Desenvolvimento e validação de um assistente virtual para farmacovigilância de vacinas

• Andréia Roque de Souza Cavalcanti Faculdade de Medicina do ABC / Imune Research Lab
• João Antônio Correa Faculdade de Medicina do ABC
• José William Araújo do Nascimento Imune Research Lab / UFPE
• Rafael Roque de Souza Imune Research Lab / UFPE
• Geicianfran da Silva Lima Roque Imune Research Lab / UFPE
• Sérgio Ricardo de Melo Queiroz UFPE

DOI: https://doi.org/10.5753/sbcas.2021.16087

Abstract

This study was carried out to develop and validate a virtual assistant for the purpose of performing pharmacovigilance of vaccines. This is a quantitative methodological research conducted in three phases: 1) survey of the scientific literature; 2) content validation through a panel of 22 health professionals; 3) implementation of an automated messaging virtual assistant. As obtained results, the content domains of the virtual assistant achieved excellent adequacy, relevance, and representativeness criteria, all above 86%; the content validity index obtained an average of 0.90 and an average Kappa value of 0.76.

References

Ayanouz, S., Abdelhakim, B.A. and Benhmed, M. (2020) A Smart Chatbot Architecture based NLP and Machine Learning for Health Care Assistance. Proceedings of the 3rd International Conference on Networking, Information Systems & Security; 78, p. 1-6. Disponível em: https://doi.org/10.1145/3386723.3387897

Brasil. Ministério da Saúde. (2020) Manual de vigilância epidemiológica de eventos adversos pós-vacinação. Ministério da Saúde, Secretaria de Vigilância em Saúde, Departamento de Imunizações e Doenças Transmissíveis. 4. ed. Brasília: Ministério da Saúde. Disponível em: http://bvsms.saude.gov.br/bvs/publicacoes/manual_vigilancia_epidemiologica_eventos_vacinacao_4ed.pdf

European Medicines Agency (2020) Guideline on good pharmacovigilance practices (GVP). Disponível em: https://www.ema.europa.eu/en/documents/regulatory-procedural-guideline/guidelines-good-pharmacovigilance-practices-gvp-introductory-cover-note-last-updated-revision-3_en.pdf

IBM (2019) “IBM Watson”, Disponível em: https://www.ibm.com/Watson/APIs

Milne-Ives, M., Cock, C., Lim, E., Shehadeh, M.H., Pennington, N., Mole, G., et al. (2020) The Effectiveness of Artificial Intelligence Conversational Agents in Health Care: Systematic Review. J Med Internet Res; 22 (10), p. e20346, Disponível em: http://dx.doi.org/10.2196/20346

Nichols, T.R., Wisner, P.M., Cripe, G., et al. (2010) Putting the Kappa Statistic to Use, Qual Assur J 13, p. 57–61. Disponível em: https://doi.org/10.1002/qaj.48

O'Neill., T.A. (2017) An Overview of Interrater Agreement on Likert Scales for Researchers and Practitioners. Frontiers In Psychology, 8(1), p. 1-15. Disponível em: http://dx.doi.org/10.3389/fpsyg.2017.00777

Oosterhuis, I., Taavola, H., Tregunno, P.M., Mas, P., Gama, S., Newbould, V., et al. (2018) Characteristics, Quality and Contribution to Signal Detection of Spontaneous Reports of Adverse Drug Reactions Via the WEB-RADR Mobile Application: A Descriptive Cross-Sectional Study. Drug Saf. 41 (10), p. 969–978, Disponível em: http://dx.doi.org/10.1007/s40264-018-0679-6

Polit, D.F., and Beck, C.T. (2006) The content validity index: Are you sure you know what’s being reported? critique and recommendations, Res Nurs Health; 29(5), p. 489–97. Disponível em: https://doi.org/10.1002/nur.20147

Soldatou, V., Soldatos, A. and Soldatos, T. (2019) Examining Socioeconomic and Computational Aspects ofVaccine Pharmacovigilance. BioMed Research International; 1-15. Disponível em: http://dx.doi.org/10.1155/2019/6576483

Xie, J. and Ele, Y. (2017) Ontology-Based Vaccine Adverse Event Representation and Analysis. Adv Exp Med Biol; 1028, p. 89-103. Disponível em: http://dx.doi.org/0.1007/978-981-10-6041-0_6