Diagnosis of renal failure by infrared spectrometric analysis of human serum samples and soft independent modeling of class analogy

Attenuated total reflection Fourier-transform infrared (ATR-FTIR) spectroscopy has been used in this research for reagent-free discrimination of serum samples obtained from healthy people and those with renal failure. No sample preparation step e.g. drying or pre-concentration is required prior to spectral analysis. Classification was performed based on the spectral variations in patient samples. In the experimental step, 75 blood serum samples, including 40 normal and 35 renal failure cases, were analyzed in 1800-900 cm(-1) spectral region. Unsupervised pattern recognition of the serum samples using cluster analysis (CA) and principal component analysis (PCA), did not demonstrate any useful capability of these techniques for discrimination aims. Supervised pattern recognition using soft independent modeling of class analogy (SIMCA) was performed. Results showed 95.12% of accuracy in ATR-FTIR diagnostic results being compared with the current clinical methods. The sensitivity and specificity of the proposed method are 100% and 91.3%, respectively. (C) 2012 Elsevier B.V. All rights reserved.