Large language models for antibiotic prescribing and antimicrobial stewardship, Antimicrobial and Resistance

With the advent of large language models (LLMs) to support healthcare decisions, researchers are exploring their role in antibiotic prescribing. Currently, there is a lack of standardization in research on using LLMs for this purpose, necessitating more efforts to identify biases and misinformation in outputs from black box models. Additionally, antimicrobial prescribing requires balancing optimal treatment for individual patients with reducing antimicrobial resistance globally, aligning with antimicrobial stewardship core objectives. This challenge demands dedicated and standardized guidance to measure the appropriateness of LLMs' suggestions. Educating future medical professionals on these aspects is crucial for ensuring the proper use of LLM-based support in antibiotic prescribing, providing a deeper understanding of their strengths and limitations. Antimicrobial resistance is projected to cause up to 10 million deaths annually by 2050, surpassing deaths from other widespread diseases. Thus, achieving balanced and safe use of LLM support in antibiotic prescribing and antimicrobial stewardship initiatives is an opportunity not to be missed.