AI-driven infrared spectroscopy in salivary oral leukoplakia
Clinical Oral Investigations · 05.11.2026 · 30 (11)
DOI: 10.1007/s00784-026-07246-3 ↗Kurz gefasst
Fachartikel in der Zeitschrift Clinical Oral Investigations, online erschienen am 05.11.2026. Verfasst von Sara Maria Santos Dias da Silva und 8 weiteren Autor:innen. Beteiligte Einrichtung: University of Taubaté - UNITAU - Taubaté, Rua dos Operários, 09, Centro, Taubaté, São Paulo, SP, 1202-340, Brazil. Hauptthemen laut MEDLINE: Leukoplakia, Oral, Saliva, Machine Learning, Artificial Intelligence. Die Arbeit nennt 22 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Universidade De Taubaté.
Abstract (Originalsprache)
Objectives
Oral potentially malignant disorders (OPMDs), particularly leukoplakia, are strongly linked to an increased risk of oral squamous cell carcinoma. Saliva has gained attention as a diagnostic biofluid due to its simple, non-invasive collection and complex biochemical composition. This study aimed to investigate the application of Fourier-transform infrared (FTIR) spectroscopy combined with machine learning to identify salivary biochemical changes. Materials and methods Saliva samples were collected from healthy control participants ( n = 22), participants with oral leukoplakia ( n = 22). Spectral data were acquired by ATR-FTIR, pre-processed with derivative analysis, normalization, and baseline correction, then analyzed using PCA and classified with Extra Trees, Random Forest, and XGBoost algorithms.
Results
The analysis revealed consistent biochemical differences within the 900–1800 cm⁻¹ region, mainly associated with proteins (Amide I and II), nucleic acids, and collagen. PCA revealed partial but relevant group separation, while machine learning models, especially Extra Trees and Random Forest, the MLP classifier achieved an AUC of 0.992 for initial dysplasia and 0.974 for severe dysplasia versus controls, indicating promising classification perfomance.
Conclusion
These findings support FTIR spectroscopy integrated with machine learning, as a powerful, non-invasive approach for salivary profiling in leukoplakia. This optical biopsy method shows promise as an auxiliary diagnostic tool for early detection and monitoring of OPMDs, enhancing preventive strategies in oral oncology.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- University of Taubaté - UNITAU - Taubaté, Rua dos Operários, 09, Centro, Taubaté, São Paulo, SP, 1202-340, Brazil.
- Department of Stomatology, School of Dentistry, University of São Paulo - USP - São Paulo, São Paulo, Brazil.
- Department of Stomatology, A.C. Camargo Cancer Center, São Paulo, Brazil.
- Federal University of São Paulo, UNIFESP - São José dos Campos, São José dos Campos, São Paulo, Brazil.
- University of Taubaté - UNITAU - Taubaté, Rua dos Operários, 09, Centro, Taubaté, São Paulo, SP, 1202-340, Brazil. luisfelipecarvalho@hotmail.com.
Förderung
- Universidade De Taubaté
Zitieren
APA
da Silva, S. M. S. D., Rizzato, J. M. B., Taromaru, A. C. Y., de Lima Medeiros, Y., Alves, F. A., Pereira, T. M., de Barros Gallo, C., Lima, F. S., & das Chagas E Silva de Carvalho, L. F. (2026). AI-driven infrared spectroscopy in salivary oral leukoplakia. Clinical Oral Investigations, 30(11). https://doi.org/10.1007/s00784-026-07246-3
Vancouver
da Silva SMSD, Rizzato JMB, Taromaru ACY, de Lima Medeiros Y, Alves FA, Pereira TM, et al. AI-driven infrared spectroscopy in salivary oral leukoplakia. Clinical Oral Investigations. 2026;30(11). doi:10.1007/s00784-026-07246-3
BibTeX
@article{daSilva2026,
author = {da Silva, Sara Maria Santos Dias and Rizzato, Jaqueline Maria Brandão and Taromaru, Ana Carolina Yumi and de Lima Medeiros, Yuri and Alves, Fábio Abreu and Pereira, Thiago Martini and de Barros Gallo, Camila and Lima, Fabianne Soares and das Chagas E Silva de Carvalho, Luis Felipe},
title = {AI-driven infrared spectroscopy in salivary oral leukoplakia},
journal = {Clinical Oral Investigations},
year = {2026},
volume = {30},
number = {11},
doi = {10.1007/s00784-026-07246-3}
}
EUVIMED