Dual-Mode Fluorescent/Intelligent Lateral Flow Immunoassay Based on Machine Learning Algorithm for Ultrasensitive Analysis of Chloroacetamide Herbicides
Yonghong Zha, Yansong Li, Jianhua Zhou, Xiaolan Liu, Ki Soo Park, Yu Zhou
Abstract
Given the harmful effect of pesticide residues, it is essential to develop portable and accurate biosensors for the analysis of pesticides in agricultural products. In this paper, we demonstrated a dual-mode fluorescent/intelligent (DM-f/DM-i) lateral flow immunoassay (LFIA) for chloroacetamide herbicides, which utilized horseradish peroxidase-IgG conjugated time-resolved fluorescent nanoparticle probes as both a signal label and amplification tool. With the newly developed LFIA in the DM-f mode, the limits of detection (LODs) were 0.08 ng/mL of acetochlor, 0.29 ng/mL of metolachlor, 0.51 ng/mL of Propisochlor, and 0.13 ng/mL of their mixture. In the DM-i mode, machine learning (ML) algorithms were used for image segmentation, feature extraction, and correlation analysis to obtain multivariate fitted equations, which had high reliability in the regression model with R 2 of 0.95 in the range of 2 × 10 2 –2 × 10 5 pg/mL. Importantly, the practical applicability was successfully validated by determining chloroacetamide herbicides in the corn sample with good recovery rates (85.4 to 109.3%) that correlate well with the regression model. The newly developed dual-mode LFIA with reduced detection time (12 min) holds great potential for pesticide monitoring in equipment-limited environments using a portable test strip reader and laboratory conditions using ML algorithms.