期刊
ANALYTICAL SCIENCES
卷 32, 期 2, 页码 225-231出版社
JAPAN SOC ANALYTICAL CHEMISTRY
DOI: 10.2116/analsci.32.225
关键词
Periodontal disease; Fourier transform infrared (FT-IR) microscopy; partial least squares (PLS) discriminant analysis; leave-one-out cross-validation (LOOCV)
资金
- Adaptable and Seamless Technology Transfer Program of Center for Revitalization Promotion, Japan Science and Technology Agency [241FT0492]
- Grants-in-Aid for Scientific Research [15K11083] Funding Source: KAKEN
Diagnosis of periodontal disease by Fourier transform infrared (FT-IR) microscopic technique was achieved for saliva samples. Twenty-two saliva samples, collected from 10 patients with periodontal disease and 12 normal volunteers, were pre-processed and analyzed by FT-IR microscopy. We found that the periodontal samples showed a larger raw IR spectrum than the control samples. In addition, the shape of the second derivative spectrum was clearly different between the periodontal and control samples. Furthermore, the amount of saliva content and the mixture ratio were different between the two samples. Partial least squares discriminant analysis was used for the discrimination of periodontal samples based on the second derivative spectrum. The leave-one-out cross-validation discrimination accuracy was 94.3%. Thus, these results show that periodontal disease may be diagnosed by analyzing saliva samples with FT-IR microscopy.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据