Evaluating large language models for anaphylaxis detection in clinical notes

Autores

  • Matheus Matos Machado University of São Paulo
  • Joice Basílio Machado Marques Sofya
  • Fabrício A. Gualdani Universidade Estadual Paulista
  • Monica Pugliese Heleodoro dos Santos Hospital Sírio-Libanês
  • Fabio Cerqueira Lario Hospital Sírio-Libanês
  • Chayanne Andrade de Araujo Hospital Sírio-Libanês
  • Fabiana Andrade Nunes Oliveira Hospital Sírio-Libanês
  • Luis Felipe Chiaverini Ensina Hospital Sírio-Libanês
  • Ricardo Marcondes Marcacini University of São Paulo
  • Dilvan Moreira University of São Paulo

DOI:

https://doi.org/10.59681/2175-4411.v16.iEspecial.2024.1364

Palavras-chave:

Anafilaxia, Modelos de Linguagem de Grande Escala, Inteligência Artificial

Resumo

Objetivo: Este estudo tem como objetivo avaliar o potencial de quatro Modelos de Linguagem de Grande Escala (LLMs) (GPT-4 Turbo, GPT-3.5 Turbo, Gemini 1.0 Pro e OpenChat 3.5) na detecção de anafilaxia em Registros Médicos Eletrônicos (EMRs). Método: O método empregado envolveu a análise de 150 relatórios médicos, utilizando diferentes prompts para testar a capacidade dos LLMs em identificar a anafilaxia. Resultados: Os resultados indicam que todos os modelos obtiveram zero falsos negativos, com destaque para o GPT-4 Turbo, que alcançou 97% de acurácia e 91% de precisão. Conclusão: Conclui-se que os LLMs demonstram potencial para auxiliar na identificação da anafilaxia, especialmente o GPT-4 Turbo. A pesquisa reforça a importância do design eficiente de prompts para otimizar a acurácia dos resultados.

Biografias Autor

Matheus Matos Machado, University of São Paulo

B.Sc., Department of Computer Science, University of São Paulo (USP), São Carlos (SP), Brazil.

Joice Basílio Machado Marques, Sofya

Ph.D., Department of Research, Sofya, São Paulo (SP), Brazil.

Fabrício A. Gualdani, Universidade Estadual Paulista

M.Sc., Department of Information Science, Universidade Estadual Paulista (UNESP), Marília (SP), Brazil.

Monica Pugliese Heleodoro dos Santos, Hospital Sírio-Libanês

M.Sc., Division of Allergy, Hospital Sírio-Libanês, São Paulo (SP), Brazil.

Fabio Cerqueira Lario, Hospital Sírio-Libanês

Ph.D., Division of Allergy, Hospital Sírio-Libanês, São Paulo (SP), Brazil.

Chayanne Andrade de Araujo, Hospital Sírio-Libanês

M.Sc., Division of Allergy, Hospital Sírio-Libanês, São Paulo (SP), Brazil.

Fabiana Andrade Nunes Oliveira, Hospital Sírio-Libanês

M.Sc., Division of Allergy, Hospital Sírio-Libanês, São Paulo (SP), Brazil.

Luis Felipe Chiaverini Ensina, Hospital Sírio-Libanês

Ph.D., Division of Allergy, Hospital Sírio-Libanês, São Paulo (SP), Brazil.

Ricardo Marcondes Marcacini, University of São Paulo

Ph.D., Department of Computer Science, University of São Paulo (USP), São Carlos (SP), Brazil.

Dilvan Moreira, University of São Paulo

Ph.D., Department of Computer Science, University of São Paulo (USP), São Carlos (SP), Brazil.

Referências

Simons FER, Ardusso LR, Bilò MB, Cardona V, Ebisawa M, El-Gamal YM, et al. International consensus on (ICON) anaphylaxis. World Allergy Organ J. 2014;7(1):9. doi: 10.1186/1939-4551-7-9. PMID: 24920969; PMCID: PMC4038846. DOI: https://doi.org/10.1186/1939-4551-7-9

Ensina LF, Min TK, Félix MMR, de Alcântara CT, Costa C. Acute urticaria and anaphylaxis: Differences and similarities in clinical management. Front Allergy. 2022;3:840999. Available from: https://www.frontiersin.org/articles/10.3389/falgy.2022.840999. DOI: https://doi.org/10.3389/falgy.2022.840999

Cardona V, Ansotegui IJ, Ebisawa M, El-Gamal Y, Fernandez Rivas M, Fineman S, et al. World Allergy Organization anaphylaxis guidance 2020. World Allergy Organ J. 2020 Oct;13(10):100472. doi: 10.1016/j.waojou.2020.100472. Available from: https://linkinghub.elsevier.com/retrieve/pii/S1939455120303756. DOI: https://doi.org/10.1016/j.waojou.2020.100472

Liu X, Shi Y, Zhang D, Chen M, Xu Y, Zhao J, et al. Management of immune related adverse events through electronic multidisciplinary consultation: Five years of experience from Peking Union Medical College Hospital. J Clin Oncol. 2023;41(16_suppl)

