Ali Stock Gallery

Two AI-driven tools can accurately detect cases of central line-associated bloodstream infection and catheter-associated urinary tract infection.



Researchers from Saint Louis University and the University of Louisville School of Medicine have explored how generative artificial intelligence (AI) can enhance healthcare-associated infection (HAI) surveillance programs. Their study, published in the American Journal of Infection Control, sheds light on the potential of AI in this critical area.

Healthcare-associated infections (HAIs) remain a significant challenge for healthcare providers worldwide. The Centers for Disease Control and Prevention (CDC) estimates that approximately one in every 31 hospital patients in the United States has at least one HAI on any given day. In 2015, there were 687,000 reported HAIs in US acute care hospitals, resulting in 72,000 patient deaths during their hospitalizations.

To address this issue, the researchers evaluated two large language models (LLMs): OpenAI’s ChatGPT Plus and an open-source model called Mixtral 8x7B. They assessed the LLMs’ ability to identify two specific types of infections:

  1. Central Line-Associated Bloodstream Infection (CLABSI)
  2. Catheter-Associated Urinary Tract Infection (CAUTI)

The LLMs were fed clinical scenarios with varying complexities, including patient symptoms, age, admission dates, and central line or catheter insertion/removal dates. Despite challenges such as missing or ambiguous information, both ChatGPT and Mixtral 8x7B accurately identified HAIs across all scenarios when given clear prompts.

This research highlights the potential of generative AI to improve infection surveillance programs, especially in cases where healthcare facilities may lack sufficient resources. By leveraging AI, healthcare organizations can enhance their ability to detect and prevent HAIs, ultimately improving patient safety and care delivery.

Remember that while AI shows promise, its implementation requires careful consideration of governance and risk management. As we continue to explore AI’s capabilities, it’s essential to strike a balance between innovation and patient well-being.