Synapse: Automated Generation of Systematic Review Protocols and AI-Assisted Screening with Large Language Models
Resumo
The exponential growth of scientific output makes systematic literature reviews (SLRs) increasingly costly to conduct manually. This paper investigates large language models (LLMs) for methodological planning and study screening in a Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA)-based workflow. Synapse generates review protocols from a researcher’s intent and assigns relevance scores to candidate studies. In an exploratory evaluation, protocol generation reached a mean cosine similarity of 0.60 across three protocol cases, while screening reached mean recall 0.967 and WSS@95 0.853 on three low-prevalence SYNERGY corpora. On the same corpora, Synapse matched ASReview’s mean recall (0.967) and obtained higher WSS@95 (0.853 versus 0.791).
Referências
Chase, H. (2022). LangChain. [link]. Acesso em: maio 2026.
Cohen, A. M., Hersh, W. R., Peterson, K., and Yen, P.-Y. (2006). Reducing workload in systematic review preparation using automated citation classification. Journal of the American Medical Informatics Association, 13(2):206–219.
De Bruin, J., Ma, Y., Ferdinands, G., Teijema, J., and Van de Schoot, R. (2023). SYNERGY — open machine learning dataset on study selection in systematic reviews.
DeepSeek-AI (2024). DeepSeek-V3 technical report.
Donners, A. A. M. T., Rademaker, C. M. A., Bevers, L. A. M., Schutgens, R. E. G., Fischer, K., Leebeek, F. W. G., and Huitema, A. D. R. (2021). Pharmacokinetics and associated efficacy of emicizumab in humans: A systematic review. Clinical Pharmacokinetics, 60(11):1395–1406.
Freitas, F. (2015). Parsifal: A tool to support researchers to perform systematic literature reviews. [link]. Acesso em: maio 2026.
Hall, T., Beecham, S., Bowes, D., Gray, D., and Counsell, S. (2012). A systematic literature review on fault prediction performance in software engineering. IEEE Transactions on Software Engineering, 38(6):1276–1304.
Harrison, H., Griffin, S. J., Kuhn, I., and Usher-Smith, J. A. (2020). Software tools to support title and abstract screening for systematic reviews in healthcare: an evaluation. BMC Medical Research Methodology, 20(1):7.
Khraisha, Q., Put, S., Kappenberg, J., Warraitch, A., and Hadfield, K. (2024). Can large language models replace humans in systematic reviews? evaluating GPT-4’s efficacy in screening and extracting data from peer-reviewed and grey literature in multiple languages. Research Synthesis Methods.
Kitchenham, B. A. and Charters, S. (2007). Guidelines for performing systematic literature reviews in software engineering. Technical Report EBSE 2007-001, Keele University and Durham University.
Kuhn, H. W. (1955). The Hungarian method for the assignment problem. Naval Research Logistics Quarterly, 2(1–2):83–97.
Mengist, W., Soromessa, T., and Legese, G. (2020). Ecosystem services research in mountainous regions: A systematic literature review on current knowledge and research gaps. Science of the Total Environment, 702:134581.
National Science Board, National Science Foundation (2023). Publications output: U.S. trends and international comparisons. Science and engineering indicators 2024. nsb-2023-33, National Center for Science and Engineering Statistics (NCSES), Alexandria, VA. Acesso em: jun. 2026.
Oud, M., Arntz, A., Hermens, M. L. M., Verhoef, R., and Kendall, T. (2018). Specialized psychotherapies for adults with borderline personality disorder: A systematic review and meta-analysis. Australian & New Zealand Journal of Psychiatry, 52(10):949–961.
Ouzzani, M., Hammady, H., Fedorowicz, Z., and Elmagarmid, A. (2016). Rayyan — a web and mobile app for systematic reviews. Systematic Reviews, 5(1):210.
Page, M. J., Moher, D., Bossuyt, P. M., Boutron, I., Hoffmann, T. C., Mulrow, C. D., Shamseer, L., Tetzlaff, J. M., Akl, E. A., Brennan, S. E., Chou, R., Glanville, J., Grimshaw, J. M., Hróbjartsson, A., Lalu, M. M., Li, T., Loder, E. W., Mayo-Wilson, E., McDonald, S., McGuinness, L. A., Stewart, L. A., Thomas, J., Tricco, A. C., Welch, V. A., Whiting, P., and McKenzie, J. E. (2021). PRISMA 2020 explanation and elaboration: updated guidance and exemplars for reporting systematic reviews. BMJ, 372:n160.
