Natural Language Processing for Allergen Identification on Food Labels: An Application in the Brazilian Context
DOI:
https://doi.org/10.59681/2175-4411.v16.iEspecial.2024.1325Keywords:
Natural Language Processing, Food Hypersensitivity, Food LabelingAbstract
Objective: Food allergies impact a significant portion of the population, presenting challenges to public health. The approach to managing these allergies is by the elimination of specific trigger foods. However, reading and interpreting food labels is challenging due to diverse and inconsistent nomenclature, as well as inadequate regulations. For the Brazilian context, we propose a Natural Language Processing solution, which will be integrated into a dedicated mobile application. Method: To recognize the diverse nomenclatures associated with allergens focusing on Portuguese terms, we developed an allergen database and a named entity recognition model, as well as text preprocessing functions. Results. The evaluation of the models achieved an average precision of 96.50. Conclusion: This solution supports safer dietary practices for individuals with food allergies, providing technological support in obtaining information about the presence of allergens in products.
References
ASBAI, "Alergia alimentar é o tema central da Semana Mundial," https://asbai.org.br/alergia-alimentar-e-o-tema-central-da-semana-mundial/, 2019.
ANVISA, "Perguntas e respostas sobre rotulagem de alergênicos," https://www.gov.br/anvisa/pt-br/centraisdeconteudo/publicacoes/alimentos/perguntas-e-respostas-arquivos/rotulagem-nutricional_2a-edicao.pdf/view, 2023.
M. Oliveira Andrade, D. Alves, W. Nascimento. "AVALIAÇÃO DA ROTULAGEM DE ALIMENTOS E DA CONFORMIDADE QUANTO A DECLARAÇÃO OBRIGATÓRIA DE ALERGÊNICOS," Alimentos: Ciência, Tecnologia e Meio Ambiente, vol. 3, no. 1, pp. 14–25, 2022.
Martins, L. "Rotulagem de alimentos alergênicos: análise das informaçoes". Hig. aliment 2023:e1113–e1113.
S. SOUZA, "Põe no rótulo. Cartilha de Alergia Alimentar," https://www.poenorotulo.com.br/, 2014.
Brasil, "RDC nº 26, de 02 de julho de 2015," , 2015.
Bilaver, L., et al. "P107 FOOD ALLERGY AND INFORMATICS: USING NATURAL LANGUAGE PROCESSING TO IDENTIFY CLINICAL PREDICTORS IN PROGRESS NOTES," in Annals of Allergy, Asthma & Immunology, vol. 127, no. 5, pp. S41–S42, 2021.
Popovski, G., et al. "FoodIE: A Rule-based Named-entity Recognition Method for Food Information Extraction.," in ICPRAM, vol. 12, pp. 915, 2019.
S. Campese, D. Pozza, "Food classification for inflammation recognition through ingredient label analysis: A real nlp case study," in Intelligent Systems and Applications: Proceedings of the 2020 Intelligent Systems Conference (IntelliSys) Volume 2, 2021, pp. 172–181.
A. Amato, G. Cozzolino, "SafeEat: extraction of information about the presence of food allergens in recipes," in Advances in Intelligent Networking and Collaborative Systems: The 12th International Conference on Intelligent Networking and Collaborative Systems (INCoS-2020) 12, 2021, pp. 194–203.
Bilaver, L., et al. "Natural language processing of pediatric progress notes for the identification of food allergy," in The Journal of Allergy and Clinical Immunology: In Practice, 2023.
Caimmi, D., et al. "Food allergy in primary care," in Acta Bio Medica: Atenei Parmensis, vol. 92, no. Suppl 7, 2021.
Banco Brasileiro de Rotulos de Alimentos, "Banco Brasileiro de Rotulos de Alimentos," https://five.epicollect.net/project/banco-brasileiro-de-rotulos-de-alimentos/, 2021.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
Submission of a paper to Journal of Health Informatics is understood to imply that it is not being considered for publication elsewhere and that the author(s) permission to publish his/her (their) article(s) in this Journal implies the exclusive authorization of the publishers to deal with all issues concerning the copyright therein. Upon the submission of an article, authors will be asked to sign a Copyright Notice. Acceptance of the agreement will ensure the widest possible dissemination of information. An e-mail will be sent to the corresponding author confirming receipt of the manuscript and acceptance of the agreement.
