Desenvolvimento de plataforma biofotônica sustentável, portátil, rápida e não invasiva associada à inteligência artificial para detecção salivar de helicobacter pylori

• Ano de defesa: 2023
• Autor(a) principal: Silva, Ghabriel Honório da
• Tipo de documento: Dissertação
• Tipo de acesso: Acesso embargado
• Idioma: por
• Instituição de defesa: Universidade Federal de Uberlândia; Brasil; Programa de Pós-graduação em Imunologia e Parasitologia Aplicadas
• Palavras-chave em Português: ATR-FTIR; Helicobacter pylori; Infecção gastrointestinal; Teste de triagem; Diagnóstico salivar; Saliva; Testes não-invasivos; Algoritmos de aprendizado de máquina; CNPQ::CIENCIAS BIOLOGICAS; Imunologia; Sistema gastrointestinal - Doenças; Glândulas salivares - Doenças; Algorítmos computacionais; ODS::ODS 3. Saúde e bem-estar - Assegurar uma vida saudável e promover o bem-estar para todos, em todas as idades.
• Link de acesso: https://repositorio.ufu.br/handle/123456789/41367; http://doi.org/10.14393/ufu.di.2023.368

Helicobacter pylori (H. pylori) infection can increase the risk of peptic ulcers and gastrointestinal neoplasms. H. pylori detection in gastric epithelial tissue collected by esophagogastroduodenoscopy (EGD) is an invasive, expensive, and a complex execution procedure, reducing access for isolated populations. H. pylori detection by Urea Breath Test (UBT) presents high-cost with limited access in low- and middle-income countries. In this context, it is critical to develop novel alternative non-invasive platforms for the portable, fast, and reagent-free detection of H. pylori. Here, we used attenuated total reflectance Fourier-transform infrared spectroscopy (ATR-FTIR) supported by Machine Learning algorithms to identify infrared vibrational modes of H. pylori diluted in human saliva. To perform it, saliva was diluted in 4 different H. pylori concentrations (108 CFU/mL, 107 CFU/mL, 106 CFU/mL, and 105 CFU/mL). Then, diluted saliva was applied to ATR-FTIR spectroscopy to perform a reagent-free, fast, and sustainable analysis of spectral signatures to identify unique vibrational modes. The obtained spectra were applied to Linear Discriminant Analysis (LDA) and Support Vector Machine (SVM) algorithms to perform the H. pylori detection. The best discrimination performances obtained from the concentrations ranged from 85% to 94% of accuracy, reaching 89% for 108 CFU/mL, 93% for 107 CFU/mL, 94% for 106 CFU/mL, and 85% for 105 CFU/mL. The data demonstrate that this proof-of-concept study has significant potential for the non-invasive detection of H. pylori using a biophotonic platform supported by artificial intelligence without the use of reagents with human saliva samples obtained by self-collection.