Raman Spectroscopy for Clinical Oncology

Table 1

A summary demonstrating three different data analysis techniques applied to diagnosis of different types of cancer. The reference for each is presented. This table is purely to show the different applications for each technique and is by no means inclusive of all literature.

Data analysis method	Type of cancer	Number of Patients or; spectra collected	Sensitivity	Specificity	Reference
PCA	Brain (neuroblastoma, ganglioneuroma)	698 spectra	100%	100%	[16]
PCA and LDA	Breast	20 patients	92%	100%	[17]
SVM	Breast (axillary lymph nodes)	10447 spectra	100%*	100%*	[18]

*The SVM used a kernel constructed based on a radial basis function and achieved the highest specificity and sensitivity compared to other kernels.