Diagnosis of basal cell carcinoma by infrared spectroscopy of whole blood samples applying soft independent modeling class analogy

J Cancer Res Clin Oncol. 2007 Dec;133(12):1001-10. doi: 10.1007/s00432-007-0286-x. Epub 2007 Aug 2.

Abstract

Attenuated total reflectance-Fourier transform infrared (ATR-FTIR) spectroscopy was applied to discriminate the blood samples obtained from healthy people and those with basal cell carcinoma, demonstrating high accuracy while soft independent modeling class analogy (SIMCA) chemometric technique is benefited. It was aimed to classify the normal case and cancer case blood samples through the use of ATR-FTIR spectroscopy as a rapid method while the sample preparation is so easy in comparison with the common pathologic methods. A total of 72 blood samples, including 32 cancer and 40 normal cases, were analyzed in 1,800-900 cm(-1) spectral region. Results showed 97.6% of accuracy being compared with the current clinical methods. Research results were exemplified with comparable data of other classification methods such as principal component analysis (PCA) and Cluster analysis. The residual errors in prediction (REP) of calibration model for normal and cancerous groups in SIMCA method were 0.00362 and 0.00343, respectively.

Publication types

  • Comparative Study
  • Evaluation Study

MeSH terms

  • Adult
  • Basal Cell Carcinoma / blood*
  • Basal Cell Carcinoma / diagnosis*
  • Cluster Analysis
  • Female
  • Humans
  • Male
  • Middle Aged
  • Principal Component Analysis
  • Reproducibility of Results
  • Sensitivity and Specificity
  • Skin Neoplasms / blood*
  • Skin Neoplasms / diagnosis*
  • Spectroscopy, Fourier Transform Infrared* / instrumentation
  • Spectroscopy, Fourier Transform Infrared* / methods