Al tools may help detect health care- associated infections, study finds
Artificial intelligence (AI) technologies can accurately identify cases of health care-associated infections (HAI) even in complex clinical scenarios, a study has found. The study, published in the American Journal of Infection Control, highlights the need for clear and consistent language when using Al tools for this purpose.
The findings also illustrate the potential for incorporating Al technology as a cost-effective component of routine infection surveillance programmes.
According to the latest HAI Hospital Prevalence Survey conducted by the Centers for Disease Control and Prevention, there were 687,000 (6.8 lakh) HAIs in acute care hospitals in the US and 72,000 HAI-related deaths among hospital patients in 2015.
About 3 per cent of all hospital patients have at least one HAI at any given time, the researchers said.
The implementation of infection surveillance programmes and other infection-prevention protocols has reduced the incidence of HAIs, but they remain a risk, particularly to critically ill hospitalised patients with inserted devices such as central lines, catheters, or breathing tubes, they said.
Many hospitals and other health care facilities have HAI surveillance programmes to monitor for increased infection risk, but they require extensive resources, training, and expertise to maintain, according to the researchers.
In resource-constrained settings, a cost-effective alternative could help to enhance surveillance programmes and allow for better protection of high-risk patients, they said.
In the new study, the researchers at Saint Louis University and the University of Louisville School of Medicine, US, evaluated the performance of two Al-powered tools for accurate identification of HAls.
One tool was built using OpenAl's ChatGPT Plus and the other was developed using an open-source large language model known as Mixtral 8x7B.
The tools were tested on two types of HAIs: central line-associated bloodstream infection (CLABSI) and catheter-associated urinary tract infection (CAUTI).
CLABSI is a serious infection that occurs when germs, usually bacteria or viruses, enter the bloodstream through a catheter. CAUTI occurs when germs (usually bacteria) enter the urinary tract through the urinary catheter and cause infection.
Descriptions of six fictional patient scenarios with varying levels of complexity were presented to the Al tools, which were then asked whether the descriptions represented a CLABSI or a CAUTL
The descriptions included information such as the parient's age, symptoms, date of admission, and dates that central lines or catheters were inserted and removed. Al responses were compared to expert answers to determine accuracy.
For all six cases, both Al tools accurately identified the HAI when given clear prompts, the researchers said.
They found that missing or ambiguous information in the descriptions could prevent the Al tools from producing accurate results.
For example, Al tool using one description that did not include the date a catheter was inserted could not give a correct response.
Abbreviations, lack of specificity, use of special characters, and dates reported in numeric format instead of with the month spelled out all led to inconsistent responses, according to the researchers.
"Our results are the first to demonstrate the power of Al-assisted HAI surveillance in the health care setting, but they also underscore the need for human oversight of this technology," said Timothy L. Wiemken, an associate professor at Saint Louis University and lead author of the research.
"With the rapid evolution of the role of Al in medicine, our proof of concept study validates thed development of Al tools with real-world patient data to support infection preventionists," Wiemken added.
Source: The Economic Times
|