Madhuri S, Vengadesan N, Aruna P, Koteeswaran D, Venkatesan P, Ganesan S
Division of Medical Physics and Lasers, Department of Physics, Anna University, Chennai, India.
Photochem Photobiol. 2003 Aug;78(2):197-204. doi: 10.1562/0031-8655(2003)078<0197:nfsobp>2.0.co;2.
Native fluorescence characteristics of blood plasma were studied in the visible spectral region, at two different excitation wavelengths, 405 and 420 nm, to discriminate patients with different stages of oral malignancy from healthy subjects. The fluorescence spectra of blood plasma of oral malignant subjects exhibit characteristic spectral differences with respect to normal subjects. Different ratios were calculated using the fluorescence intensity values at those emission wavelengths that give characteristic spectral features of each group of experimental subjects studied. These fluorescence intensity ratios were used as input variables for a multiple linear discriminant analysis across different groups. Leave-one out cross-validation was used to check the reliability of each discriminant analysis performed. The discriminant analysis performed across normal and oral cancerous subjects classified 94.7% of the original grouped cases and 93.7% of the cross-validated grouped cases. A classification algorithm was developed on the basis of the score of the discriminant functions (discriminant score) resulted in the analyses. The diagnostic potentiality of the present technique was also estimated in the discrimination of malignant subjects from normal and nonmalignant diseased subjects such as liver diseases. In the discriminant analysis performed across the three groups, normal, oral malignancy (including early and advanced stages) and liver diseases, 99% of the original grouped cases and 95.9% of the cross-validated grouped cases were correctly classified. Similar analysis performed across normal, early stage of oral malignancy, advanced oral malignancy and liver diseases correctly classified 94.9% of the original grouped cases and 91.8% of the cross-validated grouped cases.
在可见光谱区域，于405和420 nm这两个不同激发波长下，研究了血浆的天然荧光特性，以区分不同口腔恶性肿瘤阶段的患者与健康受试者。口腔恶性肿瘤患者的血浆荧光光谱与正常受试者相比呈现出特征性的光谱差异。利用在那些能给出每组研究实验对象特征光谱特征的发射波长处的荧光强度值计算不同的比率。这些荧光强度比率被用作不同组之间多元线性判别分析的输入变量。采用留一法交叉验证来检验所进行的每次判别分析的可靠性。对正常和口腔癌患者进行的判别分析对94.7%的原始分组病例和93.7%的交叉验证分组病例进行了分类。基于分析中得到的判别函数得分（判别分数）开发了一种分类算法。还评估了本技术在区分恶性受试者与正常及非恶性疾病受试者（如肝脏疾病）方面的诊断潜力。在对正常、口腔恶性肿瘤（包括早期和晚期）和肝脏疾病这三组进行判别分析时，99%的原始分组病例和95.9%的交叉验证分组病例被正确分类。对正常、口腔恶性肿瘤早期、口腔恶性肿瘤晚期和肝脏疾病进行的类似分析正确分类了94.9%的原始分组病例和91.8%的交叉验证分组病例。
