Post-Transplant Liver Monitoring Utilizing Integrated Surface-Enhanced Raman and AI in Hepatic Ischemia-Reperfusion Injury Animal Model

• Published in: International journal of nanomedicine Vol. 20; no. Issue 1; pp. 6743 - 6755
• Main Authors: Lee, Sanghwa, Kwon, Hyunhee, Oh, Jeongmin, Kim, Kyeong Ryeol, Hwang, Joonseup, Kang, Suyeon, Lee, Kwanhee, Namgoong, Jung‑Man, Kim, Jun Ki
• Format: Journal Article
• Language: English
• Published: New Zealand Dove Medical Press Limited 01.01.2025; Taylor & Francis Ltd; Dove; Dove Medical Press
• Subjects: Algorithms; Anesthesia; Animals; Artificial Intelligence; Biomarkers; Blood; Data mining; discriminant analysis; Disease Models, Animal; Ischemia; Laboratory animals; Liver; Liver - blood supply; Liver - pathology; Liver diseases; liver function; Liver ischemia-reperfusion injury; Liver Transplantation - adverse effects; Liver transplants; Machine Learning; machine learning algorithm; Male; Mice; Mice, Inbred C57BL; Original Research; Reperfusion injury; Reperfusion Injury - diagnosis; Reperfusion Injury - diagnostic imaging; Reperfusion Injury - pathology; Silicon wafers; Spectrum Analysis, Raman - methods; surface-enhanced Raman spectroscopy; Transplantation; South Korea; Japan; Taiwan; United States > US; Germany; liver ischemia-reperfusion injury; discriminant analysis; machine learning algorithm; liver function; surface-enhanced Raman spectroscopy
• ISSN: 1178-2013; 1176-9114; 1178-2013
• DOI: 10.2147/IJN.S497900

While liver transplantation saves lives from irreversible liver damage, it poses challenges such as graft dysfunction due to factors like ischemia-reperfusion (IR) injury, which can lead to significant cellular damage and systemic complications. Current diagnostic tools for detecting IR injury have limitations, necessitating advanced methods for timely intervention. This study explores the integration of surface-enhanced Raman spectroscopy (SERS) with artificial intelligence (AI) to improve diagnostic accuracy for liver IR injury. IR injury was induced using a mouse model, and histopathological and hepatic functional evaluations were conducted alongside SERS measurements. Raman signals obtained via SERS chips, which selectively filter nano-biomarkers and enhance signals, were analyzed using machine learning algorithms. The PC-LDA derived from spectra achieved an accuracy of 93.13%, while a machine learning algorithm based on PC-derived PLS-DA improved accuracy to 98.75%. Our findings emphasize the potential of combining SERS with AI to detect and specifically identify dysfunction due to liver damage early, potentially advancing patient management in liver transplantation.