Ratiometric Determination and Discrimination of Oxicams via Dual-Excitation Carbon Dots Assisted by Machine Learning
Ratiometric detection and discrimination of oxicams with dual-excitation carbon dots and machine learning
Abstract Abstract
This work presents a fluorescence method for detecting and distinguishing oxicam nonsteroidal anti-inflammatory drugs. It uses changes in the intensity ratio at two excitation peaks of fluorine- and nitrogen-codoped carbon dots for quantitative sensing, then combines XGBoost and convolutional neural networks for low-concentration discrimination and concentration prediction in real samples.
Research background
Oxicams are a common class of nonsteroidal anti-inflammatory drugs. Sensitive detection and discrimination support pharmaceutical analysis and risk monitoring. This study combines fluorescence sensing with machine learning rather than relying on a single spectral reading.
Sensing method
The study prepares fluorine- and nitrogen-codoped carbon dots through a hydrothermal method. The material has two excitation peaks near 280 nm and 340 nm. At a fixed emission wavelength, the ratio of the two excitation intensities changes with oxicam concentration. Meloxicam serves as the model compound for validating quantitative detection.
Machine learning for discrimination
After comparing several algorithms, the study uses XGBoost to distinguish oxicam drugs at low concentrations. It also develops a convolutional-neural-network-assisted sensing platform for predicting concentrations in real samples.
According to the abstract in indexing metadata, the method has a detection limit of 97 nM for meloxicam over a concentration range of 0.097–25 μM. XGBoost achieves 100% accuracy on unknown samples within the reported experimental dataset. These are the paper’s reported results and should not be generalized beyond the original experimental setting.
Publication details
- Journal: Analytical Chemistry
- Volume, issue, and pages: Volume 97, Issue 39, pages 21428–21437
- Online publication: 2025-09-25
- DOI: 10.1021/acs.analchem.5c03226
The metadata for this page was discovered through the author’s Google Scholar profile and cross-checked against Crossref, OpenAlex, and Semantic Scholar. Citation counts are dynamic and are therefore not stored in the repository.
Keywords
- carbon dots
- oxicams
- fluorescence sensing
- XGBoost
- convolutional neural network