Raman Spectral Signatures of Serum-Derived Extracellular Vesicle-Enriched Isolates May Support the Diagnosis of CNS Tumors

Investigating the molecular composition of small extracellular vesicles (sEVs) for tumor diagnostic purposes is becoming increasingly popular, especially diseases which diagnosis challenging, such as central nervous system (CNS) malignancies. Thorough examination content sEVs by Raman spectroscopy a promising but hitherto barely explored approach these types. We attempt to reveal potential role serum-derived in diagnosing CNS tumors through spectroscopic analyses using relevant number clinical samples. A total 138 serum samples were obtained from four patient groups (glioblastoma multiforme, non-small-cell lung cancer brain metastasis, meningioma and lumbar disc herniation control). After isolation, characterization assessment sEVs, Principal Component Analysis–Support Vector Machine (PCA–SVM) algorithm was performed on spectra pairwise classifications. Classification accuracy (CA), sensitivity, specificity Area Under Curve (AUC) value derived Receiver Operating Characteristic (ROC) used evaluate performance classification. The compared distinguishable with 82.9–92.5% CA, 80–95% sensitivity 80–90% specificity. AUC scores range 0.82–0.9 suggest excellent outstanding classification performance. Our results support that analysis sEV-enriched isolates method could be further developed order applicable tumors.