Arterial hypertension (AH) is a multifactorial and asymptomatic disease that affects vital organs such as the kidneys and heart. Considering its prevalence and the associated severe health repercussions, hypertension has become a disease of great relevance for public health across the globe. Conventionally, the classification of an individual as hypertensive or nonhypertensive is conducted through ambulatory blood pressure monitoring over a 24-h period. Although this method provides a reliable diagnosis, it has notable limitations, such as additional costs, intolerance experienced by some patients, and interferences derived from physical activities. Moreover, some patients with significant renal impairment may not present proteinuria. Accordingly, alternative methodologies are applied for the classification of individuals as hypertensive or nonhypertensive, such as the detection of metabolites in urine samples through liquid chromatography or mass spectrometry. However, the high cost of these techniques limits their applicability for clinical use. Consequently, an alternative methodology was developed for the detection of molecular patterns in urine collected from hypertension patients. In this study, a direct discrimination model for hypertensive and nonhypertensive individuals was generated through the amplification of Raman signals in urine samples based on gold nanoparticles and supported by chemometric techniques such as partial least squares-discriminant analysis (PLS-DA). Specifically, 162 patient urine samples were used to create a PLS-DA model. These samples included 87 urine samples from patients diagnosed with hypertension and 75 samples from nonhypertensive volunteers. The PLS-DA model with 4 latent variables (LV) was used to classify the hypertensive patients with a calibration sensitivity (SenCal) of 89.2%, cross-validation sensitivity (SenCV) of 75.4%, prediction sensitivity (SenPred) of 86.4%, calibration specificity (SpeCal) of 86.0%, cross-validation specificity (SpeCV) of 77.2%, prediction specificity (SpePred) of 77.8%, calibration accuracy (AccCal) of 87.7%, cross-validation accuracy (AccCV) of 77.0%, and prediction accuracy (AccPred) of 82.5%. This study demonstrates the ability of surface-enhanced Raman spectroscopy to differentiate between hypertensive and nonhypertensive patients through urine samples, representing a significant advance in the detection and management of AH.