Scholarlink

<p>The development of accessible diagnostic technologies for resource-limited settings remains a critical challenge in global health. This study presents a metasurface biosensor capable of simultaneous detection of cancer and malaria biomarkers. Operating at frequencies between 0.189–0.423 THz, the sensor demonstrates exceptional sensitivity of 1000 GHzRIU<sup>−1</sup> for cancer detection and 143 GHzRIU<sup>−1</sup> for malaria detection, with figure-of-merit values reaching 25.641 RIU⁻<sup>1</sup> and 5.102 RIU⁻<sup>1</sup>, respectively. The device exhibits robust performance characteristics, including consistent quality factors (6.750–10.846), low detection limits (0.065–0.520 RIU), and excellent signal stability across varying experimental conditions. Machine learning optimization using Random Forest Regression achieved R<sup>2</sup> scores of up to 94% for refractive index predictions and 89% for incident angle variations, validating the sensor’s reliability and predictive accuracy. This dual-mode biosensor represents a significant advancement in point-of-care diagnostics, offering a unified platform for simultaneous cancer and malaria screening with potential for widespread implementation in resource-constrained healthcare environments.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

VLSI-Integrated CMOS-Compatible High-Performance Terahertz Metasurface Biosensor for Dual-Mode Detection of Cancer and Malaria with Machine Learning Optimization

  • 期刊论文

  • 发表日期：

    2025年5月23日

查看全文
  • Navaneethan S,
  • Jacob Wekalao,
  • Amuthakkannan Rajakannu

摘要

The development of accessible diagnostic technologies for resource-limited settings remains a critical challenge in global health. This study presents a metasurface biosensor capable of simultaneous detection of cancer and malaria biomarkers. Operating at frequencies between 0.189–0.423 THz, the sensor demonstrates exceptional sensitivity of 1000 GHzRIU−1 for cancer detection and 143 GHzRIU−1 for malaria detection, with figure-of-merit values reaching 25.641 RIU⁻1 and 5.102 RIU⁻1, respectively. The device exhibits robust performance characteristics, including consistent quality factors (6.750–10.846), low detection limits (0.065–0.520 RIU), and excellent signal stability across varying experimental conditions. Machine learning optimization using Random Forest Regression achieved R2 scores of up to 94% for refractive index predictions and 89% for incident angle variations, validating the sensor’s reliability and predictive accuracy. This dual-mode biosensor represents a significant advancement in point-of-care diagnostics, offering a unified platform for simultaneous cancer and malaria screening with potential for widespread implementation in resource-constrained healthcare environments.