Psoriasisisconsideredawidespreaddermatologicaldiseasethatcanstronglyaffect thequalityoflife. Currently,thetreatmentiscontinueduntiltheskinsurfaceappearsclinically healed. However, lesions appearing normal may contain modifications in deeper layers. To terminatethetreatmenttooearlycanhighlyincreasetheriskofrelapses. Therefore,techniques are needed for a better knowledge of the treatment process, especially to detect the lesion modificationsindeeperlayers. Inthisstudy,wedevelopedafiber-basedSORS-SERDSsystem in combination with machine learning algorithms to non-invasively determine the treatment efficiencyofpsoriasis. ThesystemwasdesignedtoacquireRamanspectrafromthreedifferent depthsintotheskin,whichproviderichinformationabouttheskinmodificationsindeeperlayers. This way, it is expected to prevent the occurrence of relapses in case of a too short treatment. Themethodwasverifiedwithastudyof24patientsupontheirtwovisits: thedataisacquired atthebeginningofastandardtreatment(visit1)andfourmonthsafterwards(visit2). Amean sensitivityof≥85%wasachievedtodistinguishpsoriasisfromnormalskinatvisit1. Atvisit2, wherethepatientswerehealedaccordingtotheclinicalappearance,themeansensitivitywas ≈65%.