Identifying the early signs of a CLABSI \u2014 which may appear weeks in advance \u2014 can help clinicians prevent them, according to Shruti K. Gohil, MD, MPH,<\/b> assistant professor of infectious diseases and associate medical director of epidemiology and infection prevention at the University of California, Irvine.<\/p>\n
Years ago, Gohil and colleagues developed a scoring tool called the Central Line Insertion Site Assessment (CLISA) to help clinicians identify and respond to signs that a central line may be causing inflammation or infection, which can lead to a CLABSI.<\/p>\n
For this study, Gohil and colleagues trained an AI model to predict CLISA risk scores for inflammation or infection in thousands of photos of central venous catheters (CVCs) and tested the model against trained clinicians. They presented their findings at SHEA Spring, the Society for Healthcare Epidemiology of America\u2019s annual conference. <\/p>\n
The AI model analyzed 5,551 photos of 964 central-line sites taken between January 2014 and June 2017 \u2014 1,191 (21%) photos from hospitalized patients, 2,539 (46%) from outpatient oncology patients, and 1,821 (33%) from nursing home residents.<\/p>\n
The model demonstrated a sensitivity \u2014 the ability to identify infected or inflamed catheters \u2014 of 78% and a specificity \u2014 the ability to identify healthy catheters \u2014 of around 79%, with an area under the curve (AUC) of 0.87, indicating a strong ability to classify the catheter site as either low-risk or high-risk for CLABSIs, according to the researchers. AUC is the \u201cgold standard\u201d for evaluating AI models, Gohil said.<\/p>\n
The model\u2019s performance was \u201cunexpectedly strong,\u201d she told Healio, adding that it \u201cis anticipated to improve with further training.\u201d<\/p>\n
\u201cWe were surprised by how well AI could perform with minimal training,\u201d Gohil <\/b>said. \u201cAt times it seemed AI was able to identify areas of concern that even a clinician may not immediately notice from a photograph alone.\u201d <\/p>\n
One issue that will require further study is how the model performs on darker skin tones, which makes it harder to detect redness, Gohil said.<\/p>\n
Meanwhile, Gohil said the study shows that AI programs could monitor a catheter site from a non-medical location.<\/p>\n
\u201cThe algorithms developed in this study could be integrated into remote mobile apps for use by patients and health care workers in all care settings, allowing a pragmatic way to bring infection-prevention practices into the home,\u201d she said. \u201cWith more care shifting to outpatient and home settings, scalable tools to monitor central lines are increasingly important for preventing avoidable infections.\u201d <\/p>\n
For more information:<\/h2>\n <\/h2>\n Shruti K. Gohil, MD, MPH<\/b>, <\/b>can be reached at skgohil@hs.uci.edu. <\/p>\n\n
\n
Perspective<\/h2>\n Back to Top
\n
\n
\n <\/div>\n
In a recently presented abstract at SHEA Spring 2026, investigators used AI to assess more than 5,000 images from 964 CVC exit sites from 874 adult patients to define catheter exit site skin changes to predict inflammation and a potential CLABSI. Using trained experts as the gold standard, the AI generated image assessment distinguished between normal\/low risk (CLISA 0-1) and inflamed\/infected catheters (CLISA 2 or 3). <\/default:p>These findings suggest that with serial imaging, AI assessment of central line exit sites may assist in the early detection and even prevention \u2014 with prompt catheter removal \u2014 of CLABSIs. If these findings are replicated across diverse populations, infection-prevention teams and ID practitioners may have an additional tool for both surveillance and diagnosis of CLABSIs, particularly in settings where on-site presence of ID expertise is limited.<\/default:p><\/p>\nGonzalo Bearman, MD, MPH, FACP, FSHEA, FIDSA<\/p>\n
Professor of MedicineVirginia Commonwealth University<\/p>\n
Disclosures: <\/strong> Bearman reports no relevant financial disclosure.
\n <\/p>\n<\/p><\/div>\n<\/p><\/div>\n\n
Published by:<\/span>\n
Sources\/Disclosures<\/h3>\n Source: <\/h2>\n Artificial intelligence photo-detection of high-risk lines to prevent central lines associated bloodstream infection (CLABSI). Presented at: SHEA Spring; April 7-10; Chicago.<\/p>\n
References:<\/b> <\/h2>\n\n
Disclosures: <\/strong>
<\/p>\n
\n
\n
<\/p>\n
Ask a clinical question<\/strong> and tap into Healio AI’s knowledge<\/strong> base.<\/p>\n
<\/p>\nPubMed, enrolling\/recruiting trials, guidelines<\/li>\n
<\/p>\n
Clinical Guidance, Healio CME, FDA news<\/li>\n
<\/p>\n
Healio’s exclusive daily news coverage of clinical data<\/li>\n
\n <\/ul>\n
Learn more<\/button>\n <\/div>\n<\/div>\n
![\"infectious](\"https:\/\/www.healio.com\/~\/media\/h5\/feature\/news\/publogos\/idn.svg?la=en&h=19&w=171&hash=E5D33CE188190E773BF16C8B389C7AAC\")
\n <\/div>\n<\/p><\/div>\n<\/p><\/div>\n