Attenuated Total Reflection-Fourier Transform Infrared (Atr-Ftir) Spectroscopy Analysis of Saliva As a Diagnostic Specimen for Rapid Classification of Oral Squamous Cell Carcinoma Using Chemometrics Methods Publisher Pubmed



Mm Khanmohammadi Khorrami Mohammad MAHDI ; N Azimi NOZHAN ; M Koopaie MARYAM ; M Mohammadi MAHSA ; S Manifar SOHEILA ; M Khanmohammadi Khorrami MOHAMMADREZA
Source: Cancer Investigation Published:2024

Abstract

Background & Aim: Recent advancements in analytical techniques have highlighted the potential of Attenuated Total Reflection-Fourier Transform Infrared (ATR-FTIR) spectroscopy as a quick, cost-effective, non-invasive, and efficient tool for cancer diagnosis. This study aims to evaluate the effectiveness of ATR-FTIR spectroscopy in combination with supervised machine learning classification models for diagnosing OSCC using saliva samples. Methods & Materials: Eighty unstimulated whole saliva samples from OSCC patients and healthy controls were collected. The ATR-FTIR spectroscopy was performed and spectral data were used to classify healthy and OSCC groups. The data were analyzed using machine learning classification methods such as Partial Least Squares-Discriminant Analysis (PLS-DA) and Support Vector Machine Classification (SVM-C). The classification performance of the models was evaluated by computing sensitivity, specificity, precision, and accuracy. Results: The samples were classified into two classes based on their spectral data. The obtained results demonstrate a high level of accuracy in the prediction sets of the PLS-DA and SVM-C models, with accuracy values of 0.960 and 0.962, respectively. The OSCC group sensitivity values for both PLS-DA and SVM-C models was 1.00, respectively. Conclusion: The study indicates that ATR-FTIR spectroscopy, combined with chemometrics, is a potential method for the non-invasive diagnosis of OSCC using saliva samples. This method achieved high accuracy and the findings of this study suggest that ATR-FTIR spectroscopy could be further developed for clinical applications in OSCC diagnosis. © 2024 Elsevier B.V., All rights reserved.