(Press-News.org) Arlington, Va. — March 14, 2024 — A new proof-of-concept study published today in the American Journal of Infection Control (AJIC) reports that artificial intelligence (AI) technologies can accurately identify cases of healthcare-associated infections (HAI) even in complex clinical scenarios. The study, which highlights the need for clear and consistent language when using AI tools for this purpose, illustrates the potential for incorporating AI technology as a cost-effective component of routine infection surveillance programs.
According to the most recent HAI Hospital Prevalence Survey conducted by the Centers for Disease Control and Prevention, there were approximately 687,000 HAIs in acute care hospitals in the U.S. and 72,000 HAI-related deaths among hospital patients in 2015. About 3% of all hospital patients have at least one HAI at any given time. The implementation of infection surveillance programs and other infection-prevention protocols has reduced the incidence of HAIs, but they remain a risk, particularly to critically ill hospitalized patients with inserted devices such as central lines, catheters, or breathing tubes.
Many hospitals and other healthcare facilities have HAI surveillance programs to monitor for increased infection risk, but they require extensive resources, training, and expertise to maintain. In resource-constrained settings, a cost-effective alternative could help to enhance surveillance programs and allow for better protection of high-risk patients.
In this new study, researchers at Saint Louis University and the University of Louisville School of Medicine evaluated the performance of two AI-powered tools for accurate identification of HAIs. One tool was built using OpenAI’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). Descriptions of six fictional patient scenarios with varying levels of complexity were presented to the AI tools, which were then asked whether the descriptions represented a CLABSI or a CAUTI. The descriptions included information such as the patient’s age, symptoms, date of admission, and dates that central lines or catheters were inserted and removed. AI responses were compared to expert answers to determine accuracy.
For all six cases, both AI tools accurately identified the HAI when given clear prompts. Importantly, the researchers found that missing or ambiguous information in the descriptions could prevent the AI tools from producing accurate results. For example, one description did not include the date a catheter was inserted; without that detail the AI tool 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.
“Our results are the first to demonstrate the power of AI-assisted HAI surveillance in the healthcare setting, but they also underscore the need for human oversight of this technology,” said Timothy L. Wiemken, PhD, MPH, an associate professor in the division of infectious diseases, allergy, and immunology at Saint Louis University and lead author of the paper. “With the rapid evolution of the role of AI in medicine, our proof-of-concept study validates the need for continued development of AI tools with real-world patient data to support infection preventionists.”
Additional details about the study include:
Both AI tools were used with retrieval augmented generation, an approach that improves the quality of prompting through a knowledge repository that gives the AI tool additional context. In this case, the repository included material from CDC’s National Healthcare Safety Network, a tracking system for HAIs.
The ChatGPT Plus tool developed for this study, HAI Assist, is available at the OpenAI GPT Store for people with a ChatGPT Plus subscription.
“HAI surveillance is a critical responsibility for infection preventionists, and our community needs every possible tool to help us ensure the safety of our patients,” said Tania Bubb, PhD, RN, CIC, FAPIC, 2024 APIC president. “This study suggests that AI-powered tools may offer a cost-effective means of improving our surveillance programs by assisting infection preventionists in day-to-day work functions.”
About APIC
Founded in 1972, the Association for Professionals in Infection Control and Epidemiology (APIC) is the leading association for infection preventionists and epidemiologists. With more than 15,000 members, APIC advances the science and practice of infection prevention and control. APIC carries out its mission through research, advocacy, and patient safety; education, credentialing, and certification; and fostering development of the infection prevention and control workforce of the future. Together with our members and partners, we are working toward a safer world through the prevention of infection. Join us and learn more at apic.org.
About AJIC
As the official peer-reviewed journal of APIC, The American Journal of Infection Control (AJIC) is the foremost resource on infection control, epidemiology, infectious diseases, quality management, occupational health, and disease prevention. Published by Elsevier, AJIC also publishes infection control guidelines from APIC and the CDC. AJIC is included in Index Medicus and CINAHL. Visit AJIC at ajicjournal.org.
NOTES FOR EDITORS
“Assisting the Infection Preventionist: Use of Artificial Intelligence for Healthcare-Associated Infection Surveillance,” by Timothy L. Wiemken and Ruth M. Carrico, was published online in AJIC on March 14, 2024. Available at: https://doi.org/10.1016/j.ajic.2024.02.007
AUTHORS
Timothy L. Wiemken, PhD, MPH, CIC (corresponding author: tim.wiemken@gmail.com), Saint Louis University
Ruth M. Carrico, PhD, DNP, University of Louisville School of Medicine
# # #
END
Governments must act now to address the effects of climate change and air pollution on fertility rates and reproductive health, says a document published by the European Society of Human Reproduction and Embryology (ESHRE) today (Thursday).
