Machine-Learning-Assisted Aggregation-Induced Emissive Nanosilicon-Based Sensor Array for Point-of-Care Identification of Multiple Foodborne Pathogens

• Published in: Analytical chemistry (Washington) Vol. 96; no. 17; pp. 6588 - 6598
• Main Authors: Li, Yuechun, Cui, Zhaowen, Wang, Ziqi, Shi, Longhua, Zhuo, Junchen, Yan, Shengxue, Ji, Yanwei, Wang, Yanru, Zhang, Daohong, Wang, Jianlong
• Format: Journal Article
• Language: English
• Published: United States American Chemical Society 30.04.2024
• Subjects: Algorithms; analytical chemistry; artificial intelligence; Artificial neural networks; Cronobacter sakazakii; Food contamination; Food safety; Foodborne pathogens; Functional groups; Learning algorithms; Listeria monocytogenes; Machine learning; milk; Nanosensors; Neural networks; Pathogens; point-of-care systems; quantitative analysis; Sensor arrays; sensors (equipment)
• ISSN: 0003-2700; 1520-6882; 1520-6882
• DOI: 10.1021/acs.analchem.3c05662

How timely identification and determination of pathogen species in pathogen-contaminated foods are responsible for rapid and accurate treatments for food safety accidents. Herein, we synthesize four aggregation-induced emissive nanosilicons with different surface potentials and hydrophobicities by encapsulating four tetraphenylethylene derivatives differing in functional groups. The prepared nanosilicons are utilized as receptors to develop a nanosensor array according to their distinctive interactions with pathogens for the rapid and simultaneous discrimination of pathogens. By coupling with machine-learning algorithms, the proposed nanosensor array achieves high performance in identifying eight pathogens within 1 h with high overall accuracy (93.75–100%). Meanwhile, Cronobacter sakazakii and Listeria monocytogenes are taken as model bacteria for the quantitative evaluation of the developed nanosensor array, which can successfully distinguish the concentration of C. sakazakii and L. monocytogenes at more than 103 and 102 CFU mL–1, respectively, and their mixed samples at 105 CFU mL–1 through the artificial neural network. Moreover, eight pathogens at 1 × 104 CFU mL–1 in milk can be successfully identified by the developed nanosensor array, indicating its feasibility in monitoring food hazards.