Machine-Learning-Assisted Microfluidic Nanoplasmonic Digital Immunoassay for Cytokine Storm Profiling in COVID-19 Patients

作者：Zhuangqiang Gao, Yujing Song, Te Yi Hsiao, Jiacheng He, Chuanyu Wang, Jialiang Shen, Alana MacLachlan, Siyuan Dai, Benjamin H. Singer, Katsuo Kurabayashi, Pengyu Chen · 发表于：ACS Nano · 年份：2021 · DOI：10.1021/acsnano.1c06623 · 被引用次数：89 · 研究领域：Biosensors and Analytical Detection、Advanced Biosensing Techniques and Applications、SARS-CoV-2 and COVID-19 Research

Abstract Cytokine storm, known as an exaggerated hyperactive immune response characterized by elevated release of cytokines, has been described as a feature associated with life-threatening complications in COVID-19 patients. A critical evaluation of a cytokine storm and its mechanistic linkage to COVID-19 requires innovative immunoassay technology capable of rapid, sensitive, selective detection of multiple cytokines across a wide dynamic range at high-throughput. In this study, we report a machine-learning-assisted microfluidic nanoplasmonic digital immunoassay to meet the rising demand for cytokine storm monitoring in COVID-19 patients. Specifically, the assay was carried out using a facile one-step sandwich immunoassay format with three notable features: (i) a microfluidic microarray patterning technique for high-throughput, multiantibody-arrayed biosensing chip fabrication; (ii) an ultrasensitive nanoplasmonic digital imaging technology utilizing 100 nm silver nanocubes (AgNCs) for signal transduction; (iii) a rapid and accurate machine-learning-based image processing method for digital signal analysis. The developed immunoassay allows simultaneous detection of six cytokines in a single run with wide working ranges of 1–10,000 pg mL–1 and ultralow detection limits down to 0.46–1.36 pg mL–1 using a minimum of 3 μL serum samples. The whole chip can afford a 6-plex assay of 8 different samples with 6 repeats in each sample for a total of 288 sensing spots in less than 100 m...