Machine Learning-Enhanced Bacteria Detection Using a Fluorescent Sensor Array with Functionalized Graphene Quantum Dots.

Pathogenic bacteria are the source of many serious health problems, such as foodborne diseases and hospital infections. Timely and accurate detection of these pathogens is of vital significance for disease prevention, control of epidemic spread, and protection of public health security. Rapid identification of pathogenic bacteria has become a research focus in recent years. In contrast to traditional large-scale detection equipment, the fluorescent sensor array developed in this study can detect bacteria within just five min and is cost-effective. The array employs nitrogen- and sulfur-doped graphene quantum dots (NS-GQDs) synthesized through a simple hydrothermal process, making it environmentally friendly by avoiding toxic metal elements. Functionalized with antibiotics, spectinomycin, kanamycin, and polymyxin B, the NS-GQDs (renamed as S-NS-GQDs, K-NS-GQDs, and B-NS-GQDs) exhibit variable affinities for different bacteria, enabling broad-spectrum detection without targeting specific species. Upon binding with bacteria, the fluorescence intensity of the functionalized NS-GQDs decreases significantly. The sensor array exhibits distinct fluorescence responses to different bacterial species, which can be distinguished by using various machine learning algorithms. The results demonstrate that the platform can quickly and accurately identify and quantify five bacterial species, showing excellent performance in terms of accuracy, sensitivity, and stability. This makes it a promising tool with great practical application prospects in pathogenic bacterial detection.