. doi: 10.1200/JCO.2023.41.16_suppl.e14712. Available from: https://doi.org/10.1200/JCO.2023.41.16_suppl.e14712. DOI: https://doi.org/10.1200/JCO.2023.41.16_suppl.e14712

Gao Y, Li R, Caskey J, Dligach D, Miller T, Churpek MM, et al. Leveraging a medical knowledge graph into large language models for diagnosis prediction. arXiv [cs]. 2023 Aug. Available from: http://arxiv.org/abs/2308.14321. DOI: https://doi.org/10.2196/preprints.58670

Carrell DS, Gruber S, Floyd JS, Bann MA, Cushing-Haugen KL, Johnson RL, et al. Improving methods of identifying anaphylaxis for medical product safety surveillance using natural language processing and machine learning. Am J Epidemiol. 2023 Feb;192(2):283-295. doi: 10.1093/aje/kwac182. Available from: https://academic.oup.com/aje/article/192/2/283/6795959. DOI: https://doi.org/10.1093/aje/kwac182

Kural KC, Mazo I, Walderhaug M, Santana-Quintero L, Karagiannis K, Thompson EE, et al. Using machine learning to improve anaphylaxis case identification in medical claims data. JAMIA Open. 2023 Oct;6(4). doi: 10.1093/jamiaopen/ooad090. Available from: https://academic.oup.com/jamiaopen/article/doi/10.1093/jamiaopen/ooad090/7331170. DOI: https://doi.org/10.1093/jamiaopen/ooad090

Tu H, Han L, Nenadic G. Extraction of medication and temporal relation from clinical text using neural language models. arXiv [cs]. 2023 Oct. doi: 10.48550/arXiv.2310.02229. Available from: http://arxiv.org/abs/2310.02229. DOI: https://doi.org/10.1109/BigData59044.2023.10386489

Pan J, Zhang Z, Peters SR, Vatanpour S, Walker RL, Lee S, et al. Cerebrovascular disease case identification in inpatient electronic medical record data using natural language processing. Brain Inform. 2023 Sep;10(1):22. doi: 10.1186/s40708-023-00203-w. Available from: https://doi.org/10.1186/s40708-023-00203-w. DOI: https://doi.org/10.1186/s40708-023-00203-w

Lin E, Zwolinski R, Wu JT, La J, Goryachev S, Huhmann L, et al. Machine learning-based natural language processing to extract PD-L1 expression levels from clinical notes. Health Inform J. 2023 Jul;29(3):14604582231198021. doi: 10.1177/14604582231198021. Available from: http://journals.sagepub.com/doi/10.1177/14604582231198021. DOI: https://doi.org/10.1177/14604582231198021

Zitu MM, Zhang S, Owen DH, Chiang C, Li L. Generalizability of machine learning methods in detecting adverse drug events from clinical narratives in electronic medical records. Front Pharmacol. 2023 Jul;14:1218679. doi: 10.3389/fphar.2023.1218679. Available from: https://www.frontiersin.org/articles/10.3389/fphar.2023.1218679/full. DOI: https://doi.org/10.3389/fphar.2023.1218679

Afshar M, Adelaine S, Resnik F, Mundt MP, Long J, Leaf M, et al. Deployment of real-time natural language processing and deep learning clinical decision support in the electronic health record: Pipeline implementation for an opioid misuse screener in hospitalized adults. JMIR Med Inform. 2023 Apr;11. doi: 10.2196/44977. Available from: https://medinform.jmir.org/2023/1/e44977. DOI: https://doi.org/10.2196/44977

Oliveira LES, Peters AC, Silva AMP, Gebeluca CP, Gumiel YB, Cintho LMM, et al. SemClinBr - a multi-institutional and multi-specialty semantically annotated corpus for Portuguese clinical NLP tasks. J Biomed Semantics. 2022 May;13(1):1. doi: 10.1186/s13326-022-00269-1. Available from: https://doi.org/10.1186/s13326-022-00269-1. DOI: https://doi.org/10.1186/s13326-022-00269-1

Wang G, Cheng S, Zhan X, Li X, Song S, Liu Y. OpenChat: Advancing open-source language models with mixed-quality data. arXiv [cs.CL]. 2024. Available from: https://arxiv.org/abs/2309.11235.

Publicado

2024-11-19

Como Citar

Machado, M. M., Marques, J. B. M., Gualdani, F. A., dos Santos, M. P. H., Lario, F. C., de Araujo, C. A., … Moreira, D. (2024). Evaluating large language models for anaphylaxis detection in clinical notes. Journal of Health Informatics, 16(Especial). https://doi.org/10.59681/2175-4411.v16.iEspecial.2024.1364

Artigos Similares

<< < 10 11 12 13 14 15 16 17 18 19 > >> 

Também poderá iniciar uma pesquisa avançada de similaridade para este artigo.