Breakthrough in Personalized Medicine: Machine Learning-Enhanced Sensor for High-Precision Terahertz Detection

Strategic Insights -

A team of researchers from the University of Science and Technology of China has made a significant contribution to the field of personalized medicine with the development of a machine learning-enhanced sensor for detecting biomarkers in the terahertz frequency range. The sensor, which is capable of detecting isoquercitrin, a crucial flavonoid biomarker, with exceptional sensitivity and reliability, is set to revolutionize point-of-care diagnostics, nutraceutical quality control, and personalized health monitoring applications.

Key Takeaways:

  • The sensor operates in the terahertz frequency range and achieves exceptional sensitivity of 1000 GHz/RIU with a quality factor ranging from 7.849 to 8.000.
  • The integration of machine learning algorithms, including an ensemble of Random Forest, Support Vector Machine, and Neural Network models, significantly enhances analytical capabilities with 98.7% prediction accuracy and 2.3 mg/mL RMSE.
  • The sensor demonstrates robust performance across varying incidence angles and electric field distribution analysis reveals optimal resonance at 0.68 THz with maximum field confinement.
  • The proposed system offers superior detection limits, high selectivity, and exceptional reliability with 95.3% average prediction confidence.
  • The sensor is suitable for point-of-care diagnostics, nutraceutical quality control, and personalized health monitoring applications.
  • The research was funded by Princess Nourah Bint Abdulrahman University and involved a team of researchers from the University of Science and Technology of China, including Jacob Wekalao, Hussein A. Elsayed, Haifa A. Alqhtani, Mayi bin Jumah, Mostafa R. Abukhadra, Stefano Bellucci, Amuthakkannan Rajakannu, and Ahmed Mehaney.

Statistics:

  • Sensitivity: 1000 GHz/RIU
  • Quality factor: 7.849 - 8.000
  • Prediction accuracy: 98.7%
  • Root mean square error (RMSE): 2.3 mg/mL
  • Average prediction confidence: 95.3%
  • Terahertz frequency range: 0.68 THz

Sources:

  • Sensing and Bio-Sensing Research, https://doi-org.sdpl.idm.oclc.org/10.1016/j.sbsr.2025.100842
  • University of Science and Technology of China, Department of Optics and Optical Engineering
  • Sensing and Bio-Sensing Research, http://www.journals.elsevier.com/sensing-and-bio-sensing-research/