. 10. Art. No. 93.Gates A., Johnson C., Hartling L. Technology-Assisted Title and Abstract Screening for Systematic Reviews: A Retrospective Evaluation of the Abstrackr Machine Learning Tool // Systematic Reviews. 2018. Vol. 7. Art. No. 45.Gates A., Johnson C., Hartling L. Technology-Assisted Title and Abstract Screening for Systematic Reviews: A Retrospective Evaluation of the Abstrackr Machine Learning Tool // Systematic Reviews. 2018. Vol. 7. Art. No. 45.Khraisha Q., Put S., Kappenberg J., Warraitch A., Hadfield K. Can Large Language Models Replace Humans in the Systematic Review Process? Evaluating GPT-4’s Efficacy in Screening and Extracting Data from Peer-Reviewed and Grey Literature in Multiple Languages. arXiv:2310.17526 [Preprint]. 2023.Khraisha Q., Put S., Kappenberg J., Warraitch A., Hadfield K. Can Large Language Models Replace Humans in the Systematic Review Process? Evaluating GPT-4’s Efficacy in Screening and Extracting Data from Peer-Reviewed and Grey Literature in Multiple Languages. arXiv:2310.17526 [Preprint]. 2023.Zaghir J., Naguib M., Bjelogrlic M., Névéol A., Tannier X., Lovis C. Prompt Engineering Paradigms for Medical Applications: Scoping Review // Journal of Medical Internet Research. 2024. Vol. 26. P. e60501.Zaghir J., Naguib M., Bjelogrlic M., Névéol A., Tannier X., Lovis C. Prompt Engineering Paradigms for Medical Applications: Scoping Review // Journal of Medical Internet Research. 2024. Vol. 26. P. e60501.Wang Z., Chu Z., Doan T. V., Ni S., Yang M., Zhang W. History, Development, and Principles of Large Language Models: An Introductory Survey // AI Ethics. 2024. P. 1–17.Wang Z., Chu Z., Doan T. V., Ni S., Yang M., Zhang W. History, Development, and Principles of Large Language Models: An Introductory Survey // AI Ethics. 2024. P. 1–17.Shiri F. M., Perumal T., Mustapha N., Mohamed R. A Comprehensive Overview and Comparative Analysis on Deep Learning Models. arXiv:2305.17473 [Preprint]. 2023.Shiri F. M., Perumal T., Mustapha N., Mohamed R. A Comprehensive Overview and Comparative Analysis on Deep Learning Models. arXiv:2305.17473 [Preprint]. 2023.Gue C. C. Y., Rahim N. D. A., Rojas-Carabali W., Agrawal R., Palvannan R. K., Abisheganaden J., Yip W. F. Evaluating the OpenAI’s GPT-3.5 Turbo’s Performance in Extracting Information from Scientific Articles on Diabetic Retinopathy // Systematic Reviews. 2024. Vol. 13. Art. No. 135.Gue C. C. Y., Rahim N. D. A., Rojas-Carabali W., Agrawal R., Palvannan R. K., Abisheganaden J., Yip W. F. Evaluating the OpenAI’s GPT-3.5 Turbo’s Performance in Extracting Information from Scientific Articles on Diabetic Retinopathy // Systematic Reviews. 2024. Vol. 13. Art. No. 135.Wang J., Yang Z., Yao Z., Yu H. JMLR: Joint Medical LLM and Retrieval Training for Enhancing Reasoning and Professional Question Answering Capability. arXiv:2402.17887 [Preprint]. 2024.Wang J., Yang Z., Yao Z., Yu H. JMLR: Joint Medical LLM and Retrieval Training for Enhancing Reasoning and Professional Question Answering Capability. arXiv:2402.17887 [Preprint]. 2024.Huang L., Yu W., Ma W., Zhong W., Feng Z., Wang H., Chen Q., Peng W., Feng X., Qin B., et al. A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions // ACM Transactions on Information Systems. 2025. Vol. 43. P. 1–55.Huang L., Yu W., Ma W., Zhong W., Feng Z., Wang H., Chen Q., Peng W., Feng X., Qin B., et al. A Survey on Hallucination in Large Language Models: Principles, Taxonomy, Challenges, and Open Questions // ACM Transactions on Information Systems. 