APPLICATIONS OF ARTIFICIAL INTELLIGENCE IN THE DIFFERENTIAL DIAGNOSIS OF DENGUE AND COVID-19 IN ADULT PATIENTS: A SYSTEMATIC REVIEW
DOI:
https://doi.org/10.56238/arev7n10-158Keywords:
Artificial Intelligence, Clinical Diagnosis, Dengue, COVID-19, Infectious DiseasesAbstract
Artificial intelligence (AI) has established itself as an innovative tool in healthcare, particularly in improving clinical diagnosis by identifying patterns in laboratory tests and clinical signs. This study, developed from a systematic review, aimed to analyze the effectiveness of AI in increasing diagnostic accuracy in adult patients presenting with symptoms like those of dengue and COVID-19, compared to traditional medical diagnostic methods. Initially, 3,435 publications related to the use of AI in clinical settings with overlapping infectious symptoms were identified. After applying rigorous eligibility and exclusion criteria, a set of relevant studies was selected for analysis. The identified AI applications were classified into the categories of automated triage, clinical decision support, and predictive models based on laboratory data and clinical signs. The results indicated that AI offers comprehensive diagnostic support, also contributing to hospital management and resource optimization in overburdened healthcare settings. It is concluded that artificial intelligence has great potential to make the diagnosis of infectious diseases more agile, accurate, and efficient, especially in scenarios with similar clinical symptoms, such as those observed in dengue and COVID-19.
Downloads
References
GARCIA, P. H.; LIMA, C. F. Modelos computacionais para o diagnóstico de COVID-19 e dengue com base em dados clínicos. Cadernos de Saúde Digital, v. 6, n. 2, p. 77–89, 2023.
KUMAR, A. et al. Machine learning approaches for differential diagnosis of COVID-19 and dengue in adults using clinical data. Journal of Biomedical Informatics, v. 120, p. 103848, 2021. DOI: 10.1016/j.jbi.2021.103848. DOI: https://doi.org/10.1016/j.jbi.2021.103848
MARTINS, E. C.; SANTOS, D. F. Inteligência artificial no apoio ao diagnóstico clínico em ambientes de atenção primária. Revista de Medicina Digital, v. 4, n. 1, p. 45–60, 2021.
PAIXÃO, G. M. M. de; SANTOS, B. C.; ARAUJO, R. M. de; RIBEIRO, M. H.; MORAES, J. L. de; RIBEIRO, A. L. Machine Learning na Medicina: Revisão e Aplicabilidade. Arquivos Brasileiros de Cardiologia, v. 118, n. 1, p. 95–102, jan. 2022. DOI: https://doi.org/10.36660/abc.20200596
RAMOS, V. H. et al. Avaliação comparativa de algoritmos de aprendizado de máquina para diagnóstico diferencial em adultos. Saúde Inteligente, v. 9, n. 1, p. 123–137, 2023.
RAMOS, V. H. et al. Ferramentas baseadas em IA para avaliação clínica: uma revisão sistemática. International Journal of Medical Informatics, v. 165, p. 104865, 2021.
SILVA, J. F.; PEREIRA, M. R. Inteligência artificial no diagnóstico clínico: uma revisão sobre modelos aplicados à COVID-19 e arboviroses. Revista Brasileira de Saúde Digital, v. 4, n. 2, p. 112–125, 2022.
SOUZA, M. T. et al. Análise de padrões clínicos com IA no contexto da COVID-19 e arboviroses. Revista Brasileira de Computação Aplicada à Saúde, v. 3, n. 2, p. 70–85, 2023.
ZHANG, Y. et al. AI-driven decision support systems for differential diagnosis of viral infections in adults. Artificial Intelligence in Medicine, v. 132, p. 102003, 2022. DOI: 10.1016/j.artmed.2022.102003.
RAMOS, V. H. et al. Avaliação comparativa de algoritmos de aprendizado de máquina para diagnóstico diferencial em adultos. Saúde Inteligente, v. 9, n. 1, p. 123–137, 2023.
SILVA, J. F.; PEREIRA, M. R. Inteligência artificial no diagnóstico clínico: uma revisão sobre modelos aplicados à COVID-19 e arboviroses. Revista Brasileira de Saúde Digital, v. 4, n. 2, p. 112–125, 2022.
SOUZA, M. T. et al. Análise de padrões clínicos com IA no contexto da COVID-19 e arboviroses. Revista Brasileira de Computação Aplicada à Saúde, v. 3, n. 2, p. 70–85, 2023.
MARTINS, E. C.; SANTOS, D. F. Inteligência artificial no apoio ao diagnóstico clínico em ambientes de atenção primária. Revista de Medicina Digital, v. 4, n. 1, p. 45–60, 2021.
GARCIA, P. H.; LIMA, C. F. Modelos computacionais para o diagnóstico de COVID-19 e dengue com base em dados clínicos. Cadernos de Saúde Digital, v. 6, n. 2, p. 77–89, 2023.
ZHANG, Y. et al. AI-driven decision support systems for differential diagnosis of viral infections in adults. Artificial Intelligence in Medicine, v. 132, p. 102003, 2022. DOI: 10.1016/j.artmed.2022.102003.
