Infraestrutura Computacional para Apoio à Avaliação Fecal com Inteligência Artificial
Resumo
Este artigo apresenta uma infraestrutura computacional para apoio à avaliação fecal com Inteligência Artificial (IA). O trabalho parte de uma revisão sistemática da literatura (RSL), conduzida em seis bases científicas, que identificou 62 registros e incluiu 15 estudos após triagem. Os achados indicaram predominância de redes neurais convolucionais em tarefas com imagens, uso recorrente da Escala de Bristol ou de variações pediátricas, baixa disponibilidade de bases públicas e limitações de replicabilidade. A partir dessas lacunas, foi especificado um protótipo modular em três camadas, contemplando gestão web, treinamento de modelos e serviço de IA. Experimentos preliminares com bases substitutas indicaram viabilidade técnica do pipeline, com acurácia de 0,8652 no ensaio com imagens de fezes humanas. Os resultados não representam validação clínica, mas evidenciam uma base computacional inicial para estudos futuros com rastreabilidade, versionamento e auditoria.Referências
Blake, M. R., Raker, J. M., and Whelan, K. (2016). Use of the Bristol Stool Form Scale in clinical and research settings: A systematic review. The American Journal of Gastroenterology, 111(1):75–83.
Chang, J. et al. (2021). Towards an ambient estimation of stool types to support nutrition counseling for people affected by the geriatric frailty syndrome. Journal of Ambient Intelligence and Humanized Computing, 12:11315–11330.
Choy, C. A. et al. (2021a). Machine learning supports automated digital image scoring of stool consistency in diapers. Journal of Pediatric Gastroenterology and Nutrition, 73(2):147–153.
Choy, Y. P., Hu, G., and Chen, J. (2021b). Detection and classification of human stool using deep convolutional neural networks. IEEE Access, 9:160485–160496.
Dawkins, J. B. et al. (2022). Gut metabolites predict Clostridioides difficile recurrence. Microbiome, 10(1):1–14.
Fujimoto, T. et al. (2023). Effect of daily consumption of a fermented milk containing Lacticaseibacillus paracasei strain Shirota (LcS) on stool consistency in united states adults with hard or lumpy stools: A randomized controlled trial. The Journal of Nutrition, 153(6):1836–1845.
Huysentruyt, K. et al. (2023). Technician-scored stool consistency spans the full range of the Bristol Scale in a healthy US population and differs by diet and chronic stress load. The Journal of Nutrition, 153(4):1199–1207.
Jung, J. et al. (2024). Artificial intelligence- and physician-interpreted stool image characteristics correlate with C-Reactive Protein among inpatients with acute severe ulcerative colitis: A pilot study. Inflammatory Bowel Diseases, 30(3):397–406.
Kitchenham, B. and Charters, S. (2007). Guidelines for performing systematic literature reviews in software engineering. Technical Report EBSE-2007-01, EBSE Technical Report.
Lewis, S. J. and Heaton, K. W. (1997). Stool form scale as a useful guide to intestinal transit time. Scandinavian Journal of Gastroenterology, 32(9):920–924.
Nakazawa, H. et al. (2023). A mountable toilet system for personalized health monitoring via the analysis of excreta. Nature Biomedical Engineering, 7:541–553.
Van Den Berg, M. M. et al. (2024). The importance of objective stool classification in fecal 1H-NMR metabolomics: Exponential increase in stool crosslinking is mirrored in systemic inflammation and associated to fecal acetate and methionine. Metabolomics, 20(1).
Yang, X. et al. (2022). Stool image analysis for digital health monitoring by smart toilets. IEEE Transactions on Biomedical Engineering, 69(5):1655–1666.
Yu, X. et al. (2022). Human stools classification for gastrointestinal health based on an improved ResNet18 model with dual attention mechanism. Computers in Biology and Medicine, 145:105440.
Zhou, H. et al. (2023). Generation and application of a convolutional neural network algorithm in evaluating stool consistency in diapers. Acta Paediatrica, 112(3):682–689.
Zhou, Y. et al. (2024). Long-term, automated stool monitoring using a novel smart toilet: A feasibility study. Neurogastroenterology & Motility, 36(2):e14764.
