Aim or purpose: Currently, clinical diagnosis of oral cancer, which represents 2% of all cancer cases worldwide, primarily relies on biopsy and histopathological analysis; however, these methods have inherent limitations. The current study aims to explore novel diagnostic approaches for oral cancer by employing attenuated total reflection-Fourier transform infrared (ATR-FTIR) spectroscopy in conjunction with chemometrics. Materials and methods: With prior approval from the institutional bioethics committee, in this cross-sectional study, informed consents were signed and unstimulated saliva samples were collected from 41 individuals: healthy volunteers, patients with Potentially Malignant Oral Disorders (OPMDs), and patients with Oral Squamous Cell Carcinoma (OSCC). Saliva was clarified and analyzed by Fourier Transform Infrared (ATR-FTIR) spectroscopy All samples were run in triplicate. The spectral data were analyzed using machine learning classification methods and their classification performance were evaluated. Results: The standardized protocol for analyzing saliva samples using ATR-FTIR spectroscopy yielded high-quality, repeatable spectra. In the original spectra, the spectroscopic profile of proteins and lipids in the saliva of patients with OPMDs and OSCC was found to be distinct from that of healthy individuals. Chemometric analysis supported by machine learning techniques allowed the classification of the samples into three groups based on their processed spectral data and showed that the Partial Least Squares - Support Vector Machines (PLS-SVM) model had the best accuracy, specificity, and accuracy among the models evaluated. Conclusions: The findings suggest that combining ATR-FTIR spectroscopy with chemometrics is a promising method for clinical screening and non-invasive diagnosis of OPMDs and OSCC using saliva.
Discussion(0)
No comments yet. Be the first to comment.