Related Experiment Video
Updated: Aug 5, 2026
Fabrication of Carbon Nanotube High-Frequency Nanoelectronic Biosensor for Sensing in High Ionic Strength Solutions
Published on: July 22, 2013
Integrating structurally defined DNA-carbon nanotube sensors with machine learning for cancer detection
Piaoyi Chen1, Xin Zheng2, Yinong Li1
1South China Advanced Institute for Soft Matter Science and Technology, State Key Laboratory of Luminescent Materials and Devices, School of Emergent Soft Matter, South China University of Technology, Guangzhou 510640, China.
A novel artificial perception system (APS) offers accurate, low-cost liquid biopsy for cancer detection. This DNA-carbon nanotube sensor array combined with machine learning achieves high sensitivity and specificity for multicancer screening.
Area of Science:
- Biotechnology
- Medical Diagnostics
- Nanotechnology
Background:
- Liquid biopsy presents a noninvasive cancer detection method but faces challenges in accuracy, operability, and cost.
- Existing techniques often require a trade-off between sensitivity, specificity, and affordability.
Purpose of the Study:
- To develop an artificial perception system (APS) for accurate, scalable, and affordable liquid biopsy.
- To overcome the limitations of current cancer detection methods through a novel sensor and machine learning approach.
Main Methods:
- Developed a DNA-carbon nanotube sensor array to generate fluorescence fingerprints from serum samples.
- Utilized machine learning models to decode these fingerprints for disease state classification.
- Validated the APS on 253 serum samples, including liver, lung, and ovarian cancers, and noncancer controls.
Main Results:
- The APS demonstrated a mean sensitivity of 89% and specificity of 96% across all tested cancer types.
- Achieved 92% sensitivity and 95% specificity for early-stage lung cancer detection.
- Estimated the cost per test at approximately $4 USD, highlighting its affordability.
Conclusions:
- The developed APS offers a promising solution for accurate, scalable, and cost-effective multicancer detection.
- The system supports biological plausibility and clinical translation, paving the way for early cancer screening.
- This approach addresses key limitations in current liquid biopsy technologies.