2025. Vol. 43. P. 1–55.Sclar M., Choi Y., Tsvetkov Y., Suhr A. Quantifying Language Models’ Sensitivity to Spurious Features in Prompt Design or: How I Learned to Start Worrying about Prompt Formatting. arXiv:2310.11324 [Preprint]. 2023.Sclar M., Choi Y., Tsvetkov Y., Suhr A. Quantifying Language Models’ Sensitivity to Spurious Features in Prompt Design or: How I Learned to Start Worrying about Prompt Formatting. arXiv:2310.11324 [Preprint]. 2023.Saloojee H., Pettifor J. M. Maximizing Access and Minimizing Barriers to Research in Low- and Middle-Income Countries: Open Access and Health Equity // Global Health, Science and Practice. 2022. Vol. 10, No. 1. P. e2100403.Saloojee H., Pettifor J. M. Maximizing Access and Minimizing Barriers to Research in Low- and Middle-Income Countries: Open Access and Health Equity // Global Health, Science and Practice. 2022. Vol. 10, No. 1. P. e2100403.Ye A., Maiti A., Schmidt M., Pedersen S. J. A Hybrid Semi-Automated Workflow for Systematic and Literature Review Processes with Large Language Model Analysis // Future Internet. 2024. Vol. 16, No. 5. P. 167.Ye A., Maiti A., Schmidt M., Pedersen S. J. A Hybrid Semi-Automated Workflow for Systematic and Literature Review Processes with Large Language Model Analysis // Future Internet. 2024. Vol. 16, No. 5. P. 167.Liu P., Yuan W., Fu J., Jiang Z., Hayashi H., Neubig G. Pre-Train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing // ACM Computing Surveys. 2023. Vol. 55, No. 9. P. 1–35.Liu P., Yuan W., Fu J., Jiang Z., Hayashi H., Neubig G. Pre-Train, Prompt, and Predict: A Systematic Survey of Prompting Methods in Natural Language Processing // ACM Computing Surveys. 2023. Vol. 55, No. 9. P. 1–35.Eriksen M. B., Frandsen T. F. The Impact of Patient, Intervention, Comparison, Outcome (PICO) as a Search Strategy Tool on Literature Search Quality: A Systematic Review // Journal of the Medical Library Association. 2018. Vol. 106, No. 4. P. 420–431.Eriksen M. B., Frandsen T. F. The Impact of Patient, Intervention, Comparison, Outcome (PICO) as a Search Strategy Tool on Literature Search Quality: A Systematic Review // Journal of the Medical Library Association. 2018. Vol. 106, No. 4. P. 420–431.Kusano G., Akimoto K., Takeoka K. Are Longer Prompts Always Better? Prompt Selection in Large Language Models for Recommendation Systems. arXiv:2412.14454 [Preprint]. 2024.Kusano G., Akimoto K., Takeoka K. Are Longer Prompts Always Better? Prompt Selection in Large Language Models for Recommendation Systems. arXiv:2412.14454 [Preprint]. 2024.Heston T. F., Khun C. Prompt Engineering in Medical Education // International Medical Education. 2023. Vol. 2, No. 4. P. 198–205.Heston T. F., Khun C. Prompt Engineering in Medical Education // International Medical Education. 2023. Vol. 2, No. 4. P. 198–205.Lee J., Hicke Y., Yu R., Brooks C., Kizilcec R. F. The Life Cycle of Large Language Models in Education: A Framework for Understanding Sources of Bias // British Journal of Educational Technology. 2024. Vol. 55, No. 4. P. 1982–2002.Lee J., Hicke Y., Yu R., Brooks C., Kizilcec R. F. The Life Cycle of Large Language Models in Education: A Framework for Understanding Sources of Bias // British Journal of Educational Technology. 2024. Vol. 55, No. 4. P. 1982–2002.Huang D., Bu Q., Zhang J., Xie X., Chen J., Cui H. Bias Testing and Mitigation in LLM-Based Code Generation. arXiv:2309.14345 [Preprint]. 2023.Huang D., Bu Q., Zhang J., Xie X., Chen J., Cui H. Bias Testing and Mitigation in LLM-Based Code Generation. arXiv:2309.14345 [Preprint]. 2023.

The authors declare that there are no conflicts of interest present.