Analytical Evaluation of Simulated Kidney-Disease Profiles: Comparison of a Portable Near-Infrared Spectrophotometer with a Benchtop FT-NIR.
- 1iBB-Institute for Bioengineering and Biosciences, i4HB-The Associate Laboratory Institute for Health and Bioeconomy, IST-Instituto Superior Técnico, Universidade de Lisboa, 1049-001 Lisbon, Portugal.
- 2ISEL-Instituto Superior de Engenharia de Lisboa, Instituto Politécnico de Lisboa, 1549-020 Lisbon, Portugal.
- 3Instituto de Plasmas e Fusão Nuclear, IST-Instituto Superior Técnico, Universidade de Lisboa, 1049-001 Lisboa, Portugal.
Abstract
Chronic kidney disease (CKD) is commonly assessed using blood biomarkers such as creatinine, urea and albumin. This study compared a portable six-channel near-infrared (NIR) analyzer (miniNIR; 1300-2100 nm) with a benchtop Fourier-transform near-infrared (FT-NIR) instrument for the discrimination and quantification of fifty-four independent concentration-defined profiles in composed fetal bovine serum solutions spanning six simulated KDIGO categories. SVM-RBF, Random Forest, XGBoost, Logistic regression and partial least-squares discriminant analysis (PLS-DA) were evaluated. For miniNIR binary 'healthy/disease' profile discrimination, SVM-RBF yielded a validation AUC of 1.00, accuracy of 0.91, sensitivity of 1.00 and specificity of 0.83. The six-class profile assignment was substantially more difficult: PLS-DA was selected by grouped nested cross-validation, but validation accuracy was 0.18, macro-F1 was 0.11 and macro-AUC was 0.77 across the evaluable classes. For miniNIR regression, validation R² values were 0.48 for creatinine, 0.30 for urea and 0.10 for albumin. The strongest FT-NIR validation results were R² = 0.64 for creatinine, 0.79 for urea and 0.89 for albumin, depending on the spectral window. For FT-NIR binary 'healthy/disease' profile discrimination, SVM-RBF yielded a validation AUC of 0.99, accuracy of 0.71 and a specificity of 0.47. Although the high binary AUC in this controlled concentration design for the miniNIR, it should not be interpreted as evidence of CKD-specific recognition or clinical performance. The comparison quantifies the information retained and lost when continuous FT-NIR sampling is reduced to six broad discrete channels; validation in clinically characterized human samples is required before any screening application can be considered.
Related
- Impact of Sample Storage Conditions on Phenolic Profiles of Commercial Wines Assessed by UHPLC-HRMS: Implications for Analytical Reproducibility
- Mass-Scaling of Quantum Tunnelling in Hydrogen Bonds: Analytical Model and Comparison with Multidimensional Potentials
- Comparison of Two Passive Samplers for Hydrophilic and Lipophilic Phycotoxins and Expansion of Analytical Methods for Quantification Using UPLC-MS/MS.
- Experimental and Analytical Evaluation of Strengthening Techniques for Ultra-High-Performance Concrete Circular Columns
- PyCDFT: A Python-scriptable library for analytical evaluation of orbital conceptual density (matrix) functional theory
BibTeX
@article{serrano2026analytical,
title = {{Analytical Evaluation of Simulated Kidney-Disease Profiles: Comparison of a Portable Near-Infrared Spectrophotometer with a Benchtop FT-NIR.}},
author = {Diogo Serrano and Paulo Zoio and Bernardo B Carvalho and Luís P Fonseca and Cecília R C Calado},
journal = {Biosensors},
year = {2026},
month = oct,
doi = {10.3390/bios16100573},
url = {https://europepmc.org/article/MED/42930120},
note = {CC BY},
}
RIS
TY - JOUR
TI - Analytical Evaluation of Simulated Kidney-Disease Profiles: Comparison of a Portable Near-Infrared Spectrophotometer with a Benchtop FT-NIR.
AU - Diogo Serrano
AU - Paulo Zoio
AU - Bernardo B Carvalho
AU - Luís P Fonseca
AU - Cecília R C Calado
PY - 2026
DA - 2026/10/12
JO - Biosensors
DO - 10.3390/bios16100573
UR - https://europepmc.org/article/MED/42930120
AB - Chronic kidney disease (CKD) is commonly assessed using blood biomarkers such as creatinine, urea and albumin. This study compared a portable six-channel near-infrared (NIR) analyzer (miniNIR; 1300-2100 nm) with a benchtop Fourier-transform near-infrared (FT-NIR) instrument for the discrimination and quantification of fifty-four independent concentration-defined profiles in composed fetal bovine serum solutions spanning six simulated KDIGO categories. SVM-RBF, Random Forest, XGBoost, Logistic regression and partial least-squares discriminant analysis (PLS-DA) were evaluated. For miniNIR binary 'healthy/disease' profile discrimination, SVM-RBF yielded a validation AUC of 1.00, accuracy of 0.91, sensitivity of 1.00 and specificity of 0.83. The six-class profile assignment was substantially more difficult: PLS-DA was selected by grouped nested cross-validation, but validation accuracy was 0.18, macro-F1 was 0.11 and macro-AUC was 0.77 across the evaluable classes. For miniNIR regression, validation R² values were 0.48 for creatinine, 0.30 for urea and 0.10 for albumin. The strongest FT-NIR validation results were R² = 0.64 for creatinine, 0.79 for urea and 0.89 for albumin, depending on the spectral window. For FT-NIR binary 'healthy/disease' profile discrimination, SVM-RBF yielded a validation AUC of 0.99, accuracy of 0.71 and a specificity of 0.47. Although the high binary AUC in this controlled concentration design for the miniNIR, it should not be interpreted as evidence of CKD-specific recognition or clinical performance. The comparison quantifies the information retained and lost when continuous FT-NIR sampling is reduced to six broad discrete channels; validation in clinically characterized human samples is required before any screening application can be considered.
SN - 2079-6374
ER -