ATR-FTIR Spectroscopy of Saliva and Machine Learning as a Screening Test for Sjögren Disease
Analytical Chemistry · 02.12.2025 · 97 (47) · 26034-26044
DOI: 10.1021/acs.analchem.5c04238 ↗Kurz gefasst
Fachartikel in der Zeitschrift Analytical Chemistry, online erschienen am 18.11.2025. Verfasst von Jhonatan Contreras und 7 weiteren Autor:innen. Beteiligte Einrichtung: Photonic Data Science Department, Leibniz Institute of Photonic Technology (IPHT), Albert-Einstein-Straße 9, Jena 07745, Germany. Hauptthemen laut MEDLINE: Sjogren's Syndrome, Machine Learning, Saliva. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 43 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Bundesministerium f?r Bildung und Forschung.
Abstract (Originalsprache)
Sjögren's disease is often an underdiagnosed autoimmune condition that primarily affects the exocrine glands, resulting in symptoms such as dry eyes and dry mouth. Diagnostic challenges stem from nonspecific symptoms, the absence of definitive biomarkers, and the invasiveness and cost associated with current clinical tests. This study investigates the application of attenuated total reflectance Fourier-transform infrared spectroscopy (ATR-FTIR), in conjunction with a neural network and Monte Carlo dropout-based uncertainty estimation to distinguish patients with Sjögren's disease from healthy individuals. Uncertainty estimates were used to identify ambiguous spectra and refine training data, improving predictive performance and enabling confidence-aware interpretation. To minimize bias related to sex-based prevalence, model training was limited to female participants, among whom the disease is more common. To guarantee independent validation, a stratified cross-validation strategy was used. In each fold, the network is initialized with random weights, trained exclusively on the training subset, and evaluated on the corresponding unseen data. The refined (uncertainty-aware) model achieved 75% accuracy and 73% sensitivity at the individual spectrum level, and 79% accuracy and 76% sensitivity at the patient level. These findings highlight the potential of an uncertainty-aware, noninvasive, machine learning-based method as a reliable tool for the early diagnosis of Sjögren's Disease.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Photonic Data Science Department, Leibniz Institute of Photonic Technology (IPHT), Albert-Einstein-Straße 9, Jena 07745, Germany.
- Institute of Physical Chemistry & Abbe Center of Photonics (ACP), Friedrich Schiller University Jena, Helmholtzweg 4, Jena 07743, Germany.
- Department of Chemistry and Center for Biophotonic Technology and Artificial Intelligence (CeBAI), University at Albany, SUNY, Albany, New York 12222, United States.
- Department of Biological Sciences and the RNA Institute, University at Albany, SUNY, Albany, New York 12222, United States.
- Division of Otolaryngology Head and Neck Surgery, Albany Medical College, Albany, New York 12208, United States.
ORCID-Profile: Jhonatan Contreras, Oleg Ryabchykov, Jürgen Popp, Igor K Lednev
Förderung
- Bundesministerium f?r Bildung und Forschung
Zitieren
APA
Contreras, J., Vyas, B., Ryabchykov, O., Larsen, M., Gildener-Leapman, N., Bocklitz, T., Popp, J., & Lednev, I. K. (2025). ATR-FTIR Spectroscopy of Saliva and Machine Learning as a Screening Test for Sjögren Disease. Analytical Chemistry, 97(47), 26034-26044. https://doi.org/10.1021/acs.analchem.5c04238
Vancouver
Contreras J, Vyas B, Ryabchykov O, Larsen M, Gildener-Leapman N, Bocklitz T, et al. ATR-FTIR Spectroscopy of Saliva and Machine Learning as a Screening Test for Sjögren Disease. Analytical Chemistry. 2025;97(47):26034-26044. doi:10.1021/acs.analchem.5c04238
BibTeX
@article{Contreras2025,
author = {Contreras, Jhonatan and Vyas, Bhavik and Ryabchykov, Oleg and Larsen, Melinda and Gildener-Leapman, Neil and Bocklitz, Thomas and Popp, Jürgen and Lednev, Igor K},
title = {ATR-FTIR Spectroscopy of Saliva and Machine Learning as a Screening Test for Sjögren Disease},
journal = {Analytical Chemistry},
year = {2025},
volume = {97},
number = {47},
pages = {26034--26044},
doi = {10.1021/acs.analchem.5c04238}
}
EUVIMED