Detection of Antibodies for COVID-19 from Reflectance Spectrum Using Supervised Machine Learning

Since the coronavirus disease 2019 occurred, the lateral flow immunoassay (LFIA) test strip has become a global testing tool for convenience and low cost. However, some studies have shown that LFIA strips perform poorly compared to other professional testing methods. This paper proposes a new method...

Full description

Saved in:
Bibliographic Details
Published in2022 IEEE Sensors pp. 1 - 4
Main Authors Tsai, Ciao-Ming, Hong, Chitsung, Kong, Wei-Yi, Chiu, Wei-Huai, Ko, Cheng-Hao, Fang, Weileun
Format Conference Proceeding
LanguageEnglish
Published IEEE 30.10.2022
Subjects
COVID-19
LFIA
Machine learning
Reflectivity
Sensitivity and specificity
Sensors
spectra
Strips
Training
Online AccessGet full text

Cover

More Information
Summary:Since the coronavirus disease 2019 occurred, the lateral flow immunoassay (LFIA) test strip has become a global testing tool for convenience and low cost. However, some studies have shown that LFIA strips perform poorly compared to other professional testing methods. This paper proposes a new method to improve the accuracy of LFIA strips using spectral signals. A spectrochip module is applied to disperse the reflected light from the LFIA strips. The obtained spectral signals will be used for supervised machine learning. After training, the trained model has 93.8% accuracy compared to the standard test. This result indicated that the evaluation method based on the spectrum of LFIA strips could enhance the detection performance.
ISSN:2168-9229
DOI:10.1109/SENSORS52175.2022.9967070