EUVIMEDEUVIMED entdecken
Crossref

FTIR-based profiling of sinusitis: Stabilized feature selection through Boruta and Monte Carlo methods

Przemysław Raczkiewicz, Adrian Odrzywolski, Maryna Khalavka, Andrzej Stepulak, Adrian Andrzejczak, Janusz Klatka, Joanna Depciuch

Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy · 2026

DOI: 10.1016/j.saa.2025.126779 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2026. Verfasst von Przemysław Raczkiewicz und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biochemistry and Molecular Biology, Medical University of Lublin, 20-093 Lublin, Poland. Hauptthemen laut MEDLINE: Sinusitis. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 30 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Sinusitis is a prevalent inflammatory condition lacking rapid, non-invasive diagnostic tools. In this study, Fourier-transform infrared (FTIR) spectroscopy was applied to distinguish serum samples collected from sinusitis patients and healthy controls. FTIR spectra were preprocessed and analyzed using a robust, two-stage feature selection framework combining the Boruta algorithm and Monte Carlo Feature Selection within a nested cross-validation design. Both methods consistently highlighted a narrow spectral band between 3400 and 3550 cm-1 as a key region for discrimination. However, derivative spectra outside this band (e.g. 1940-2360 cm-1) were also repeatedly selected, indicating dispersed biochemical signal. Eighteen consensus features (first-derivative, full-range) enabled an SVM to reach 94 % accuracy (sens 1.00, spec 0.83, κ 0.87) on the 17-patient held-out set. Although overlap among individual 5 cm-1 bins is only moderate (mean Jaccard ≈ 0.26), a bin from the 3400-3550 cm-1 band emerges in virtually every cross-validation split, implying that this high-wavenumber region robustly carries disease-related biochemical signal. Feature selection frequency heatmaps emphasized this region's importance across cross-validation folds. Furthermore, dimensionality reduction techniques (PCA, UMAP, and t-SNE) revealed distinct clustering between patient and control groups, and permutation testing confirmed the statistical significance of the classification. These findings demonstrate that serum-based FTIR spectroscopy, combined with rigorous feature selection, holds promise as a non-invasive diagnostic aid for sinusitis, while highlighting the need for broader comparative studies in future research.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

SinusitisSpectroscopy, Fourier Transform InfraredHumansMonte Carlo MethodAlgorithmsMaleAdultFemaleCase-Control StudiesSupport Vector MachineMiddle Aged

Stichwörter der Autor:innen

Boruta algorithmFTIR spectroscopyMonte Carlo feature selectionSinusitis

Autor:innen und Institutionen

  • Department of Biochemistry and Molecular Biology, Medical University of Lublin, 20-093 Lublin, Poland.
  • Independent Unit of Spectroscopy and Chemical Imaging, Faculty Medical Science, Medical University of Lublin, Chodźki 4a, 20-093 Lublin, Poland.
  • Department of Otolaryngology and Laryngological Oncology, Medical University of in Lublin, Jaczewskiego 8, 20-954 Lublin, Poland.
  • Department of Biochemistry and Molecular Biology, Medical University of Lublin, 20-093 Lublin, Poland; Institute of Nuclear Physics, Polish Academy of Sciences, 31-342 Krakow, Poland. Electronic address: joanna.depciuch…

Zitieren

APA

Raczkiewicz, P., Odrzywolski, A., Khalavka, M., Stepulak, A., Andrzejczak, A., Klatka, J., & Depciuch, J. (2026). FTIR-based profiling of sinusitis: Stabilized feature selection through Boruta and Monte Carlo methods. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy. https://doi.org/10.1016/j.saa.2025.126779

Vancouver

Raczkiewicz P, Odrzywolski A, Khalavka M, Stepulak A, Andrzejczak A, Klatka J, et al. FTIR-based profiling of sinusitis: Stabilized feature selection through Boruta and Monte Carlo methods. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy. 2026. doi:10.1016/j.saa.2025.126779

BibTeX
@article{Raczkiewicz2026,
  author = {Raczkiewicz, Przemysław and Odrzywolski, Adrian and Khalavka, Maryna and Stepulak, Andrzej and Andrzejczak, Adrian and Klatka, Janusz and Depciuch, Joanna},
  title = {FTIR-based profiling of sinusitis: Stabilized feature selection through Boruta and Monte Carlo methods},
  journal = {Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy},
  year = {2026},
  doi = {10.1016/j.saa.2025.126779}
}
Kostenlos starten →