Abstract: The disclosed invention relates to a method for identifying biomarkers for the stratification of hypertensive patients among different hypertension diseases: endocrine forms of hypertension and primary hypertension. The method is a machine-learning based method using one trained classifier on a predefined input dataset to rank several combinations of omics biomarkers (miRNA, steroids, metanephrines, small metabolites) on the basis of the computation of at least one evaluation parameter. A combination of biomarkers is selected to stratify the hypertensive patient among said plurality of hypertension diseases. Also, the disclosed invention relates to a method for stratifying hypertensive patients, such as hypertensive patients with endocrine forms of hypertension (EHT).