Machine Learning-Guided Cobalt@Copper Dual-Metal Electrochemical Sensor for Urinary Creatinine Detection

Area of Science:

• Electrochemistry
• Nanomaterials Science
• Biomedical Engineering

Background:

• Creatinine monitoring is crucial for assessing kidney function.
• Existing methods for creatinine detection can be expensive or complex.
• Development of cost-effective and sensitive electrochemical sensors is needed.

Purpose of the Study:

• To develop a reliable and cost-effective electrochemical sensor for creatinine monitoring.
• To leverage synergistic effects of dual-metal electrodes and machine learning for enhanced performance.
• To validate the sensor's performance in real-world biological samples.

Main Methods:

• Fabrication of a dual-metal cobalt@copper electrode via sequential electrodeposition of nanoparticles.
• Characterization of electrode-nanoparticle complexation using cyclic voltammetry and spectroelectrochemical analyses.
• Application of machine learning algorithms (Random Forest, Extra Trees, XGBoost) for data analysis and feature optimization.

Main Results:

• Achieved a linear detection range of 0.00-4.00 mM with high sensitivity (6.06 ± 0.65 microA mM^-1) and a low limit of detection (0.13 mM).
• Demonstrated excellent selectivity against common interfering substances like urea, glucose, and ascorbic acid.
• Validated practical application in urine samples, showing strong agreement with standard creatinine assays.

Conclusions:

• The developed cobalt@copper electrochemical sensor, enhanced by machine learning, provides a sensitive, selective, and cost-effective platform for creatinine monitoring.
• The synergistic effect of dual metals and optimized data analysis significantly improves sensor performance.
• This approach holds promise for improved diagnostics and point-of-care applications in kidney function assessment.