Artificial IntelligenceNCT07889895
AI Prediction of PIVC-Related Phlebitis
An observational study of Artificial Intelligence and Phlebitis After Infusion, run by Kutahya Health Sciences University at 2 sites in Turkey (Türkiye).
Trial summary
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. Read more about this study
- Who is it for?
- Ages 18 to 85 years
- Conditions the study is for
- Artificial Intelligence, Phlebitis After Infusion, Phlebitis
- What is being tested?
- Artificial Intelligence-Based Phlebitis Detection Model
- How many people
- 461 participants
- Where
- 2 sitesTurkey (Türkiye)
- Study dates
- 15 Jul 2025to 13 Sep 2026
- Phase
- Observational
- Are there results?
- None posted in the registry
Key requirements
Who can take part, as listed by the sponsor. Only the study team can confirm whether you are eligible, so take this list to your doctor.
- Ages 18 to 85 years
- All sexes
- No healthy volunteers
- Adult, Older adult
Study population: 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.
Who may be able to join
None listed.
Who cannot join
- 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.
Trial locations and contacts
2 sites in 1 country.
Turkey (Türkiye)2 sites
Kutahya Health Sciences University
Kütahya, Kütahya, 43020
Kutahya Health Sciences University
Merkez, Kütahya, 43000
About this study
Official title: Predicting Peripheral Intravenous Catheter-Related Phlebitis With AI-Based Models.
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.
Read the detailed description
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.
- Conditions
- Artificial Intelligence, Phlebitis After Infusion, Phlebitis
- Being tested
- Artificial Intelligence-Based Phlebitis Detection Model
- Keywords
- Peripheral Intravenous Catheter (PIVC), Phlebitis, Artificial Intelligence, Machine Learning, Prediction Model
- Medical subject headings
- Phlebitis
What participants receive
What participants receive. In a randomised study each person is assigned to one group by chance.
Artificial Intelligence-Based Phlebitis Detection ModelOther
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.
| Study group | Role | What they receive |
|---|---|---|
| Phlebitis Image Dataset | A single cohort consisting of images used to develop and evaluate a model for phlebitis prediction Receives: Other: Artificial Intelligence-Based Phlebitis Detection Model |
What is being measured
The primary outcome is the main question the study is designed to answer.
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.
Measured: 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.
Measured: Up to 14 months
Timeline
From the start of the study to its completion; the mark is today. Estimated dates are the sponsor’s plan.
- First posted22 Oct 2026
- Study start15 Jul 2025
- Primary completion15 Feb 2026
- Study completion13 Sep 2026
Resources
- Official record on ClinicalTrials.govThe registry entry this page is built from, with its full change history.
- Other trials for Artificial IntelligenceStudies of the same condition, open and under way.
- More trials run by Kutahya Health Sciences UniversityThe sponsor's other registered studies.
- What the trial phases meanHow a treatment moves from first tests in people to approval.
More details
For doctors and researchers: how the study is designed, who runs it, and its registry IDs.
Study design
- Study type
- Observational
- Observational model
- Cohort
- Time perspective
- Prospective
- Enrolment
- 461 participants (actual)
Sponsor and investigators
- Lead sponsor
- Kutahya Health Sciences University
- Sponsor type
- University, hospital or other
- Responsible party
- Sponsor
- Investigators
- BURCU NAL, Principal investigator, Kütahya Health Science University
IDs, dates and publications
- ClinicalTrials.gov ID
- NCT07889895
- Sponsor's protocol ID
- KutahyaHSU2026
- Status last verified
- Jul 2025
- First submitted
- 15 Sep 2026
- Last updated
- 22 Oct 2026
- Results posted
- No
- Data monitoring committee
- No
- FDA-regulated drug
- No
- FDA-regulated device
- No
Study at a glance
From the registry record, last updated by the sponsor on 22 Oct 2026. Recruitment status is as the sponsor reported it: confirm with the study team.
- Official title
- Predicting Peripheral Intravenous Catheter-Related Phlebitis With AI-Based Models.
