Detecting Antibiotic Resistance with AI: Microbial Minutes

April 26, 2024

Scientists are leveraging artificial intelligence (AI) to develop new strategies for detecting antibiotic resistance in bacteria.

What's Hot in the Microbial Sciences?

Susceptible or resistant? When it comes to treating bacterial infections, the answer is crucial. In the clinic, microbiologists test bacterial isolates from patients to determine whether they are susceptible or resistant to a given antibiotic, a process known as antimicrobial susceptibility testing (AST). This information helps doctors decide what antibiotic to give patients, which is critical as the antimicrobial resistance crisis grows in scale and scope. The downside is that classic AST methods can take several days, during which patients may be treated with suboptimal antibiotics. But artificial intelligence (AI) could help. Scientists are finding ways to use AI and machine learning to develop testing tactics that are easy, accurate—and quick. Key take-aways and resources used in this Microbial Minutes are listed below.

Key Take-Aways

  • Determining if a bacterial isolate is susceptible or resistant to a given antibiotic informs patient care.
  • Gold-standard antimicrobial susceptibility testing (AST) methods can require several days before they guide key clinical decisions. 
  • Scientists are using AI to develop AST tactics that are accurate and quick. This includes leveraging deep learning, a form of machine learning, to detect resistance at the single-cell level in as little as 30 minutes.
  • This is just 1 way in which AI is being applied to detect and manage bacterial pathogens amidst the growing threat of antimicrobial resistance. 

Resources

Featured Study

  • Zagajewski A., et al. Deep learning and single-cell phenotyping for rapid antimicrobial susceptibility detection in Escherichia coli. Communications Biology, Nov. 14, 2023.

Additional Sources

  • Andersson D., et al. Mechanisms and clinical relevance of bacterial heteroresistance. Nature Reviews Microbiology, June 24, 2019.
  • Bhattacharyya R.P., et al. Simultaneous detection of genotype and phenotype enables rapid and accurate antibiotic susceptibility determination. Nature Medicine, Nov. 25, 2019.
  • Ding Y., et al. Artificial intelligence-assisted point-of-care testing system for ultrafast and quantitative detection of drug-resistant bacteria. SmartMat, May 10, 2023.
  • Hu X., et al. Novel Clinical mNGS-Based Machine Learning Model for Rapid Antimicrobial Susceptibility Testing of Acinetobacter baumannii. Journal of Clinical Microbiology, April 6, 2023.
  • Maheshwari R. What is Deep Learning AI? Forbes Advisor, April 3, 2023.
  • Pascucci M., et al. AI-based mobile application to fight antibiotic resistance. Nature Communications, Feb. 19, 2021.
  • Prinzi, A. Updating Breakpoints in Antimicrobial Susceptibility Testing. Asm.org, Dec. 13, 2023.
  • Stokes J.M., et al. A Deep Learning Approach to Antibiotic Discovery. Cell, Feb. 20, 2020.
  • Wang, S., et al. A Practical Approach for Predicting Antimicrobial Phenotype Resistance in Staphylococcus aureus Through Machine Learning Analysis of Genome Data. Frontiers in Microbiology, March 2, 2022.
  • Wong F., et al. Discovery of a structural class of antibiotics with explainable deep learning. Nature, Dec. 20, 2023.
  • Vasala A., et al. Modern Tools for Rapid Diagnostics of Antimicrobial Resistance. Frontiers in Cellular and Infection Microbiology. July 15, 2020. 

We want to hear from you! Please take 2-3 minutes to fill out the survey linked below. Your answers will help us improve future Microbial Minutes. And don't forget to subscribe to ASM's YouTube channel to be notified whenever a new video drops. 



Author: Madeline Barron, Ph.D.

Madeline Barron, Ph.D.
Madeline Barron, Ph.D. is the Science Communications Specialist at ASM. She obtained her Ph.D. from the University of Michigan in the Department of Microbiology and Immunology.