Development of a novel sustainable, portable, fast, and non-invasive platform based on ATR-FTIR technology coupled with machine learning algorithms for Helicobacter pylori detection in human saliva

•Infrared salivary spectra supported by machine learning algorithms can be used for Helicobacter pylori detection.•Detection of H pylori in saliva by ATR-FTIR shows high accuracy values at concentrations higher than 105 CFU/mL.•The vibrational modes related to the amide II region are critical to H pylori in saliva.•This sustainable approach permits fast detection without reagents with some advantages compared to currently used methods. Helicobacter pylori (H. pylori) infection can increase the risk of peptic ulcers and gastric neoplasms. H. pylori detection in gastric epithelial tissue collected by esophagogastroduodenoscopy (EGD) is an invasive, costly, and stands as an invasive and examiner-dependent procedure necessitating suitable sedation. complex execution procedure, reducing access for isolated populations. H. pylori detection by Urea Breath Test (UBT) presents high outlay 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, accessible through self-collection 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 concentrations (108 CFU/mL, 107 CFU/mL, 106 CFU/mL, and 105 CFU/mL) of H. pylori. Then, diluted saliva with or without H. pylori were applied to ATR-FTIR spectroscopy to perform a reagent-free, fast, and sustainable analysis of spectral signatures to identify unique vibrational modes to identify this pathogen. The obtained spectra were applied to Linear Discriminant Analysis (LDA) and Support Vector Machine (SVM) algorithms to perform the H. pylori detection. The results indicate that the method was highly accurate between 108 - 105 CFU/mL, achieving an accuracy of 89 % for 108 CFU/mL, 93 % for 107 CFU/mL, 94 % for 106 CFU/mL, and 85 % for 105 CFU/mL with SVM algorithm. This proof-of-concept study demonstrates the significant potential of a biophotonic platform supported by artificial intelligence for the non-invasive detection of H. pylori in human saliva samples obtained by self-collection, without the use of reagents. The data reveal that this proof-of-concept study has significant potential for the non-invasive detection of H. pylori using a biophotonic platform supported by arti