Abstract
Dengue and leptospirosis are prevalent diseases in tropical and subtropical regions, posing significant public health challenges. These illnesses exhibit overlapping symptoms, including fever, muscle pain, and headaches, which complicates diagnosis and delays appropriate treatment. This study explores the use of attenuated total reflectance-Fourier transform infrared spectroscopy (ATR-FTIR) combined with multivariate analysis to distinguish between the two infections by analyzing blood plasma in both liquid and dry states. A total of 114 patient samples at varying infection stages (n = 43 for leptospirosis and n = 71 for dengue) were examined using linear discriminant analysis (LDA), quadratic discriminant analysis (QDA), and support vector machine (SVM) in conjunction with genetic algorithms (GA), successive projection algorithms (SPA), and principal component analysis (PCA) for feature selection and extraction. The SPA-QDA model applied to dried plasma delivered exceptional results, achieving 100% sensitivity, specificity, and accuracy in distinguishing the two diseases using only 30 spectral variables. ANOVA calculations, conducted with a 95% confidence level, identified four key wavenumbers (1601 cm(-1), 1735 cm(-1), 1747 cm(-1), and 1870 cm(-1)) as critical for class differentiation.