Skip to content
#protein folding Open access

Machine learning-assisted chemometric analysis of salivary ATR-FTIR spectra for the diagnosis of oral submucous fibrosis

Oct 2026 · Frontiers in Oncology · Vol 16 · 0 citations · 21 references
Medicine

TL;DR

Salivary ATR-FTIR combined with machine learning demonstrated promising classification performance and preliminary performance in an independent cohort, but larger, diverse, multicenter studies with rigorous validation are needed before clinical implementation.

Abstract

Background Oral submucous fibrosis (OSMF) is a chronic, potentially malignant disorder strongly linked to areca nut chewing. Clinical diagnosis is challenging, and histopathology, though the gold standard, is invasive and subject to inter-observer variability. Saliva analysis using Fourier Transform Infrared (FTIR) spectroscopy offers a promising non-invasive alternative. This study evaluated salivary ATR-FTIR spectral analysis integrated with machine learning for classification of OSMF, individuals with adverse oral habits, and healthy controls. Methodology Unstimulated saliva samples were collected from 450 participants comprising 150 patients with clinically diagnosed OSMF, 150 individuals with adverse oral habits without clinical evidence of OSMF, and 150 healthy controls. After centrifugation, the saliva supernatant was analyzed by ATR-FTIR spectroscopy over 400–4000 cm−¹. Spectra underwent baseline correction and normalization followed by Savitzky–Golay smoothing. For machine-learning analysis, Standard Scaler and PCA were incorporated within the classification pipeline. Decision Tree, Random Forest, support vector machine (SVM), and XGBoost classifiers were evaluated using stratified 10-fold cross-validation. Hyperparameter optimization and performance estimation used the same cross-validation framework. An independent cohort of 90 participants was used for validation. Results XGBoost showed the highest cross-validation performance, with accuracies of 90.62% for Normal versus Habit, 97.67% for Normal versus OSMF, and 91.30% for three-class classification. Statistical analysis identified 157 nominally significant wavenumbers (p<0.05) within a continuous region from 1581 to 2142 cm−¹ corresponding to protein and collagen bands. Principal component analysis showed that PC1 and PC2 explained 89.26% and 6.95% of the total variance, respectively (96.21% cumulatively). In the independent validation cohort, accuracy was 80.0% for OSMF versus Normal and 71.7% for Habit versus Normal. Conclusion Salivary ATR-FTIR combined with machine learning demonstrated promising classification performance and preliminary performance in an independent cohort. The identified spectral region is biologically plausible in the context of altered salivary biochemical composition associated with inflammation and fibrosis, but it should not be regarded as a validated disease-specific biomarker. Salivary ATR-FTIR is best considered a complementary, non-invasive screening and risk-stratification approach rather than a replacement for clinical/oral examination or histopathological assessment when biopsy is indicated. Larger, diverse, multicenter studies with rigorous validation are needed before clinical implementation.

Read PDF

Similar papers

Open access Oct 2026

Determination of specific salivary biochemical profiles in oral and ovarian cancer using machine learning and SHAP analysis

Introduction: Saliva contains local and systemic molecular signals that may support non-invasive cancer detection, but the diagnostic value of integrated salivary profiles across anatomically distinct malignancies remains unclear. Objective: This study evaluates whether multivariable salivary signatures could distingui...

E. I. Dyachenko, L. Bel'skaya · 0 citations
Open access Sep 2026

Infrared spectroscopy with statistical analysis and machine learning for cancer risk assessment in inflammatory bowel disease patients

Patients with inflammatory bowel disease (IBD) undergo regular colonoscopic surveillance due to their elevated risk of developing colorectal cancer (CRC). However, current clinical, endoscopic and histopathological risk stratification methods can be limited in sensitivity and objectivity, highlighting the need for comp...

E. Kumi-Barimah, Raneem Toman, A. Jha et al. · 0 citations
Open access Oct 2026

ATR-FTIR Spectroscopy Combined with Machine Learning Enables Detection of Schistosomiasis-Associated Biochemical Signatures in Human Serum

Overall, ATR-FTIR spectroscopy combined with machine learning shows potential as a rapid, reagent-free, and minimally sample-intensive complementary approach for schistosomiasis screening, warranting validation in larger, geographically diverse cohorts.

Victor Freire Ferreira de Aguilar, T. M. Cirilo, D. C. Caixeta et al. · 0 citations
Review Open access Oct 2026

SALIVA AS A SOURCE OF TUMOR-ASSOCIATED SIGNALS: A REVIEW OF FOURIER-TRANSFORM INFRARED SPECTROSCOPY (FTIR) AND RAMAN STUDIES

Relevance: Saliva is a promising non-invasive biological matrix for detecting tumor-associated changes. However, most reported salivary biomarkers and spectroscopic signatures have been obtained from patients with clinically established disease rather than from truly preclinical settings.The study aimed to summarize th...

D. Shestakov, U. Sagyngali, A. Zhumina et al. · 0 citations

Related blog posts

Google DeepMind Blog Sep 30, 2026

Introducing SynthID Bio

Proof of concept for watermarking AI-generated proteins while preserving biological function.

MIT News · Artificial Intelligence Aug 27, 2026

Looking beyond natural sequences

A new machine-learning framework aims to improve the success rate of computational protein design while moving away from results that reproduce sequences found in nature.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.