Rapid Identification of Etomidate and Its Structural Analogues Based on Surface-Enhanced Raman Spectroscopy and Machine Learning
10.12116/j.issn.1004-5619.2025.350703
- VernacularTitle:基于表面增强拉曼光谱与机器学习的依托咪酯及其结构类似物的快速鉴识
- Author:
Zi-Wen GUO
1
;
Tian-Yu QIU
;
Yue CAO
Author Information
1. 南京医科大学基础医学院法医学系,江苏 南京 211166
- Keywords:
forensic medicine;
toxicological analysis;
etomidate;
structural analogues;
silver nanopar-ticles(AgNPs);
surface-enhanced Raman spectroscopy(SERS);
machine learning;
rapid screening
- From:
Journal of Forensic Medicine
2025;41(4):364-370
- CountryChina
- Language:Chinese
-
Abstract:
Objective To obtain differential spectral characteristics of etomidate and its structural ana-logues,and to establish a rapid identification method using surface-enhanced Raman spectroscopy(SERS)combined with machine learning algorithms for distinguishing etomidate and its analogues.Methods Silver nanoparticles(AgNPs)were used as the SERS substrate to collect SERS spectra of etomidate,metomidate,propoxate,and isopropoxate at two concentrations of 1×10-4 and 1×10-5 mol/L.SERS spectra were also obtained from blood and urine samples containing 1×10-5 mol/L of etomidate,metomidate,propoxate,and isopropoxate,as well as from confiscated e-cigarette oil containing etomi-date.Uniform manifold approximation and projection(UMAP)was employed for nonlinear dimensiona-lity reduction and visualization,and a classification model based on the XGBoost algorithm was con-structed to enable discriminant analysis of these four structurally highly similar compounds.Results Mi-nor characteristic peak shifts(5-3 cm-1)were identified in the range of 1 398-811 cm-1.Qualitative identification of the compounds in serum,urine and e-cigarette oil samples was achieved without pre-treatment.After UMAP dimensionality reduction,distinct clustering separation among different sub-stances was observed.The XGBoost model achieved 100%classification accuracy on the test set.Feature weight analysis revealed that C-N stretching vibration(841 cm-1),C=O stretching vibration(1 367 cm-1),and C-O-C asymmetric vibration(1 049 cm-1)were the key spectral bands for discrimination.Conclu-sion The combination of SERS and machine learning can effectively amplify subtle differences in mo-lecular structures,enabling rapid and accurate identification of etomidate and its analogues.This ap-proach is suitable for on-site rapid screening in forensic toxicology.
