Related Experiment Video
Updated: Jun 10, 2026
08:20
Superior Auto-Identification of Trypanosome Parasites by Using a Hybrid Deep-Learning Model
Published on: October 27, 2023
Artificial intelligence enabled performance evaluation of an enhanced SPR biosensor for malaria diagnosis
Md Al Amin Islam Utshob1, Maymona Binte Juwel1, Khandakar Mohammad Ishtiak1
1Department of Electrical and Electronic Engineering, Ahsanullah University of Science and Technology, 141 & 142, Love Road, Tejgaon Industrial Area, Dhaka, 1208, Bangladesh.
Scientific Reports
|June 8, 2026
Summary
A new surface plasmon resonance (SPR) biosensor using a multilayer structure offers a rapid and highly sensitive method for malaria diagnosis. This advanced sensor shows excellent performance for detecting malaria, even in its ring stage.
Area of Science:
- Biomedical Engineering
- Nanotechnology
- Plasmonics
Background:
- Malaria poses a significant global health threat, exacerbated by drug-resistant strains and climate change.
- There is a critical need for rapid, sensitive diagnostic tools for effective malaria control.
Purpose of the Study:
- To propose and analyze a novel multilayer surface plasmon resonance (SPR) biosensor for enhanced malaria diagnosis.
- To evaluate the biosensor's performance using advanced simulation techniques.
Main Methods:
- Utilized the transfer matrix method (TMM), finite element method (FEM), and finite difference time domain (FDTD) simulations.
- Designed a novel SPR biosensor with a multilayer N-FK51a+SiO2+Cu+HfO2+BP structure.
- Employed artificial neural network (ANN), ANFIS, and RBFNN models for sensor response prediction.
Main Results:
- Achieved a maximum angular sensitivity of 541.42 deg/RIU with a narrow FWHM of 1.98 deg.
- Demonstrated high detection accuracy (0.502 deg^-1) and quality factor (272.21 RIU^-1).
- Successfully predicted malaria stages using ANN, ANFIS, and RBFNN models, confirming enhanced performance.
Conclusions:
- The proposed SPR biosensor design exhibits superior sensitivity and accuracy for malaria diagnosis, particularly for the ring stage.
- The integration of SiO2, Cu, HfO2, and black phosphorus significantly enhances plasmonic field interactions.
- The sensor demonstrates robustness for real-time malaria detection and potential for broader biomedical applications.