Zhu, Q. et al. (2023). Integrative analysis of γδT cells and dietary factors reveals predictive values for autism spectrum disorder in children. Brain, Behavior, and Immunity, 111:148–159.
Zhu, Y. et al. (2024). The effectiveness of artificial intelligence in assisting mothers with assessing infant stool consistency in a breastfeeding cohort study in china. Nutrients, 16(2):200.
Chang, J. et al. (2021). Towards an ambient estimation of stool types to support nutrition counseling for people affected by the geriatric frailty syndrome. Journal of Ambient Intelligence and Humanized Computing, 12:11315–11330.
Choy, C. A. et al. (2021a). Machine learning supports automated digital image scoring of stool consistency in diapers. Journal of Pediatric Gastroenterology and Nutrition, 73(2):147–153.
Choy, Y. P., Hu, G., and Chen, J. (2021b). Detection and classification of human stool using deep convolutional neural networks. IEEE Access, 9:160485–160496.
Dawkins, J. B. et al. (2022). Gut metabolites predict Clostridioides difficile recurrence. Microbiome, 10(1):1–14.
Fujimoto, T. et al. (2023). Effect of daily consumption of a fermented milk containing Lacticaseibacillus paracasei strain Shirota (LcS) on stool consistency in united states adults with hard or lumpy stools: A randomized controlled trial. The Journal of Nutrition, 153(6):1836–1845.
Huysentruyt, K. et al. (2023). Technician-scored stool consistency spans the full range of the Bristol Scale in a healthy US population and differs by diet and chronic stress load. The Journal of Nutrition, 153(4):1199–1207.
Jung, J. et al. (2024). Artificial intelligence- and physician-interpreted stool image characteristics correlate with C-Reactive Protein among inpatients with acute severe ulcerative colitis: A pilot study. Inflammatory Bowel Diseases, 30(3):397–406.
Kitchenham, B. and Charters, S. (2007). Guidelines for performing systematic literature reviews in software engineering. Technical Report EBSE-2007-01, EBSE Technical Report.
Lewis, S. J. and Heaton, K. W. (1997). Stool form scale as a useful guide to intestinal transit time. Scandinavian Journal of Gastroenterology, 32(9):920–924.
Nakazawa, H. et al. (2023). A mountable toilet system for personalized health monitoring via the analysis of excreta. Nature Biomedical Engineering, 7:541–553.
Van Den Berg, M. M. et al. (2024). The importance of objective stool classification in fecal 1H-NMR metabolomics: Exponential increase in stool crosslinking is mirrored in systemic inflammation and associated to fecal acetate and methionine. Metabolomics, 20(1).
Yang, X. et al. (2022). Stool image analysis for digital health monitoring by smart toilets. IEEE Transactions on Biomedical Engineering, 69(5):1655–1666.
Yu, X. et al. (2022). Human stools classification for gastrointestinal health based on an improved ResNet18 model with dual attention mechanism. Computers in Biology and Medicine, 145:105440.
Zhou, H. et al. (2023). Generation and application of a convolutional neural network algorithm in evaluating stool consistency in diapers. Acta Paediatrica, 112(3):682–689.
Zhou, Y. et al. (2024). Long-term, automated stool monitoring using a novel smart toilet: A feasibility study. Neurogastroenterology & Motility, 36(2):e14764.
Zhu, Q. et al. (2023). Integrative analysis of γδT cells and dietary factors reveals predictive values for autism spectrum disorder in children. Brain, Behavior, and Immunity, 111:148–159.
Zhu, Y. et al. (2024). The effectiveness of artificial intelligence in assisting mothers with assessing infant stool consistency in a breastfeeding cohort study in china. Nutrients, 16(2):200.
Publicado
15/06/2026
Como Citar
TAUIL, Lucas Chasseraux; BREGA, José Remo Ferreira.
Infraestrutura Computacional para Apoio à Avaliação Fecal com Inteligência Artificial. In: ESCOLA REGIONAL DE INFORMÁTICA DO TRIÂNGULO MINEIRO (ERI-TM), 1. , 2026, Uberlândia/MG.
Anais [...].
Porto Alegre: Sociedade Brasileira de Computação,
2026
.
p. 1-5.
DOI: https://doi.org/10.5753/eritm.2026.25248.
