Rapid Bacterial Detection and Identification of Bacterial Strains Using Machine Learning Methods Integrated With a Portable Multichannel Fluorometer

Abstract

Rapid and sensitive bioburden detection is of paramount importance in different applications including public health, and food and water safety. To overcome the traditional limitations of bacterial detection i.e., lengthy culture time, and complicated procedure, a low-cost, portable multichannel fluorometer coupled with machine learning (ML) has been implemented in this study. Five different strains of bacterial samples were tested along with the negative control for time-series fluorescence data collection and analysis. We applied different conventional unsupervised and supervised machine learning techniques with extracted features followed by preprocessing of the data. Initially, machine learning algorithms were applied for the qualitative detection of bacteria by binary classification followed by regression analysis to predict the level of contamination for E. coli. The multiclass classification was used to identify gram-positive, and gram-negative bacterial strains and differentiate all the bacterial strains tested. Our results show that around 97.9% accuracy can be achieved for bacterial contamination detection for as low as 1 CFU/mL while 92.1% accuracy can be achieved for differentiating the gram-positive and gram-negative strains. Additionally, with 1 minute of data, high accuracy is obtained for detecting bioburden, proving the multichannel fluorometer’s rapid detection capability. The multichannel fluorometer integrated with ML analytics is capable of automating data analysis and determining accurate and rapid bacterial detection on-site with the prediction of bioburden levels and differentiating bacterial strains and the protocol can be applied to the biosensors with a similar data type.

Keywords

• Bioburden
• fluorescence
• machine learning
• supervised algorithm
• unsupervised algorithm
• features