Connect with us


Study suggests that AI tools could be beneficial in detecting health care-associated infections, reports ET HealthWorld.



AI tools may help detect health care-associated infections, study finds, ET HealthWorld

A recent study published in the American Journal of Infection Control has revealed that artificial intelligence (AI) technologies can accurately identify cases of health care-associated infections (HAI) even in complex clinical scenarios. The study emphasizes the importance of clear and consistent language when utilizing AI tools for this purpose, pointing towards the potential for incorporating AI technology as a cost-effective component of routine infection surveillance programs.

According to the latest HAI Hospital Prevalence Survey conducted by the Centers for Disease Control and Prevention, there were 687,000 HAIs in acute care hospitals in the US with 72,000 HAI-related deaths among hospital patients in 2015. About 3 percent of all hospital patients have at least one HAI at any given time, highlighting the significance of effective surveillance and prevention measures.

The study evaluated the performance of two AI-powered tools for accurately identifying HAIs, one built using OpenAI’s ChatGPT Plus and the other developed using an open-source large language model known as Mixtral 8x7B. These tools were tested on two types of HAIs: central line-associated bloodstream infection (CLABSI) and catheter-associated urinary tract infection (CAUTI).

For all six cases presented to the AI tools with varying levels of complexity, both tools accurately identified the HAI when given clear prompts. However, missing or ambiguous information in the descriptions could hinder the accuracy of AI responses, emphasizing the need for human oversight of this technology.

The lead author of the research, Timothy L. Wiemken, an associate professor at Saint Louis University, emphasized the importance of continued development of AI tools with real-world patient data to support infection preventionists in the health care setting. The results of this study highlight the potential of AI-assisted HAI surveillance while underscoring the necessity of human intervention to ensure accurate outcomes.

Click to comment

You must be logged in to post a comment Login

Leave a Reply