Predicting and identifying antimicrobial resistance in the marine environment using AI and machine learning algorithms.

Fough, Faranak; Janjua, Ghalib; Zhao, Yafan; Don, Aakash Welgamage

Abstract

Antimicrobial resistance (AMR) is an increasingly critical public health issue necessitating precise and efficient methodologies to achieve prompt results. The accurate and early detection of AMR is crucial, as its absence can pose life-threatening risks to diverse ecosystems, including the marine environment. The spread of AMR among microorganisms in the marine environment can have significant consequences, potentially impacting human life directly. This study focuses on evaluating the diameters of the disc diffusion zone and employs artificial intelligence and machine learning techniques such as image segmentation, data augmentation, and deep learning methods to enhance accuracy and predict microbial resistance.

Citation

FOUGH, F., JANJUA, G., ZHAO, Y. and DON, A.W. 2023. Predicting and identifying antimicrobial resistance in the marine environment using AI and machine learning algorithms. In Proceedings of the 2023 IEEE (Institute of Electrical and Electronics Engineers) International workshop on Metrology for the sea (MetroSea 2023); learning to measure sea health parameters, 4-6 October 2023, La Valletta, Malta. Piscataway: IEEE [online], pages 121-126. Available from: https://doi.org/10.1109/MetroSea58055.2023.10317294

• Conference Name: 2023 IEEE (Institute of Electrical and Electronics Engineers) International workshop on Metrology for the sea (MetroSea 2023); learning to measure sea health parameters
• Conference Location: La Valletta, Malta
• Start Date: Oct 4, 2023
• End Date: Oct 6, 2023
• Acceptance Date: Jun 30, 2023
• Online Publication Date: Dec 31, 2023
• Publication Date: Dec 31, 2023
• Deposit Date: Jan 11, 2024
• Publicly Available Date: Jan 11, 2024
• Publisher: Institute of Electrical and Electronics Engineers (IEEE)
• Pages: 121-126
• DOI: https://doi.org/10.1109/MetroSea58055.2023.10317294
• Keywords: Artificial intelligence; Machine learning methods; Inhibition zone measurement; Convolutional neural networks; Antimicrobial susceptibility test
• Public URL: https://rgu-repository.worktribe.com/output/2184711