EUVIMEDEUVIMED entdecken
Crossref

Interpretable Random Forest (machine learning) analysis of two-trace 2D-COS FTIR spectra for multilayer biochemical characterization of colorectal precancerous

Sivakumaran Karthikeyan, Monica Maribel Mata-Miranda, Adriana Martinez-Cuazitl, Francisco Garibay-Gonzalez, Alejandro Deciga-Alcaraz, Gustavo Jesus Vazquez-Zapien

Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy · 2026-11 · 361 · 128078

DOI: 10.1016/j.saa.2026.128078 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2026-11. Verfasst von Sivakumaran Karthikeyan und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Physics, Dr. Ambedkar Government Arts College, Chennai, Tamil Nadu 600039, India. Electronic address: physicskarthik@gmail.com. Hauptthemen laut MEDLINE: Colorectal Neoplasms, Machine Learning, Precancerous Conditions, Random Forest. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 72 Literaturangaben.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This study investigates colorectal precancer-associated biochemical alterations across the mucosa, submucosa, and muscular layers by correlating two-trace two-dimensional Fourier transform infrared (2T2D-FTIR) spectra using random forests machine learning. The 2T2D-FTIR analyses markedly enhanced spectral resolution, enabling clear discrimination of overlapping vibrational bands that are indistinct in conventional one-dimensional FTIR spectra. Premalignant tissues exhibited pronounced reductions in lipid-associated CH2 and CH3 stretching vibrations, indicating disrupted lipid metabolism, increased lipid consumption, and membrane remodelling. Precancer-associated modifications in the amide I region indicate shifts in protein secondary structure. Substantial changes in the fingerprint-region bands reflect metabolic reprogramming, abnormal cell proliferation, and increased DNA abundance. Random Forest classification demonstrated exceptional performance, achieving perfect accuracy, precision, recall, and specificity across tissue layers. Submucosa samples showed complete separability driven by a single dominant spectral feature, while muscular-layer samples required minimal additional complexity due to slight biological heterogeneity. The generated decision trees demonstrated complete leaf purity, indicating the absence of classification ambiguity. These results underscore the strong biological consistency of premalignant spectral signatures. Overall, integrating 2T2D-FTIR spectroscopy with machine learning provides a powerful and reliable framework for probing molecular changes in colorectal cancer and supports its potential for highly accurate, non-invasive diagnostic applications.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Colorectal NeoplasmsMachine LearningPrecancerous ConditionsRandom ForestHumansSpectroscopy, Fourier Transform Infrared

Stichwörter der Autor:innen

2T2DArtificial intelligenceColorectal cancerDysplasiaFTIRMachine learningRandom forest

Autor:innen und Institutionen

  • Department of Physics, Dr. Ambedkar Government Arts College, Chennai, Tamil Nadu 600039, India. Electronic address: physicskarthik@gmail.com.
  • Escuela Militar de Medicina, Centro Militar de Ciencias de la Salud, Secretaría de la Defensa Nacional, 11200 Mexico City, Mexico; Hospital Central Militar, Secretaría de la Defensa Nacional, 11200 Mexico City, Mexico.
  • Escuela Militar de Medicina, Centro Militar de Ciencias de la Salud, Secretaría de la Defensa Nacional, 11200 Mexico City, Mexico; Hospital Central Militar, Secretaría de la Defensa Nacional, 11200 Mexico City, Mexico.…

Zitieren

APA

Karthikeyan, S., Mata-Miranda, M. M., Martinez-Cuazitl, A., Garibay-Gonzalez, F., Deciga-Alcaraz, A., & Vazquez-Zapien, G. J. (2026). Interpretable Random Forest (machine learning) analysis of two-trace 2D-COS FTIR spectra for multilayer biochemical characterization of colorectal precancerous. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 361, 128078. https://doi.org/10.1016/j.saa.2026.128078

Vancouver

Karthikeyan S, Mata-Miranda MM, Martinez-Cuazitl A, Garibay-Gonzalez F, Deciga-Alcaraz A, Vazquez-Zapien GJ. Interpretable Random Forest (machine learning) analysis of two-trace 2D-COS FTIR spectra for multilayer biochemical characterization of colorectal precancerous. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy. 2026;361:128078. doi:10.1016/j.saa.2026.128078

BibTeX
@article{Karthikeyan2026,
  author = {Karthikeyan, Sivakumaran and Mata-Miranda, Monica Maribel and Martinez-Cuazitl, Adriana and Garibay-Gonzalez, Francisco and Deciga-Alcaraz, Alejandro and Vazquez-Zapien, Gustavo Jesus},
  title = {Interpretable Random Forest (machine learning) analysis of two-trace 2D-COS FTIR spectra for multilayer biochemical characterization of colorectal precancerous},
  journal = {Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy},
  year = {2026},
  volume = {361},
  pages = {128078},
  doi = {10.1016/j.saa.2026.128078}
}
Kostenlos starten →