Além da Automação: Decifrando o Alinhamento de Aplicações de Inteligência Artificial com os Manuais de Revisões Sistemáticas

Mariluci Zanela; Deborah Ribeiro Carvalho; Ricardo Mendes Junior

doi:10.36489/saudecoletiva.2025v15i93p14751-14770

Autores

Mariluci Zanela Doutoranda do Programa de Pós-graduação em Gestão da Informação da Universidade Federal do Paraná. https://orcid.org/0009-0001-5436-5609
Deborah Ribeiro Carvalho Professora do Programa de Pós-graduação em Gestão da Informação da Universidade Federal do Paraná. https://orcid.org/0000-0002-9735-650X
Ricardo Mendes Junior Professor do Programa de Pós-graduação em Gestão da Informação da Universidade Federal do Paraná. https://orcid.org/0000-0003-4947-0364

DOI:

https://doi.org/10.36489/saudecoletiva.2025v15i93p14751-14770

Palavras-chave:

Revisões sistemáticas como assunto, Metodologia, Revisão sistemática, Armazenamento, Recuperação da informação, Saúde, Inteligência artificial, Aprendizado de máquina

Resumo

Revisões Sistemáticas (RS) representam uma metodologia consolidada para a síntese de evidências científicas na área da saúde, sua condução exige rigor metodológico, preconizado pelos manuais JBI e Cochrane. Avanços tecnológicos, como a Inteligência Artificial (IA) foram integrados às RS, automatizando etapas e otimizando recursos. Este estudo identificou como as aplicações baseadas em IA utilizadas na elaboração de RS da área da saúde se alinham a estes manuais, avaliando 29 estudos que empregaram IA em diferentes etapas da RS. A análise revelou que 51,7% (15 estudos) atenderam aos manuais, enquanto os 48,3% (14 estudos) não atenderam. A etapa de Seleção (primeira triagem), representou 89,7% dos estudos (26 de 29). Enquanto etapas como formulação de estratégia de busca, avaliação de risco de viés e síntese de resultados não foram abordadas. Conclui-se que, para garantir a confiabilidade das RS apoiadas por IA, é necessário alinhar essas ferramentas às diretrizes metodológicas dos manuais, bem como de um esforço conjunto entre desenvolvedores de softwares e a comunidade científica.

Referências

Page MJ, McKenzie JE, Bossuyt PM, Boutron I, Hoffmann TC, Mulrow CD, Shamseer L, Tetzlaff JMMJ, et al. The PRISMA 2020 statement: an updated guideline for reporting systematic reviews. BMJ. 2021;29(372). Disponível em: https://doi.org/10.1136/bmj.n71

Clarke M, Chalmers I. Reflections on the history of systematic reviews. BMJ Evid Based Med. 2018;23(4):121-122. Disponível em: https://doi.org/10.1136/bmjebm-2018-110968

Ahn HS, Kim HJ. An introduction to systematic review. J Korean Med Assoc. 2014;57(1):49-59. Disponível em: https://www.researchgate.net/publication/272396557_An_introduction_to_systematic_review

Aromataris E, Lockwood C, Porritt K, Pilla B, Jordan Z, Editors. JBI Manual for Evidence Synthesis. JBI; 2024. Disponível em: https://synthesismanual.jbi.global

Higgins JPT, Thomas J, Chandler J, Cumpston M, Li T, Page MJ, et al., Editors. Cochrane Handbook for Systematic Reviews of Interventions. Version 6.5, 2024. Disponível em; https://training.cochrane.org/handbook/current

Gusenbauer M, Haddaway NR. What every researcher should know about searching – Clarifying the fundamentals of literature searching. Res Synth Methods. 2020;11(3):136-147. Disponível em: https://doi.org/10.1002/jrsm.1427

Ioannidis JPA. The mass production of redundant, misleading, and conflicted systematic reviews and meta-analyses. Milbank Quarterly. 2016;94(3):485-514. Disponível em: https://doi.org/10.1111/1468-0009

Blaizot A, Veettil SK, Saidoung P, Moreno-Garcia CF, Wiratunga N, Aceves-Martins M, Lai NM, Chaiyakunapruk N. Using artificial intelligence methods for systematic review in health sciences: a systematic review. Res Synth Methods. 2022;13(3):353-362. Disponível em: https://doi.org/10.1002/jrsm.1553

Tóth B, Berek l, Gulácsi l, et al. automation of systematic reviews of biomedical literature: a scoping review of studies indexed in Pubmed. Syst Rev. 2024;13:174. Disponível em: https://doi.org/10.1186/s13643-024-02592-3.

