Machine learning pipeline with custom grid search for colorectal Raman spectroscopy data
Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy · 2026
DOI: 10.1016/j.saa.2025.126749 ↗Kurz gefasst
Fachartikel in der Zeitschrift Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2026. Verfasst von Daniela Janstová und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Mathematics, Informatics and Cybernetics, Faculty of Chemical Engineering, University of Chemistry and Technolog, Praguey, Technická 5,…. Hauptthemen laut MEDLINE: Spectrum Analysis, Raman, Machine Learning, Colorectal Neoplasms. Die Arbeit nennt 46 Literaturangaben. Gefördert von: Ministerstvo Zdravotnictví Ceské Republiky.
Abstract (Originalsprache)
Colorectal cancer remains a major health burden, and its early detection is crucial for effective treatment. This study investigates the use of a handheld Raman spectrometer in combination with machine learning to classify colorectal tissue samples collected during colonoscopy. A dataset of 330 spectra from 155 participants was preprocessed using a standardized pipeline, and multiple classification models were trained to distinguish between healthy and pathological tissue. Due to the strong class imbalance and limited data size, a custom grid search approach was implemented to optimize both model hyperparameters and preprocessing parameters. Unlike standard GridSearchCV, our method prioritized balanced accuracy on the test set to reduce bias toward the dominant class. Among the tested classifiers, the Decision Tree (DT) and Support Vector Classifier (SVC) achieved the highest balanced accuracy (71.77% for DT and 70.77% for SVC), outperforming models trained using traditional methods. These results demonstrate the potential of Raman spectroscopy as a rapid, non-destructive screening tool and highlight the importance of tailored model selection strategies in biomedical applications. While this study is based on a limited dataset, it serves as a promising step toward more robust classification models and supports the feasibility of this approach for future clinical validation.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Mathematics, Informatics and Cybernetics, Faculty of Chemical Engineering, University of Chemistry and Technolog, Praguey, Technická 5, Prague, 166 28, Czechia. Electronic address: janstovd@vscht.cz.
- Department of Mathematics, Informatics and Cybernetics, Faculty of Chemical Engineering, University of Chemistry and Technolog, Praguey, Technická 5, Prague, 166 28, Czechia. Electronic address: tomesj@vscht.cz.
- Department of Analytical Chemistry, Faculty of Chemical Engineering, University of Chemistry and Technology, Prague, Technická 5, Prague, 166 28, Czechia. Electronic address: valisj@vscht.cz.
- Department of Analytical Chemistry, Faculty of Chemical Engineering, University of Chemistry and Technology, Prague, Technická 5, Prague, 166 28, Czechia. Electronic address: sinical@vscht.cz.
- Department of Analytical Chemistry, Faculty of Chemical Engineering, University of Chemistry and Technology, Prague, Technická 5, Prague, 166 28, Czechia. Electronic address: kowyzu@gmail.com.
- The 4th Internal Clinic - Gastroenterology and Hepatology, General University Hospital in Prague, U Nemocnice 2, Prague, 128 00, Czechia. Electronic address: jaromir.petrtyl@lf1.cuni.cz.
Förderung
- Ministerstvo Zdravotnictví Ceské Republiky
Zitieren
APA
Janstová, D., Tomeš, J., Vališ, J., Synytsya, A., Kováčová, Z., Petrtýl, J., Setnička, V., & Mareš, J. (2026). Machine learning pipeline with custom grid search for colorectal Raman spectroscopy data. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy. https://doi.org/10.1016/j.saa.2025.126749
Vancouver
Janstová D, Tomeš J, Vališ J, Synytsya A, Kováčová Z, Petrtýl J, et al. Machine learning pipeline with custom grid search for colorectal Raman spectroscopy data. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy. 2026. doi:10.1016/j.saa.2025.126749
BibTeX
@article{Janstov2026,
author = {Janstová, Daniela and Tomeš, Jakub and Vališ, Jan and Synytsya, Alla and Kováčová, Zuzana and Petrtýl, Jaromír and Setnička, Vladimír and Mareš, Jan},
title = {Machine learning pipeline with custom grid search for colorectal Raman spectroscopy data},
journal = {Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy},
year = {2026},
doi = {10.1016/j.saa.2025.126749}
}
EUVIMED