Related Experiment Video
Updated: Sep 12, 2025
06:12
Multimodal Analytical Platform on a Multiplexed Surface Plasmon Resonance Imaging Chip for the Analysis of Extracellular Vesicle Subsets
Published on: March 17, 2023
1.6K
Engineering the Interfacial Charge Transfer Dynamics by Plasmonic S-Scheme Heterojunctions for
Zhen Yang1, Jing Wang1, Jiahui Zhao2
1Anhui Laboratory of Functional Coordinated Complexes for Materials Chemistry and Application, School of Chemical and Environmental Engineering, Anhui Polytechnic University, Wuhu 241000, P. R. China.
Analytical Chemistry
|August 9, 2025
Summary
We developed a machine learning-powered biosensor for disease diagnostics. This dual-mode sensor accurately detects cardiac troponin I (cTnI) at low levels, enabling advanced point-of-care testing.
Area of Science:
- Materials Science and Engineering
- Biomedical Engineering
- Analytical Chemistry
Background:
- Photoelectrochemical (PEC)-coupled dual-mode biosensors are crucial for point-of-care diagnostics.
- Machine learning (ML) integration enhances disease marker detection accuracy.
- Advanced materials are needed to improve biosensor performance.
Purpose of the Study:
- To develop a machine learning-powered, dual-channel immunoassay biosensor.
- To integrate plasmonic TiO2@NH2-MIL-125/Au S-scheme photoelectrodes with CdSe@ZIF-8 fluorescent probes.
- To achieve sensitive and accurate detection of cardiac troponin I (cTnI) for point-of-care applications.
Main Methods:
- Fabrication of a plasmonic S-scheme photoelectrode (TiO2@NH2-MIL-125/Au) and nanoconfined fluorescent probes (CdSe@ZIF-8).
- Construction of a smartphone-compatible PEC-coupled dual-mode biosensor.
- Utilizing a random forest algorithm and convolutional neural network for signal processing and cTnI quantification.
Main Results:
- The optimized photoelectrode showed a 581% enhancement in photocurrent density.
- The biosensor achieved an ultralow limit of detection for cTnI (6.01 fg/mL).
- The ML regression model demonstrated high accuracy (R2 = 0.9966) and low prediction error (5%) for cTnI quantification.
Conclusions:
- An intelligent, field-deployable dual-mode biosensing platform was established.
- The integration of advanced materials and ML analytics enables transformative point-of-care diagnostics.
- This approach offers a robust solution for sensitive and accurate disease marker detection.
