An observational study in Artificial Intelligence, Phlebitis After Infusion and Phlebitis, sponsored by Kutahya Health Sciences University. Completed at 2 sites in Turkey (Türkiye). Open to participants aged 18 Years to 85 Years. Per ClinicalTrials.gov, last updated 2026-10-22.
Sponsored by Kutahya Health Sciences University · Observational
This study aims to develop and validate multimodal AI-based prediction models for peripheral intravenous catheter (PIVC)-related phlebitis by integrating demographic, clinical, catheter-related, and phlebitis image data. The models will be evaluated for their ability to accurately predict phlebitis risk, with the goal of facilitating early identification, timely intervention, and improved patient safety.
Participants with peripheral intravenous catheters (PIVCs) will be monitored for the development of PIVC-related phlebitis. The insertion sites will be assessed at predefined time points using the Visual Infusion Phlebitis Score (VIPS). Phlebitis will be identified and graded according to the VIPS criteria.
Photographic images of the PIVC insertion sites will be obtained during the assessment period. The collected images, together with relevant demographic, clinical, and catheter-related characteristics, will be used to develop and validate machine learning-based prediction models. The primary focus of the models will be the detection and prediction of PIVC-related phlebitis based on photographic image data.
The performance of the developed models will be evaluated using appropriate diagnostic and predictive performance measures. The study aims to determine whether image-based artificial intelligence can accurately identify PIVC-related phlebitis and support early recognition and timely clinical intervention.
42 studies on the registry are indexed under Phlebitis; 9 are open to participants now.
Browse Phlebitis studies →Kutahya Health Sciences University is the lead sponsor of 216 studies on the registry; 49 are open to participants now.
Counted across the registry records on this site, refreshed daily.
The study population will consist of adult hospitalized patients requiring peripheral intravenous catheter (PIVC) insertion for intravenous therapy. Demographic, clinical, catheter-related, and catheter-site image data will be collected prospectively to develop and validate artificial intelligence-based models for predicting PIVC-related phlebitis. Participants will be monitored for the development of phlebitis using the Visual Infusion Phlebitis (VIP) Scale throughout the catheterization period.
IInclusion Criteria:
Adults aged 18 years or older.
Hospitalized patients requiring insertion of a peripheral intravenous catheter (PIVC).
Patients able to provide written informed consent or whose legally authorized representative can provide consent, if applicable.
Patients willing to undergo routine clinical assessment and catheter-site photography for AI model development.
Exclusion Criteria:
Presence of phlebitis or local skin infection at the intended catheter insertion site before PIVC placement.
Central venous catheter or other non-peripheral vascular access devices.
Patients with severe skin conditions, burns, or wounds at the catheter insertion site that prevent accurate assessment or imaging.
Poor-quality or missing clinical data or catheter-site images that preclude AI model development.
Patients who withdraw consent during the study.
A single cohort consisting of images used to develop and evaluate a model for phlebitis prediction
Other: Artificial Intelligence-Based Phlebitis Detection Model
An artificial intelligence-based model will be developed and evaluated to detect or predict phlebitis using clinical images. The model's performance will be assessed using image-based data.
Peripheral Intravenous Catheter-Related Phlebitis Occurrence
Occurrence of peripheral intravenous catheter-related phlebitis, assessed using the Visual Infusion Phlebitis Scale. The Visual Infusion Phlebitis Scale scores range from 0 to 5 (0 = healthy intravenous site, no signs of phlebitis; 5 = advanced stage thrombophlebitis). Higher scores indicate a worse outcome. Phlebitis will be defined as a Visual Infusion Phlebitis Scale score of 2 or higher.
Time frame: From peripheral intravenous catheter insertion until catheter removal or up to 7 days after insertion, whichever occurs first
Performance of the AI-Based Prediction Model
Photographs of peripheral intravenous catheter-related phlebitis sites will be captured in real time using a mobile phone from patients diagnosed with phlebitis. After the required number of images has been collected from all patients, the images will be graded by expert nurses and a physician using the Visual Infusion Phlebitis Scale (range 0 to 5; 0 = healthy intravenous site, 5 = advanced stage thrombophlebitis; higher scores indicate a worse outcome). The labeled dataset will then be divided into training, validation, and test sets. A deep learning model will be developed using the training and validation sets, and the final performance of the model will be determined on the test set using sensitivity, specificity, accuracy, precision, recall, and F1-score (each ranging from 0 to 1; higher values indicate better performance), and calibration.
Time frame: Up to 14 months
Ran from Jul 2025 to primary completion in Feb 2026, 7 months.
How these figures are worked out, and which studies are left out of them.
From the registry record's own update history. This site started tracking changes on Sep 25, 2026; for anything earlier, see the record history on ClinicalTrials.gov ↗
This study is completed, as verified in Jul 2025. You cannot join it, but the record below documents what was studied.
Get an email when the registry record changes — status, dates, results — or when someone posts here.
Sign in to followQuestions and observations about this study, from anyone following it. Not medical advice, and not a channel to the study team — their contact details are on the registry record.
Sign in to join the discussion. Reading takes no account; posting does. You choose a display name, and a pseudonym is the default.
Nothing here yet. If you are running this trial, taking part in it, or weighing whether to, this is the place to say so.
Kutahya Health Sciences University →