The factsheets* provide comprehensive information on global warming, evidence of its impact on fertility, and calls on policymakers to promote swift prevention measures.
Priorities should be to reach net zero CO2 emissions within the next 20 years, and to keep global warming within a 1.5% increase, says the expert ...
In preparation for the 2024 Olympic surfing competition, a new judging tower is being constructed in the reef lagoon at Teahupo’o, Tahiti. Researchers from the University of Hawai‘i (UH) at Mānoa, UH Hilo, and Arizona State University and community partners in Tahiti recently published a study in Remote Sensing that assessed the potential impacts of the tower and emphasized the importance of protecting the valuable reef—both as an integral part of the ecosystem and a resource for the local community.
“We ...
DURHAM, N.H. — Carbon dioxide (CO2) emissions are not typically associated with water ways, like streams and rivers, but emerging research shows that water bodies play an important role in storing and releasing carbon dioxide. As many states look for cost-effective ways to mitigate climate change, scientists at the New Hampshire Agricultural Experiment Station at the University of New Hampshire looked at a way to optimize CO2 sensors to better measure carbon dioxide emissions in lotic, or moving, bodies of water offering a new tool that can help provide valuable information for everything from land use to climate action plans.
“These sensors, adapted for highly ...
U.S. veterans of the wars in Afghanistan and Iraq who suffered mild traumatic brain injury from exposure to explosive blasts were found to have changes in cerebrospinal fluid proteins that are typically seen in people who develop Alzheimer’s disease, according to researchers at the University of Washington School of Medicine and VA Puget Sound Health Care System.
“While our research does not prove that veterans who experienced these injuries will develop Alzheimer’s disease, it raises the possibility that ...
Cases of cancer among UK men and women aged 35-69 years have seen a modest rise over the last quarter of a century, but there has also been a substantial decline in death rates, finds a study published by The BMJ today.
The results show a fall in death rates for all cancers combined and for 17 out of 22 cancer types examined, which the researchers say is likely due to fewer people smoking, screening programmes, and improved treatment, while a rise in some less common cancers may be due to higher levels of overweight and obesity, ...
A first of its kind study by Cancer Research UK reveals premature cancer death rates in 35–69-year-olds fell by more than a third over 25 years
Improvements in the UK are a result of smokefree policies, prevention measures, early detection programmes like cancer screening, and more effective treatment options
But the study paints a mixed picture with cancer cases on the rise and cancer mortality rates still too high
The charity’s manifesto, ‘Longer, ...
To combine two low-energy photons into one high-energy photon efficiently, the energy must be able to hop freely, but not too quickly, between randomly oriented molecules of a solid. This Kobe University discovery provides a much-needed design guideline for developing materials for more efficient PV cells, displays, or even anti-cancer therapies.
Light of different colors has different energies and is therefore useful for very different things. For the development of more efficient PV cells, OLED displays, or anti-cancer therapies it is desirable to be able to upcycle two low-energy photons into a high-energy photon, ...
Globally, more than half of patients die after infection with the neglected tropical disease, melioidosis, often before they are diagnosed1. A new rapid test could save lives by diagnosing patients in hours, rather than several days taken by current bacterial culture methods, meaning they receive the correct antibiotics faster.
The test uses CRISPR to detect a genetic target that is specific to Burkholderia pseudomallei, the bacterium that causes melioidosis, with 93 per cent sensitivity. It was ...
Revolutionary chronic wound treatment could help millions
A team of international scientists has developed an effective treatment for preventing infection in chronic wounds that does not involve antibiotics
The treatment involves the plasma (electrical gas) activation of hydrogel dressings to produce a unique mix of different chemical oxidants that applied to the wound are effective in decontaminating and aiding healing in chronic wounds
The new method is a significant advance that could revolutionise the treatment of diabetic foot ulcers and internal wounds
More than 540 million people ...
AMES, Iowa – Ravindra Singh has spent years studying a gene that when missing or mutated causes spinal muscular atrophy (SMA), a deadly disease that’s among the most common genetic disorders in children. His team’s latest work will make the search for treatments even more effective in the years to come.
Singh, a professor of biomedical science at Iowa State University, led an eight-year project to create a truncated version of the Survival Motor Neuron 2 (SMN2) gene to facilitate quicker, cheaper and less fragmented research. Nucleic Acids Research, a peer-reviewed ...
