EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Renal Cell Carcinoma Discrimination through Attenuated Total Reflection Fourier Transform Infrared Spectroscopy of Dried Human Urine and Machine Learning Techniques

Bogdan Adrian Buhas iD, Lucia Ana-Maria Muntean, Guillaume Ploussard, Bogdan Ovidiu Feciche, Iulia Andras iD, Valentin Toma iD, Teodor Andrei Maghiar, Nicolae Crișan, Rareș-Ionuț Știufiuc iD, Constantin Mihai Lucaciu iD

International Journal of Molecular Sciences · 2024

DOI: 10.3390/ijms25189830 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Molecular Sciences, 2024. Verfasst von Bogdan Adrian Buhas und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Urology, Medicover Hospital, 323T Principala St., 407062 Suceagu, Romania. Hauptthemen laut MEDLINE: Carcinoma, Renal Cell, Kidney Neoplasms, Machine Learning. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 55 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministerul Cercetării și Inovării, Ministry of Research, Innovation and Digitization, CNCS—UEFISCDI, University of Oradea, Romania.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Renal cell carcinoma (RCC) is the sixth most common cancer in men and is often asymptomatic, leading to incidental detection in advanced disease stages that are associated with aggressive histology and poorer outcomes. Various cancer biomarkers are found in urine samples from patients with RCC. In this study, we propose to investigate the use of Attenuated Total Reflection-Fourier Transform Infrared Spectroscopy (ATR-FTIR) on dried urine samples for distinguishing RCC. We analyzed dried urine samples from 49 patients with RCC, confirmed by histopathology, and 39 healthy donors using ATR-FTIR spectroscopy. The vibrational bands of the dried urine were identified by comparing them with spectra from dried artificial urine, individual urine components, and dried artificial urine spiked with urine components. Urea dominated all spectra, but smaller intensity peaks, corresponding to creatinine, phosphate, and uric acid, were also identified. Statistically significant differences between the FTIR spectra of the two groups were obtained only for creatinine, with lower intensities for RCC cases. The discrimination of RCC was performed through Principal Component Analysis combined with Linear Discriminant Analysis (PCA–LDA) and Support Vector Machine (SVM). Using PCA–LDA, we achieved a higher discrimination accuracy (82%) (using only six Principal Components to avoid overfitting), as compared to SVM (76%). Our results demonstrate the potential of urine ATR-FTIR combined with machine learning techniques for RCC discrimination. However, further studies, especially of other urological diseases, must validate this approach.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Carcinoma, Renal CellKidney NeoplasmsMachine LearningHumansSpectroscopy, Fourier Transform InfraredMaleFemaleMiddle AgedAgedPrincipal Component AnalysisAdultDiscriminant AnalysisBiomarkers, TumorSupport Vector MachineCreatinineUrinalysis

Stichwörter der Autor:innen

attenuated total reflection Fourier transform infrareddried urinelinear discrimination analysis–principal component analysismachine learningrenal cell carcinomasupport vector machine

Substanzen

Biomarkers, TumorCreatinine

Autor:innen und Institutionen

  • Department of Urology, Medicover Hospital, 323T Principala St., 407062 Suceagu, Romania.
  • Faculty of Medicine and Pharmacy, University of Oradea, 1 Universitatii St., 410087 Oradea, Romania.
  • Department of Medical Education, Iuliu Hatieganu University of Medicine and Pharmacy, 8 Victor Babes St., 400347 Cluj-Napoca, Romania.
  • Department of Urology, La Croix du Sud Hospital, 52 Chemin de Ribaute St., 31130 Quint-Fonsegrives, France.
  • Faculty of Medicine, Iuliu Hatieganu University of Medicine and Pharmacy, 8 Victor Babes St., 400347 Cluj-Napoca, Romania.
  • Department of Nanobiophysics, MedFuture Research Center for Advanced Medicine, Iuliu Hatieganu University of Medicine and Pharmacy, 4-6 Pasteur St., 400337 Cluj-Napoca, Romania.

ORCID-Profile: Bogdan Adrian Buhas, Iulia Andras, Valentin Toma, Rareș-Ionuț Știufiuc, Constantin Mihai Lucaciu

Förderung

  • Ministerul Cercetării și Inovării
  • Ministry of Research, Innovation and Digitization, CNCS—UEFISCDI
  • University of Oradea, Romania

Zitieren

APA

Buhas, B. A., Muntean, L. A., Ploussard, G., Feciche, B. O., Andras, I., Toma, V., Maghiar, T. A., Crișan, N., Știufiuc, R. I., & Lucaciu, C. M. (2024). Renal Cell Carcinoma Discrimination through Attenuated Total Reflection Fourier Transform Infrared Spectroscopy of Dried Human Urine and Machine Learning Techniques. International Journal of Molecular Sciences. https://doi.org/10.3390/ijms25189830

Vancouver

Buhas BA, Muntean LA, Ploussard G, Feciche BO, Andras I, Toma V, et al. Renal Cell Carcinoma Discrimination through Attenuated Total Reflection Fourier Transform Infrared Spectroscopy of Dried Human Urine and Machine Learning Techniques. International Journal of Molecular Sciences. 2024. doi:10.3390/ijms25189830

BibTeX
@article{Buhas2024,
  author = {Buhas, Bogdan Adrian and Muntean, Lucia Ana-Maria and Ploussard, Guillaume and Feciche, Bogdan Ovidiu and Andras, Iulia and Toma, Valentin and Maghiar, Teodor Andrei and Crișan, Nicolae and Știufiuc, Rareș-Ionuț and Lucaciu, Constantin Mihai},
  title = {Renal Cell Carcinoma Discrimination through Attenuated Total Reflection Fourier Transform Infrared Spectroscopy of Dried Human Urine and Machine Learning Techniques},
  journal = {International Journal of Molecular Sciences},
  year = {2024},
  doi = {10.3390/ijms25189830}
}
Kostenlos starten →