Qualitative and quantitative detection and identification of two benzodiazepines based on SERS and convolutional neural network technology

Sha, Xuanyu; Fang, Guoqiang; Cao, Guangxu; Li, Shuzhi; Hasi, Wuliji; Han, Siqingaowa

doi:10.1039/d2an01277d

Cited by 13 publications

(4 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ANNs are often referred to as the approach of machine learning and artificial intelligence, because of their broad successful use in many fields. 157 They have also been applied for the analysis of SERS data of several types of biological samples, e.g., for food analysis, 158 forensics, 159,160 palynology, 161 or medical diagnostics. 162 Due to the variability of SERS signals, convolutional neural networks are particularly well suited and perform very well, 132 because they contain convolutional and pooling layers that summarize features that may be present in neighboring data points.…”

Section: Analysis Of Complex Sers Data With Machine Learning Approachesmentioning

confidence: 99%

SERS microscopy as a tool for comprehensive biochemical characterization in complex samples

Kneipp,

Seifert,

Gärber

2024

Chem. Soc. Rev.

View full text Add to dashboard Cite

show abstract

Section: Analysis Of Complex Sers Data With Machine Learning Approachesmentioning

confidence: 99%

SERS microscopy as a tool for comprehensive biochemical characterization in complex samples

Kneipp,

Seifert,

Gärber

2024

Chem. Soc. Rev.

View full text Add to dashboard Cite

show abstract

“…Convolutional neural networks (CNNs) are a novel feature extraction technique that are extensively employed in recognition and classification models [7][8][9][10][11]. By allowing neurons to share parameters, CNN lowers the number of parameters in the model, simplifying it and improving feature extraction from the data.Laeli A R [12] et al classified tuberculosis by using CNN for feature extraction from chest X-ray images and combining it with other techniques.…”

Section: Introductionmentioning

confidence: 99%

Drug Classification and Identification Method Based on X-ray Absorption Spectroscopy Combined with Machine Learning

FANG,

LIU,

CHEN

et al. 2024

Preprint

View full text Add to dashboard Cite

With the emergence of new drugs, it is imperative to study new detection methods with higher detection speed and accuracy. Traditional detection methods require high requirements for detection instruments and environments, and are complex to operate. x-ray absorption spectroscopy NDT technology has the advantages of low operational difficulty, penetrating observation, and strong ability to differentiate substances, and is well suited for drug detection and identification. A combination of X-ray absorption spectroscopy, convolutional neural network (CNN), support vector machine (SVM) and improved particle swarm optimization algorithm (IPSO) is used to achieve the classification and identification of drugs. Firstly, 14 chemical reagents with chemical formula similar to that of drugs are selected as experimental samples, and the X-ray absorption spectra of these 14 samples are obtained using X-ray detectors. Then, the features of the spectral data are extracted using CNN, and the SVM model is trained with the extracted features and the two important initial parameters of the SVM are optimized using IPSO with the introduction of weight decay. Finally, the trained model is applied to the test set and the performance is evaluated by several metrics. The experimental results show that the model not only makes the parameter-optimized traditional machine learning model SVM very effective and improves the prediction accuracy to 99.14%, but also avoids the disadvantages of high complexity, dramatically long running time and reduced efficiency due to the direct fusion of IPSO and SVM, and can be well applied to drug classification, which can substantially improve the recognition accuracy with almost constant The algorithm running efficiency can be improved substantially with almost the same recognition accuracy. Therefore, the combination of X-ray absorption spectrometry with CNN, IPSO and SVM can provide a fast, highly accurate and reliable classification and recognition method with broad application prospects in the field of drug detection and identification. CCTS: O611.5 Literature Identification Code: A

show abstract

“…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 .…”

Section: Introductionmentioning

confidence: 99%

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

Martens,

Gozdzialski,

Newman

et al. 2024

Anal. Chem.

View full text Add to dashboard Cite

The detection of trace adulterants in opioid samples is an important aspect of drug checking, a harm reduction measure that is required as a result of the variability and unpredictability of the illicit drug supply. While many analytical methods are suitable for such analysis, community-based approaches require techniques that are amenable to point-of-care applications with minimal sample preparation and automated analysis. We demonstrate that surfaceenhanced Raman spectroscopy (SERS), combined with a random forest classifier, is able to detect the presence of two common sedatives, bromazolam (0.32−36% w/w) and xylazine (0.15−15% w/w), found in street opioid samples collected as a part of a community drug checking service. The Raman predictions, benchmarked against mass spectrometry results, exhibited high specificity (88% for bromazolam, 96% for xylazine) and sensitivity (88% for bromazolam, 92% for xylazine) for the compounds of interest. We additionally provide evidence that this exceeds the performance of a more conventional approach using infrared spectral data acquired on the same samples. This demonstrates the feasibility of SERS for point-of-care analysis of challenging multicomponent samples containing trace adulterants.

show abstract

Qualitative and quantitative detection and identification of two benzodiazepines based on SERS and convolutional neural network technology

Abstract: Drug abuse is a global social issue of concern. As the drug market expands, there is an urgent need for technological methods to rapidly detect drug abuse to meet the...

Cited by 13 publications

References 39 publications

SERS microscopy as a tool for comprehensive biochemical characterization in complex samples

SERS microscopy as a tool for comprehensive biochemical characterization in complex samples

Drug Classification and Identification Method Based on X-ray Absorption Spectroscopy Combined with Machine Learning

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

Contact Info

Product

Resources

About