Ratiometric Determination and Discrimination of Oxicams via Dual-Excitation Carbon Dots Assisted by Machine Learning

Area of Science:

• Analytical Chemistry
• Materials Science
• Biomedical Engineering

Background:

• Oxicams, a class of nonsteroidal anti-inflammatory drugs (NSAIDs), are widely used but pose health risks with excessive consumption.
• Current detection methods for oxicams may lack the sensitivity and specificity required for real-time health monitoring.
• There is a need for innovative and highly sensitive analytical techniques for oxicam detection.

Purpose of the Study:

• To develop a novel, highly sensitive fluorescent approach for the detection and discrimination of oxicams.
• To utilize fluorine and nitrogen codoped carbon dots as a sensing platform for oxicams.
• To integrate machine learning algorithms for enhanced oxicam analysis and real-world application.

Main Methods:

• Synthesis of fluorine and nitrogen codoped carbon dots via a hydrothermal method.
• Development of a fluorescence-based detection method measuring excitation intensity ratios.
• Application of XGBoost and Convolutional Neural Network (CNN) algorithms for discrimination and prediction.

Main Results:

• The carbon dot sensor exhibited a bright blue emission with distinct excitation peaks.
• A linear relationship was observed between excitation intensity ratio and oxicam concentration.
• The method achieved a low limit of detection (LOD) of 97 nM for meloxicam (MLX) within a 0.097–25 μM range.
• XGBoost algorithm demonstrated 100% accuracy in discriminating ultralow oxicam concentrations (0–3.5 μM).
• A CNN-assisted platform successfully predicted oxicams in real samples.

Conclusions:

• The developed fluorescent carbon dot sensor offers a sensitive and selective method for oxicam detection.
• Machine learning algorithms, particularly XGBoost and CNN, significantly enhance oxicam discrimination and real-sample analysis.
• This approach expands the utility of carbon dots in sensing and provides a viable strategy for public health monitoring of oxicams.