Author Description

"Antimicrobial resistance (AMR) is a serious danger to contemporary medicine and a global health issue. To stop AMR from emerging and spreading further, effective prevention techniques are urgently needed. Machine learning (ML) is being used more and more to predict antibiotic resistance in pathogens based on gene content and genome composition as data sets comprising hundreds or thousands of pathogen genomes become available. One of the main goals of this work is to promote the use of ML in front-line contexts while simultaneously emphasizing the additional improvements that are required to use these techniques in a secure and confident manner. Given the variety of quantitative and qualitative laboratory indicators of AMR, the issue of what to anticipate is not an easy one"--