Fast and accurate analytical tools are essential to monitor food safety and identify any unwanted contaminants. Traditional methods are limited by time delays in analysis, costly and time-consuming sample preparation, and the need for highly skilled workers. Thus, the rapid development of electrochemical sensors has contributed to significant advances in the quantitative detection and screening of food bacteria. And the combination of analytical methods with machine learning methods provides high analytical accuracy in complex food matrices. This research focuses on developing a simple approach to creating an electrochemical platform with high sensitivity and selectivity. We propose using of the current-voltage (I−V) characteristics at the interface between the eutectic gallium-indium alloy (eGaIn) electrode and the hydrogel (Figure 1) to detect Streptococcus thermophilus and Bacillus coagulans bacterial concentrations in the range from 104 to 108 CFU/mL. When a potential difference is applied, a current flows through the system, as a result of which gallium is oxidized and its cations begin to diffuse into the hydrogel. In the hydrogel, gallium cations interact with bacteria, their metabolites, and phosphate anions. The interaction of gallium cations with various concentrations of bacteria leads to the formation of lactate and phosphate film in different ratios. Redox processes of the formation and decomposition of the film with different constituents determine the shape of the I-V characteristic peaks, which differ in the potential range of 0.02 – 5 V. We apply the feed-forward deep neural network model (multilayer perceptron) for logical data analysis. Multilayer perceptron training allows the detection of individual states at the eGaIn / hydrogel interface that depend on the hydrogel composition. An excellent determination accuracy of 94% is achieved. In five out of six cases, the trained multilayer perceptron model obtained correct results with the highest probabilities.

Soft hydrogel actuator for fast machine-learning-assisted bacteria detection

ACS Spring 2022

The official archive and repository for all ACS Meetings & Expositions abstracts and select posters or presentations.