EUVIMEDEUVIMED entdecken
Crossref

Mid-infrared spectroscopy combined with machine learning for rapid detection of caffeine in creatine supplements: Supporting food safety and product integrity

Maria Clara da Cruz Pires, Antonio Carlos Albani de Oliveira, Gabriely Silveira Folli, Wanderson Romão, Paulo Roberto Filgueiras, Blanca Elena Guerrero Daboin, Valerio Garrone Barauna, Fabiano Kenji Haraguchi

Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy · 2026

DOI: 10.1016/j.saa.2025.127351 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2026. Verfasst von Maria Clara da Cruz Pires und 7 weiteren Autor:innen. Beteiligte Einrichtung: Postgraduate Program in Nutrition and Health, Federal University of Espírito Santo (UFES), Av. Mal. Campos, 1468, Maruípe, 29047-100 Vitória, ES, Bra…. Hauptthemen laut MEDLINE: Creatine, Caffeine, Dietary Supplements, Machine Learning. Die Arbeit nennt 63 Literaturangaben. Gefördert von: Coordenação de Aperfeiçoamento de Pessoal de Nível Superior, Instituto Nacional de Ciência e Tecnologia em Toxinas, Universidade Federal do Espírito Santo.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Creatine (CR) and Caffeine (CAF) are popular and extensively consumed dietary supplements (DS) on a global scale. Although the concomitant use of these substances may augment their effectiveness, it results in the risk of adulteration through mislabeling or the undisclosed addition of CAF. The use of reliable and rapid analytical screening tools is essential to ensure product integrity and protect consumer health. This study explores the application of Attenuated Total Reflectance Fourier-Transform Infrared (ATR-FTIR) spectroscopy combined with Machine Learning (ML) algorithms to detect and quantify CAF in CR supplements. Six commercial creatine brands were analyzed: five were intentionally adulterated with CAF at concentrations ranging from 0.0 % to 20.0 % (w/w), in 2.0 % increments (0.0 %, 2.0 %, 4.0 %, 6.0 %, 8.0 %, 10.0 %, 12.0 %, 14.0 %, 16.0 %, 18.0 %, and 20.0 %), while a sixth, previously unseen brand was used exclusively for external validation. Chemometric models, including Principal Component Analysis (PCA), Support Vector Machine (SVM) and Partial Least Squares (PLS) were performed. Two independent blind tests were conducted to assess the reproducibility and generalizability of the models: the first using three creatine brands included in model training, and the second using the independent sixth brand. The SVM model attained a Sensitivity (SEN) of 100 % and a Specificity (SPEC) of 75 % in the test dataset, whereas it reached 100 % SEN and 100 % SPEC in the blind tests. The PLS model exhibited a moderate quantitative performance, with a Root Mean Squared Error of Prediction (RMSEp) of 3.06 % and a Coefficient of Determination (R2) of 0.75 in the test dataset. In the first blind test, the PLS model showed R2 = 0.7 and RMSE = 2.84 %, while in the second blind test, the PLS metrics were R2 = 0.73 and RMSE = 2.11 %. Overall, these results demonstrate that ATR-FTIR spectroscopy combined with ML provides a reliable framework for screening creatine supplements adulterated with caffeine, supporting its potential use in industrial quality control and regulatory monitoring.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

CreatineCaffeineDietary SupplementsMachine LearningFood SafetySpectroscopy, Fourier Transform InfraredPrincipal Component AnalysisFood ContaminationDrug ContaminationReproducibility of ResultsSupport Vector Machine

Stichwörter der Autor:innen

Dietary supplementsFood safetyFourier transform infraredMachine learningSpectroscopy

Substanzen

CreatineCaffeine

Autor:innen und Institutionen

  • Postgraduate Program in Nutrition and Health, Federal University of Espírito Santo (UFES), Av. Mal. Campos, 1468, Maruípe, 29047-100 Vitória, ES, Brazil; Molecular Physiology and Artificial Intelligence Laboratory, Fede…
  • Molecular Physiology and Artificial Intelligence Laboratory, Federal University of Espírito Santo (UFES), Av. Mal. Campos, Maruípe, 29047-100 Vitória, ES, Brazil; Federal Institute of Espírito Santo (IFES), Av. Min. Sal…
  • Molecular Physiology and Artificial Intelligence Laboratory, Federal University of Espírito Santo (UFES), Av. Mal. Campos, Maruípe, 29047-100 Vitória, ES, Brazil; Chemometrics Laboratory, LabPetro, Federal University of…
  • Federal Institute of Espírito Santo (IFES), Av. Min. Salgado Filho, 1000, Soteco, 29106-010, Vila Velha, ES, Brazil.
  • Chemometrics Laboratory, LabPetro, Federal University of Espírito Santo (UFES), Av. Fernando Ferrari, 514, Goiabeiras, 29075-053 Vitória, ES, Brazil.
  • Postgraduate Program in Nutrition and Health, Federal University of Espírito Santo (UFES), Av. Mal. Campos, 1468, Maruípe, 29047-100 Vitória, ES, Brazil.

Förderung

  • Coordenação de Aperfeiçoamento de Pessoal de Nível Superior
  • Instituto Nacional de Ciência e Tecnologia em Toxinas
  • Universidade Federal do Espírito Santo
  • Foundation for Research Support of Espírito Santo
  • Conselho Nacional de Desenvolvimento Científico e Tecnológico

Zitieren

APA

da Cruz Pires, M. C., de Oliveira, A. C. A., Folli, G. S., Romão, W., Filgueiras, P. R., Daboin, B. E. G., Barauna, V. G., & Haraguchi, F. K. (2026). Mid-infrared spectroscopy combined with machine learning for rapid detection of caffeine in creatine supplements: Supporting food safety and product integrity. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy. https://doi.org/10.1016/j.saa.2025.127351

Vancouver

da Cruz Pires MC, de Oliveira ACA, Folli GS, Romão W, Filgueiras PR, Daboin BEG, et al. Mid-infrared spectroscopy combined with machine learning for rapid detection of caffeine in creatine supplements: Supporting food safety and product integrity. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy. 2026. doi:10.1016/j.saa.2025.127351

BibTeX
@article{daCruzPires2026,
  author = {da Cruz Pires, Maria Clara and de Oliveira, Antonio Carlos Albani and Folli, Gabriely Silveira and Romão, Wanderson and Filgueiras, Paulo Roberto and Daboin, Blanca Elena Guerrero and Barauna, Valerio Garrone and Haraguchi, Fabiano Kenji},
  title = {Mid-infrared spectroscopy combined with machine learning for rapid detection of caffeine in creatine supplements: Supporting food safety and product integrity},
  journal = {Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy},
  year = {2026},
  doi = {10.1016/j.saa.2025.127351}
}
Kostenlos starten →