Diagnosis of Ischemic Renal Failure Using Surface-Enhanced Raman Spectroscopy and a Machine Learning Algorithm

Abstract

To diagnose renal function using a biochip capable of detecting SERS and to assess Raman measurements taken from a bilateral renal ischemia model and the feasibility of early diagnosis was done. After generating a bilateral renal ischemia rat model, blood and urine were collected. After confirming the presence of renal injury and function, liquid drops were placed onto a Raman chip whose surface had been enhanced with Au-ZnO nanorods. SERS biomarkers that diffused into the nanogaps were selectively amplified. Raman signals varied based on the severity of the renal function, and these differences were confirmed statistically. These results confirm that renal ischemia leads to renal dysfunction and that surface-enhanced Raman spectroscopy and a machine learning algorithm can be used to track signals in the urine from the release of SERS biomarkers.

Label‐free atherosclerosis diagnosis through a blood drop of apolipoprotein E knockout mouse model using surface‐enhanced Raman spectroscopy validated by machine learning algorithm

“…If ischemia‐producing severe stenosis is detected earlier by the Raman‐based method, both medical and interventional treatment may improve clinical outcomes. In a previous study, ischemic renal dysfunction was detected with the SERS sensing chip, 60 and this Raman signal and the Raman signal in atherosclerosis were separated. This shows that it is possible to diagnose organ‐specific atherosclerosis, and there are plans to expand the scope through various animal and clinical studies in the future.…”

Practices, Potential, and Perspectives for Detecting Predisease Using Raman Spectroscopy

“…Furthermore, surface-enhanced Raman scattering (SERS), spatially offset Raman spectroscopy (SORS), and incorporating machine learning are complementary technologies that increase the detection sensitivity in liquid biopsies [63][64][65] and deep layers of tissues and organs [58,66]. They also increase accuracy in discriminant analysis [67][68][69][70][71][72].…”

Trace Detection of Adulterants in Illicit Opioid Samples Using Surface-Enhanced Raman Scattering and Random Forest Classification

“…Surface-enhanced Raman spectroscopy (SERS) has a potential to meet this need, as the amplification of Raman signals through localized electromagnetic fields can provide access to suitably low concentrations of interest for drug analysis. − SERS has demonstrated success for trace detection of adulterants in complex biological samples and laboratory mixtures of opioid samples. − Despite the promise of SERS, significant method development is required for it to reliably detect and differentiate trace adulterants in street drugs, often involving interferences in complex mixtures. , Progress in this area has simultaneously focused on the platform itself, including optimizing the design of SERS substrate, both in general and for specific analytes, − and the associated analysis methods. ,, The success of manual spectral interpretation is often limited for SERS, and there is a significant interest in the application of chemometric approaches. ,− Unsupervised machine learning (ML) methods such as principal component analysis (PCA), have been demonstrated for the detection of fentanyl using SERS spectra of binary drug mixtures . However, given the variability of SERS measurements, these unsupervised ML techniques often struggle to differentiate trace components as the complexity of the sample matrix increases .…”