Improving Vibrational Spectroscopy Prospects in Frontline Clinical Diagnosis: Fourier Transform Infrared on Buccal Mucosa Cancer

Abstract

We report a novel method with higher than 90% accuracy in diagnosing buccal mucosa cancer. We use Fourier transform infrared spectroscopic analysis of human serum by suppressing confounding high molecular weight signals, thus relatively enhancing the biomarkers' signals. A narrower range molecular weight window of the serum was also investigated that yielded even higher accuracy on diagnosis. The most accurate results were produced in the serum's 10-30 kDa molecular weight region to distinguish between the two hardest to discern classes, i.e., premalignant and cancer patients. This work promises an avenue for earlier diagnosis with high accuracy as well as greater insight into the molecular origins of these signals by identifying a key molecular weight region to focus on.

Figure 1

Difference in the average spectra of cancer and premalignant patient serum from healthy for whole serum. Error in faded color around each line shows level of distinction for each spectrum.

Figure 2

(A) Explained variance graph depending on the number of principle components (PCs) used. (B) Cross-validated sensitivity and specificity values dependent on the number of PCs used in the model. Example graph to demonstrate how the accuracy plateaus after a sufficient number of principle components. The cross-validated accuracy does not decrease after a point as the SVM algorithm ignores the unnecessary components and minimal or no overfitting occurs. The two graphs mimic one another; the plateau in panel B starts at 25 principle components whereas in panel A there is 99.84% variance explained. This example is from the classification of the whole cancer vs premalignant subset.

Figure 3

Classification accuracies between FTIR spectra of premalignant and cancer patients for different serum molecular weight subsets (molecular windows). The 95% confidence interval is shown by the gray lines over the bars. The 10–30 kDa window performed significantly better than the whole serum.