Machine Learning Approach to Enhance the Performance of MNP-Labeled Lateral Flow Immunoassay

Nano-Micro Letters

Xuyang Huo¹  Daxiang Cui²  Wenqiang Yan²  Kan Wang²  Hao Xu³  Qinghui Jin⁴ 

[1] Department of Biomedical Engineering, JiLin Medical University, 132013, JiLin, People’s Republic of China;Department of Instrument Science and Engineering, School of Electronic Information and Electrical Engineering, Shanghai Engineering Research Center for Intelligent Diagnosis and Treatment Instrument, Key Laboratory of Thin Film and Microfabrication (Ministry of Education), Shanghai Jiao Tong University, 200240, Shanghai, People’s Republic of China;School of Naval Architecture, Ocean and Civil Engineering, Shanghai Jiao Tong University, 200240, Shanghai, People’s Republic of China;State Key Laboratory of Transducer Technology, Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences, 200050, Shanghai, People’s Republic of China;Faculty of Electrical Engineering and Computer Science, Ningbo University, 315211, Ningbo, People’s Republic of China;

关键词: Point-of-care testing;    Immunochromatography test strips;    Magnetic nanoparticles;    Machine learning;    Support vector machine;   

DOI  :  10.1007/s40820-019-0239-3

来源: Springer

【 摘 要 】

tsAn ultrasensitive multiplex biosensor was designed to quantify magnetic nanoparticles on immunochromatography test strips.A machine learning model was constructed and used to classify both weakly positive and negative samples, significantly enhancing specificity and sensitivity.A waveform reconstruction method was developed to appropriately restore the distorted waveform for weak magnetic signals.

【 授权许可】

CC BY