Single test-based diagnosis of multiple cancer types using Exosome-SERS-AI for early stage cancers

This research paper explores a novel method for early-stage cancer detection using a combination of exosomes, surface-enhanced Raman spectroscopy (SERS), and artificial intelligence (AI). The study demonstrates the ability to simultaneously detect six cancer types (lung, breast, colon, liver, pancreas, and stomach) with high accuracy using a single test. The AI model analyzes SERS profiles of plasma exosomes to identify cancer presence and tissue of origin, achieving an area under the curve (AUC) of 0.970 for cancer presence and a mean AUC of 0.945 among early-stage cancer patients. The integrated model shows a sensitivity of 90.2% and specificity of 94.4% in predicting cancer type.

Hyunku Shin, Byeong Hyeon Choi, On Shim, Jihee Kim, Yong Park, Suk Ki Cho, Hyun Koo Kim, Yeonho Choi