Pinna, T. and Edwards, D. J. (2020). A systematic review of associations between interoception, vagal tone, and emotional regulation: Potential applications for mental health, wellbeing, psychological flexibility, and chronic conditions. Frontiers in Psychology, 11:1792.
Reimers, N. and Gurevych, I. (2019). Sentence-BERT: Sentence embeddings using Siamese BERT-networks. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing (EMNLP-IJCNLP), pages 3982–3992.
Sanghera, R., Thirunavukarasu, A. J., El Khoury, M., O’Logbon, J., Chen, Y., Watt, A., Mahmood, M., Butt, H., Nishimura, G., and Soltan, A. (2025). High-performance automated abstract screening with large language model ensembles. Journal of the American Medical Informatics Association, 32(5):893–905.
Scott, A. M., Forbes, C., Clark, J., Carter, M., Glasziou, P., and Munn, Z. (2021). Systematic review automation tools improve efficiency but lack of knowledge impedes their adoption: a survey. Journal of Clinical Epidemiology, 138:80–94.
Singh, A., D’Arcy, M., Cohan, A., Downey, D., and Feldman, S. (2023). SciRepEval: A multi-format benchmark for scientific document representations. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 5548–5566, Singapore. Association for Computational Linguistics.
Tsampasian, V., Elghazaly, H., Chattopadhyay, R., Debski, M., Naing, T. K. P., Garg, P., Clark, A., Ntatsaki, E., and Vassiliou, V. S. (2023). Risk factors associated with post-COVID-19 condition: A systematic review and meta-analysis. JAMA Internal Medicine, 183(6):566–580.
van de Schoot, R., de Bruin, J., Schram, R., Zahedi, P., de Boer, J., Weijdema, F., Kramer, B., Huijts, M., Hoogerwerf, M., Ferdinands, G., Harkema, A., Willemsen, J., Ma, Y., Fang, Q., Hindriks, S., Tummers, L., and Oberski, D. L. (2021). An open source machine learning framework for efficient and transparent systematic reviews. Nature Machine Intelligence, 3(2):125–133.
Veritas Health Innovation (2023). Covidence systematic review software. [link]. Acesso em: maio 2026.
Wang, S., Scells, H., Zhuang, S., Potthast, M., Koopman, B., and Zuccon, G. (2024). Zero-shot generative large language models for systematic review screening automation. In Advances in Information Retrieval (ECIR 2024).
Wilson, E. B. (1927). Probable inference, the law of succession, and statistical inference. Journal of the American Statistical Association, 22(158):209–212.
Cohen, A. M., Hersh, W. R., Peterson, K., and Yen, P.-Y. (2006). Reducing workload in systematic review preparation using automated citation classification. Journal of the American Medical Informatics Association, 13(2):206–219.
De Bruin, J., Ma, Y., Ferdinands, G., Teijema, J., and Van de Schoot, R. (2023). SYNERGY — open machine learning dataset on study selection in systematic reviews.
DeepSeek-AI (2024). DeepSeek-V3 technical report.
Donners, A. A. M. T., Rademaker, C. M. A., Bevers, L. A. M., Schutgens, R. E. G., Fischer, K., Leebeek, F. W. G., and Huitema, A. D. R. (2021). Pharmacokinetics and associated efficacy of emicizumab in humans: A systematic review. Clinical Pharmacokinetics, 60(11):1395–1406.
Freitas, F. (2015). Parsifal: A tool to support researchers to perform systematic literature reviews. [link]. Acesso em: maio 2026.
Hall, T., Beecham, S., Bowes, D., Gray, D., and Counsell, S. (2012). A systematic literature review on fault prediction performance in software engineering. IEEE Transactions on Software Engineering, 38(6):1276–1304.
Harrison, H., Griffin, S. J., Kuhn, I., and Usher-Smith, J. A. (2020). Software tools to support title and abstract screening for systematic reviews in healthcare: an evaluation. BMC Medical Research Methodology, 20(1):7.
Khraisha, Q., Put, S., Kappenberg, J., Warraitch, A., and Hadfield, K. (2024). Can large language models replace humans in systematic reviews? evaluating GPT-4’s efficacy in screening and extracting data from peer-reviewed and grey literature in multiple languages. Research Synthesis Methods.
Kitchenham, B. A. and Charters, S. (2007). Guidelines for performing systematic literature reviews in software engineering. Technical Report EBSE 2007-001, Keele University and Durham University.
Kuhn, H. W. (1955). The Hungarian method for the assignment problem. Naval Research Logistics Quarterly, 2(1–2):83–97.
Mengist, W., Soromessa, T., and Legese, G. (2020). Ecosystem services research in mountainous regions: A systematic literature review on current knowledge and research gaps. Science of the Total Environment, 702:134581.