Gil AC. Como elaborar projetos de pesquisa. 6. ed. São Paulo: Atlas; 2017.

Bekhuis T, Demner-Fushman D. Screening nonrandomized studies for medical systematic reviews: a comparative study of classifiers. Artif Intell Med. 2012;55(3):197-207. Disponível em: https://doi.org/10.1016/j.artmed.2012.05.002

Jonnalagadda S, Petitti D. A new iterative method to reduce workload in systematic review process. Int J Comput Biol Drug Des. 2013;6(1-2):5-17. Disponível em; https://doi.org/10.1504/ijcbdd.2013.052198

Kim S, Choi J. Improving the performance of text categorization models used for the selection of high quality articles. Healthc Inform Res. 2012;18(1):18-28. Disponível em: https://doi.org/10.4258/hir.2012.18.1.18

Blake C, Lucic A. Automatic endpoint detection to support the systematic review process. J Biomed Inform. 2015 Aug;56:42-56. Disponível em: https://doi.org/10.1016/j.jbi.2015.05.004

Rathbone J, Hoffmann T, Glasziou P. Faster title and abstract screening? Evaluating Abstrackr, a semi-automated online screening program for systematic reviewers. Syst Rev. 2015;4:80. Disponível em: https://doi.org/10.1186/s13643-015-0067-6

Hashimoto K, Kontonatsios G, Miwa M, Ananiadou S. Topic detection using paragraph vectors to support active learning in systematic reviews. J Biomed Inform. 2016;62:59-65. Disponível em: https://pmc.ncbi.nlm.nih.gov/articles/PMC4981645/

Przybyła P, Brockmeier AJ, Kontonatsios G, Le Pogam MA, McNaught J, von Elm E, Nolan K, Ananiadou S. Prioritising references for systematic reviews with RobotAnalyst: a user study. Res Synth Methods. 2018;9(3):470-488. Disponível em: https://doi.org/10.1002/jrsm.1311

Tsafnat G, Glasziou P, Karystianis G, Coiera E. Automated screening of research studies for systematic reviews using study characteristics. Syst Rev. 2018 Apr 25;7(1):64. Disponível em: https://doi.org/10.1186/s13643-018-0724-7

Bucheli Guerrero VA. Desarrollo del estado del arte en investigación: una herramienta basada en inteligencia artificial. Rev Politécnica. 2019;15(30):70-81. Disponível em; http://dx.doi.org/10.33571/rpolitec.v15n30a7

Gartlehner G, Wagner G, Lux L, Affengruber L, Dobrescu A, Kaminski-Hartenthaler A, Viswanathan M. Assessing the accuracy of machine-assisted abstract screening with DistillerAI: a user study. Syst Rev. 2019;8(1):277. Disponível em: https://doi.org/10.1186/s13643-019-1221-3

Gates A, Guitard S, Pillay J, Elliott SA, Dyson MP, Newton AS, Hartling L. Performance and usability of machine learning for screening in systematic reviews: a comparative evaluation of three tools. Syst Rev. 2019;8(1):278. Disponível em; https://doi.org/10.1186/s13643-019-1222-2

Gates A, Gates M, Sebastianski M, Guitard S, Elliott SA, Hartling L. The semi-automation of title and abstract screening: a retrospective exploration of ways to leverage Abstrackr's relevance predictions in systematic and rapid reviews. BMC Med Res Methodol. 2020;20(1):139. Disponível em: https://doi.org/10.1186/s12874-020-01031-w

Howard BE, Phillips J, Tandon A, Maharana A, Elmore R, Mav D, Sedykh A, Thayer K, et al. SWIFT-Active Screener: accelerated document screening through active learning and integrated recall estimation, Environ Int. 2020;138:105623. Disponível em: https://doi.org/10.1016/j.envint.2020.105623

Orgeolet L, Foulquier N, Misery L, Redou P, Pers JO, Devauchelle-Pensec V, Saraux A. Can artificial intelligence replace manual search for systematic literature? Review on cutaneous manifestations in primary Sjögren's syndrome. Rheumatology (Oxford). 2020;59(4):811-819. Disponível em; https://doi.org/10.1093/rheumatology/kez370

Popoff E, Besada M, Jansen JP, Cope S, Kanters S. Aligning text mining and machine learning algorithms with best practices for study selection in systematic literature reviews. Syst Rev. 2020 Dec 13;9(1):293. Disponível em: https://doi.org/10.1186/s13643-020-01520-5

Burns JK, Etherington C, Cheng-Boivin O, Boet S. Using an artificial intelligence tool can be as accurate as human assessors in level one screening for a systematic review. Health Info Libr J. 2024;41(2):136-148. Disponível em: https://doi.org/10.1111/hir.12413 Epub 2021. PMID: 34792285.

