Abstract
Raman spectroscopy (RS) has been used in the discrimination of normal and tumor cells for years. It is very important to validate an existing classification model using different algorithms. In this work, two algorithms of support vector classification (SVC) are utilized to validate our previous work about a LDA classification model of nasopharyngeal carcinoma (NPC) cell lines C666-1, CNE2 and nasopharyngeal normal cell line NP69. All of these two SVC algorithms use the same data set as the previous LDA model and, achieve great sensitivity and specificity. The final results show that our previous LDA classification model could be supported by different SVC algorithms and this demonstrates our classification model is reliable and may be helpful to the realization of RS to be one of diagnostic techniques of NPC.
Highlights
Nasopharyngeal carcinoma (NPC) is a malignant tumor which mainly spreads in Chinese southern area, while the incidence is relatively low in the others [6]
C666-1, CNE2 and NP69 could be separated into three clusters along with the directions of LDF1 and LDF2
Raman spectroscopy (RS) combining with various multivariate statistical analysis algorithms is feasible to distinguish normal and tumor cells, to validate an existing classification model under different algorithms is very important for its reliability
Summary
Nasopharyngeal carcinoma (NPC) is a malignant tumor which mainly spreads in Chinese southern area, while the incidence is relatively low in the others [6]. Analysis of Raman spectra may provide arrays of fingerprint assignments of physical vibration mode. Such information could be used to characterize differences between human normal and tumor samples combining with various multivariate statistical analysis algorithms include partial least squares (PLS), linear discriminant analysis (LDA), support vector machines (SVMs), etc. It is necessary to validate an existing classification model under different algorithms according to which the data set should be absolutely identical. A LDA model has been established to classify NPC and nasopharyngeal normal cell lines (C666-1, CNE2 and NP69) [11], and the objective of the present work is to validate this model using support vector classification (SVC). In order to take different validations of the proposed LDA model, two SVC algorithms introduced in detail below are utilized to the validation processes
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