National Science Board, National Science Foundation (2023). Publications output: U.S. trends and international comparisons. Science and engineering indicators 2024. nsb-2023-33, National Center for Science and Engineering Statistics (NCSES), Alexandria, VA. Acesso em: jun. 2026.
Oud, M., Arntz, A., Hermens, M. L. M., Verhoef, R., and Kendall, T. (2018). Specialized psychotherapies for adults with borderline personality disorder: A systematic review and meta-analysis. Australian & New Zealand Journal of Psychiatry, 52(10):949–961.
Ouzzani, M., Hammady, H., Fedorowicz, Z., and Elmagarmid, A. (2016). Rayyan — a web and mobile app for systematic reviews. Systematic Reviews, 5(1):210.
Page, M. J., Moher, D., Bossuyt, P. M., Boutron, I., Hoffmann, T. C., Mulrow, C. D., Shamseer, L., Tetzlaff, J. M., Akl, E. A., Brennan, S. E., Chou, R., Glanville, J., Grimshaw, J. M., Hróbjartsson, A., Lalu, M. M., Li, T., Loder, E. W., Mayo-Wilson, E., McDonald, S., McGuinness, L. A., Stewart, L. A., Thomas, J., Tricco, A. C., Welch, V. A., Whiting, P., and McKenzie, J. E. (2021). PRISMA 2020 explanation and elaboration: updated guidance and exemplars for reporting systematic reviews. BMJ, 372:n160.
Pinna, T. and Edwards, D. J. (2020). A systematic review of associations between interoception, vagal tone, and emotional regulation: Potential applications for mental health, wellbeing, psychological flexibility, and chronic conditions. Frontiers in Psychology, 11:1792.
Reimers, N. and Gurevych, I. (2019). Sentence-BERT: Sentence embeddings using Siamese BERT-networks. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing (EMNLP-IJCNLP), pages 3982–3992.
Sanghera, R., Thirunavukarasu, A. J., El Khoury, M., O’Logbon, J., Chen, Y., Watt, A., Mahmood, M., Butt, H., Nishimura, G., and Soltan, A. (2025). High-performance automated abstract screening with large language model ensembles. Journal of the American Medical Informatics Association, 32(5):893–905.
Scott, A. M., Forbes, C., Clark, J., Carter, M., Glasziou, P., and Munn, Z. (2021). Systematic review automation tools improve efficiency but lack of knowledge impedes their adoption: a survey. Journal of Clinical Epidemiology, 138:80–94.
Singh, A., D’Arcy, M., Cohan, A., Downey, D., and Feldman, S. (2023). SciRepEval: A multi-format benchmark for scientific document representations. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 5548–5566, Singapore. Association for Computational Linguistics.
Tsampasian, V., Elghazaly, H., Chattopadhyay, R., Debski, M., Naing, T. K. P., Garg, P., Clark, A., Ntatsaki, E., and Vassiliou, V. S. (2023). Risk factors associated with post-COVID-19 condition: A systematic review and meta-analysis. JAMA Internal Medicine, 183(6):566–580.
van de Schoot, R., de Bruin, J., Schram, R., Zahedi, P., de Boer, J., Weijdema, F., Kramer, B., Huijts, M., Hoogerwerf, M., Ferdinands, G., Harkema, A., Willemsen, J., Ma, Y., Fang, Q., Hindriks, S., Tummers, L., and Oberski, D. L. (2021). An open source machine learning framework for efficient and transparent systematic reviews. Nature Machine Intelligence, 3(2):125–133.
Veritas Health Innovation (2023). Covidence systematic review software. [link]. Acesso em: maio 2026.
Wang, S., Scells, H., Zhuang, S., Potthast, M., Koopman, B., and Zuccon, G. (2024). Zero-shot generative large language models for systematic review screening automation. In Advances in Information Retrieval (ECIR 2024).
Wilson, E. B. (1927). Probable inference, the law of succession, and statistical inference. Journal of the American Statistical Association, 22(158):209–212.
Publicado
19/10/2026
Como Citar
CRUZ, KevinWashington Azevedo da; TORRES, Renato Hidaka; SAMPAIO NETO, Nelson Cruz.
Synapse: Automated Generation of Systematic Review Protocols and AI-Assisted Screening with Large Language Models. In: ENCONTRO NACIONAL DE INTELIGÊNCIA ARTIFICIAL E COMPUTACIONAL (ENIAC), 23. , 2026, Cuiabá/MT.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 3391-3402.
ISSN 2763-9061.
DOI: https://doi.org/10.5753/eniac.2026.31381.