Chai KEK, Lines RLJ, Gucciardi DF, Ng L. Research Screener: a machine learning tool to semi-automate abstract screening for systematic reviews. Syst Rev. 2021;10(1):93. Disponível em: https://doi.org/10.1186/s13643-021-01635-3

Pham B, Jovanovic J, Bagheri E, Antony J, Ashoor H, Nguyen TT, Rios P, Robson R, Thomas SM, Watt J, Straus SE, Tricco AC. Text mining to support abstract screening for knowledge syntheses: a semi-automated workflow. Syst Rev. 2021;10(1):156. Disponível em: https://doi.org/10.1186/s13643-021-01700-x .

Qin X, Liu J, Wang Y, Liu Y, Deng K, Ma Y, Zou K, Li L, Sun X. Natural language processing was effective in assisting rapid title and abstract screening when updating systematic reviews. J Clin Epidemiol. 2021;133:121-129. Disponível em: https://doi.org/10.1016/j.jclinepi.2021.01.010.

Borissov N, Haas Q, Minder B, Kopp-Heim D, von Gernler M, Janka H, Teodoro D, Amini P. Reducing systematic review burden using Deduklick: a novel, automated, reliable, and explainable deduplication algorithm to foster medical research. Syst Rev. 2022;11(1):172. Disponível em: https://doi.org/10.1186/s13643-022-02045-9 .

Facchinetti T, Benetti G, Giuffrida D, Nocera A. Slr-kit: a semi-supervised machine learning framework for systematic literature reviews. Knowledge-Based Systems. 2022;251:109266. Disponível em: https://doi.org/10.1016/j.knosys.2022.109266.

Muller AE, Ames HMR, Jardim PSJ, Rose CJ. Machine learning in systematic reviews: Comparing automated text clustering with Lingo3G and human researcher categorization in a rapid review. Res Synth Methods. 2022 Mar;13(2):229-241. Disponível em: https://doi.org/10.1002/jrsm.1541 .

Reis AHS, de Oliveira ALM, Fritsch C, Zouch J, Ferreira P, Polese JC. Usefulness of machine learning softwares to screen titles of systematic reviews: a methodological study. Syst Rev. 2023;12(1):68. Disponível em: https://doi.org/10.1186/s13643-023-02231-3 .

Kebede MM, Le Cornet C, Fortner RT. In-depth evaluation of machine learning methods for semi-automating article screening in a systematic review of mechanistic literature. Res Synth Methods. 2023 Mar;14(2):156-172. Dispon[ivel em: https://doi.org/10.1002/jrsm.1589 .

Li J, Kabouji J, Bouhadoun S, Tanveer S, Filion KB, Gore G, Josephson CB, Kwon CS, et al. Sensitivity and specificity of alternative screening methods for systematic reviews using text mining tools. J Clin Epidemiol. 2023;162:72-80. Disponível em: https://doi.org/10.1016/j.jclinepi.2023.07.010 .

Natukunda A, Muchene LK. Unsupervised title and abstract screening for systematic review: a retrospective case-study using topic modelling methodology. Syst Rev. 2023 Jan 3;12(1):1. Disponível em: https://doi.org/10.1186/s13643-022-02163-4 .

Oude Wolcherink MJ, Pouwels XGLV, van Dijk SHB, Doggen CJM, Koffijberg H. Can artificial intelligence separate the wheat from the chaff in systematic reviews of health economic articles? Expert Rev Pharmacoecon Outcomes Res. 2023;23(9):1049-1056. Disponível em: https://doi.org/10.1080/14737167.2023.2234639 .

Qureshi R, Shaughnessy D, Gill KAR, Robinson KA, Li T, Agai E. Are ChatGPT and large language models "the answer" to bringing us closer to systematic review automation? Syst Rev. 2023 Apr 29;12(1):72. Disponível em: https://doi.org/10.1186/s13643-023-02243-z .

Van Dijk SHB, Brusse-Keizer MGJ, Bucsán CC, Van der Palen J, Doggen CJM, Lenferink A. Artificial intelligence in systematic reviews: promising when appropriately used. BMJ Open. 2023;13:e072254. Disponível em: https://doi.org/10.1136/bmjopen-2023-072254 .