Dual-Mode SERS Lateral Flow Aptamer Assay with Machine Learning-Driven Highly Sensitive Interferon-γ Detection.

Area of Science:

• Biomedical Engineering
• Analytical Chemistry
• Immunology

Background:

• Interferon-γ (IFN-γ) is a crucial pro-inflammatory cytokine and biomarker for immune conditions.
• Detecting low pg/mL concentrations of IFN-γ requires ultrasensitive methods for early diagnosis.

Purpose of the Study:

• To develop a dual-mode aptamer assay for ultrasensitive detection of IFN-γ.
• To integrate machine learning for enhanced diagnostic accuracy and interpretation of results.

Main Methods:

• A competitive binding lateral flow aptamer assay utilizing surface-enhanced Raman scattering (SERS).
• Quantitative detection with a limit of detection of 2.23 pg/mL and a dynamic range of 5-2000 pg/mL.
• Clinical validation with human serum and machine learning algorithms (MLR, MLP, Random Forest) for classification.

Main Results:

• The assay achieved a limit of detection of 2.23 pg/mL, enabling ultrasensitive IFN-γ measurement.
• Clinical validation demonstrated high accuracy in distinguishing IFN-γ concentration tiers.
• The MLR model achieved 94.12% overall accuracy and excellent group-specific sensitivities and specificities.

Conclusions:

• The dual-mode SERS aptamer assay provides a robust and practical solution for ultrasensitive cytokine detection.
• Machine learning integration significantly enhances diagnostic performance for immune-related conditions.
• The platform shows potential for point-of-care applications in precision diagnostics.