Related Experiment Video
Updated: Feb 28, 2026
Development of a Lateral Flow Immunochromatographic Strip for Rapid and Quantitative Detection of Small Molecule Compounds
Published on: November 13, 2021
Development of a chemometric-assisted SERS method for simultaneous analysis of HDL and LDL cholesterol in blood serum
Rimsha Khan1, Kinza Khan1, Haq Nawaz1
1Department of Chemistry, University of Agriculture Faisalabad, Faisalabad 38000, Pakistan.
Insights
Surface-enhanced Raman spectroscopy (SERS) effectively profiles High-density lipoproteins (HDL) and Low-density lipoproteins (LDL) cholesterol in blood serum. Advanced machine learning, specifically SVM-SMOTE, enhances accuracy in differentiating these critical lipid markers for cardiovascular disease risk assessment.
Area of Science:
- Biomedical Engineering
- Analytical Chemistry
- Clinical Diagnostics
Background:
- Cardiovascular diseases (CVD) are a leading cause of mortality globally.
- Abnormal concentrations of High-density lipoproteins (HDL) and Low-density lipoproteins (LDL) are key contributors to CVD.
- Accurate differentiation of HDL and LDL cholesterol is crucial for CVD risk assessment.
Purpose of the Study:
- To compare High-density lipoproteins (HDL) and Low-density lipoproteins (LDL) cholesterol using Surface-enhanced Raman spectroscopy (SERS).
- To apply chemometric and machine learning techniques for accurate lipid profiling and differentiation.
- To validate the efficacy of SVM-SMOTE in handling imbalanced lipid concentration data.
Main Methods:
- Utilized Surface-enhanced Raman spectroscopy (SERS) with silver nanoparticles (Ag-NPs) for spectral analysis of clinical blood serum samples.
- Employed Principal Component Analysis (PCA) for differentiating HDL and LDL cholesterol spectral features.
- Applied Support Vector Machine-Synthetic minority over-sampling technique (SVM-SMOTE) to address data imbalance and improve classification accuracy.
Main Results:
- SERS successfully identified distinct spectral features for HDL and LDL cholesterol.
- PCA effectively differentiated between HDL and LDL cholesterol in blood serum samples.
- SVM-SMOTE demonstrated improved performance, slightly increasing the macro-average Area Under the Curve (AUC) from 0.97 to 0.98, while maintaining a test AUC of 0.95.
Conclusions:
- SERS, combined with chemometric and advanced machine learning, provides an accurate method for comparative profiling of HDL and LDL cholesterol.
- The SVM-SMOTE model shows high accuracy and validation for differentiating lipid concentrations, reducing overfitting risks.
- This approach holds significant potential for improved CVD risk assessment through precise lipid analysis.
Abstract:
Cardiovascular diseases (CVD) are becoming a serious threat to human health. These are considered the leading causes of mortality. Abnormal lipid concentrations in the body, such as High-density lipoproteins (HDL) and Low-density lipoproteins (LDL), are major factors that contribute to CVD. Surface-enhanced Raman spectroscopy (SERS) has the potential to be used to compare HDL and LDL cholesterol. In the current study, SERS was employed for the comparative profiling of HDL and LDL cholesterol using clinical blood serum samples along with silver nanoparticles (Ag-NPs) as the SERS substrate. The SERS spectral features of HDL and LDL cholesterol were clearly identified by applying various chemometric statistical tools. The Principal Component Analysis (PCA) was employed for the differentiation of blood serum samples of HDL and LDL cholesterol. Moreover, the support vector machine-Synthetic minority over-sampling technique (SVM-SMOTE) was used to accurately address the different imbalanced concentration of HDL and LDL cholesterol in order to reduce the risk of overfitting as compared to traditional machine learning algorithms. The SMOTE algorithm improves the interpretability of SVM by analyzing the minority classes of data sets. The macro-average Area Under the Curve (AUC) increased slightly from 0.97 to 0.98 with SMOTE, though the test Area Under the Curve was the same as 0.95. These results showed the accuracy and validation of the SMOTE model for the comparison of blood serum samples of HDL and LDL cholesterol.
