Diagnosis and classification of kidney transplant rejection using machine learning-assisted surface-enhanced Raman spectroscopy using a single drop of serum.

The quest to reduce kidney transplant rejection has emphasized the urgent requirement for the development of non-invasive, precise diagnostic technologies. These technologies aim to detect antibody-mediated rejection (ABMR) and T-cell-mediated rejection (TCMR), which are asymptomatic and pose a risk of potential kidney damage. The protocols for managing rejection caused by ABMR and TCMR differ, and diagnosis has traditionally relied on invasive biopsy procedures. Therefore, a convergence system using a nano-sensing chip, Raman spectroscopy, and AI technology was introduced to facilitate diagnosis using serum samples obtained from patients with no major abnormality, ABMR, and TCMR after kidney transplantation. Tissue biopsy and Banff score analysis were performed across the groups for validation, and 5 μL of serum obtained at the same time was added onto the Au-ZnO nanorod-based Surface-Enhanced Raman Scattering sensing chip to obtain Raman spectroscopy signals. The accuracy of machine learning algorithms for principal component-linear discriminant analysis and principal component-partial least squares discriminant analysis was 93.53% and 98.82%, respectively. The collagen (an indicative of kidney injury), creatinine, and amino acid-derived signals (markers of kidney function) contributed to this accuracy; however, the high accuracy was primarily due to the ability of the system to analyze a broad spectrum of various biomarkers.