Surface-Enhanced Raman Scattering (SERS) spectroscopic technique and chemometric methods were combined to make a first noninvasive diagnosis of Chagas disease in human blood serum samples. We worked with 110 samples of patients; 45 of them healthy, and 65 infected which were separated into asymptomatic and symptomatic samples. Because of the biological samples exhibiting the Raman signals, the SERS effect was achieved using concentrated silver nanoparticles synthesized previously and attached prior to data collection. SERS spectra of each sample were acquired in the range from 400 to1700 cm−1 using a Raman microscope system. Both, Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA) were used for the data analysis.The results obtained had an accuracy of 96.3% for the classification of the samples into three groups (healthy, symptomatic, and asymptomatic patients).