Principal Investigator: Prof. Carlo Liberale
Poster Presenter: Elisa Grassi
Cancer is a leading cause of death globally, accounting for nearly 20 million deaths in 2020. A key factor for reducing cancer-associated mortality is early diagnosis. However, the current methods for screening patients are invasive, not accurate in the early stages of the disease and often involve subjectivity in their interpretation. A revolutionary development in the diagnosis of cancer is the analysis of circulating biomarkers in body fluids, referred as liquid biopsy. Among all the techniques for analyzing liquid biopsies, Raman Spectroscopy emerged as a powerful approach, due to its capability to probe the vibrational spectroscopic signature of molecules in a label-free manner, with high sensitivity and specificity. We propose a method for the screening and prognosis of cancer combining Raman spectroscopy with decision algorithms. The efficiency of our method has been demonstrated differentiating between cancer patients (breast and colon cancer) and healthy controls. After probing the Raman spectra of blood plasma samples, the data have been preprocessed and then classified via a Support Vector Machine (SVM) model. Finally, the classification’s performance was assessed by a leave-one out cross validation, obtaining sensitivity and specificity results higher than 90%. These results consolidate the efficiency of Raman spectroscopy combined with a SVM classifier for the diagnosis of different types of cancer.