- ClinicalTrials.gov ID
- NCT07889895
- Acronym / sponsor ID
- KutahyaHSU2026
- Conditions
- Artificial Intelligence, Phlebitis After Infusion, Phlebitis
- Keywords
- Peripheral Intravenous Catheter (PIVC), Phlebitis, Artificial Intelligence, Machine Learning, Prediction Model
- Study type
- Observational
- Recruitment status
- Completed
- Enrolment
- 461 participants (actual)
- Lead sponsor
- Kutahya Health Sciences UniversityUniversity, hospital or other
- Study start
- 15 Jul 2025 (actual)
- Primary completion
- 15 Feb 2026 (actual)
- Study completion
- 13 Sep 2026 (actual)
- First posted
- 22 Oct 2026 (actual)
- Results
- Not posted in the source record
Clinical summary
The research question as the sponsor registered it. This describes what the study plans to test, not what it found.
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.
Detailed description
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.
Study design
- Observational model
- Cohort
- Time perspective
- Prospective
- Number of arms
- 1
| Arm | Type | Receives |
|---|---|---|
| Phlebitis Image Dataset | – | Other: Artificial Intelligence-Based Phlebitis Detection ModelA single cohort consisting of images used to develop and evaluate a model for phlebitis prediction |
Who may qualify
- Ages
- 18 to 85 years
- Sex
- All
- Healthy volunteers
- Not accepted
- Age groups
- Adult, Older adult
- Study population
- 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.
Key inclusion criteria (0 listed)
Key exclusion criteria (5 listed)
- 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.
Eligibility is decided by the study team after screening; this overview does not establish that a patient qualifies. Full inclusion and exclusion criteria.
Interventions
| Intervention | Type | Arms |
|---|---|---|
| Artificial Intelligence-Based Phlebitis Detection ModelAn 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. | Other | Phlebitis Image Dataset |
Primary outcome
Peripheral Intravenous Catheter-Related Phlebitis Occurrence
Time frame: From peripheral intravenous catheter insertion until catheter removal or up to 7 days after insertion, whichever occurs first
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.
Performance of the AI-Based Prediction Model
Time frame: Up to 14 months
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.
Results and safety
The study is completed, but results are not available in the source record. That does not mean the treatment did or did not work.
Research links
- Official record on ClinicalTrials.govLast updated by the sponsor 22 Oct 2026.
Related trials for Artificial Intelligence
RecruitingObservational study
AI-powered ECG Analysis Using Willem™ Software in High-risk Cardiac Patients (WILLEM)
Cardiomyopathies, Cardiac Arrest
Recruiting
Managing Premyopia in Chinese Children Using Artificial Intelligence Assisted Defocus Incorporated Multiple Segments Based Spectacle Lens: a Randomized Controlled Clinical Trial
Pre-myopia, Myopia
Not yet recruitingObservational study
AI-assisted Tracheal Intubation in Children
Intubation
Recruiting
AI-assisted Home-based Intervention for ADHD Children
ADHD - Attention Deficit Disorder With Hyperactivity, ADHD - Combined Type
Not yet recruitingObservational study
Discovering Determinants of Food Intake by Application of Artificial Intelligence to Complex, High-Dimensional Data
Healthy Volunteer
Referral and contact
AzTrials does not enrol participants or take referrals. Contact the study team or a site listed below; they decide who can take part. This study is not recruiting at the moment.
BURCU NAL principal investigator
Kütahya Health Science University
2 sites in 1 country: see every site and its status.
Questions about this trial
What is this clinical trial studying?
An observational study of Artificial Intelligence and Phlebitis After Infusion, run by Kutahya Health Sciences University at 2 sites in Turkey (Türkiye).
The full registered description is in the About this study section and the official record.
Who may be eligible to take part?
The sponsor lists 0 inclusion and 5 exclusion criteria. Eligibility is decided by the study team after screening, so read the full criteria and contact a listed site.
Is this clinical trial currently recruiting?
The record says: finished, as of the sponsor's last update on 22 Oct 2026. Status can change between updates, so confirm with the study contact before making plans.
Where is the study taking place?
The record lists 2 sites in Turkey (Türkiye). Whether a site is taking part right now should be confirmed with that site. See every site.
What are the possible benefits and risks?
They depend on the study and the treatment, and no study can promise a benefit. The study team explains the known risks during informed consent, before anyone joins; the record itself does not list them.
Are results available for this study?
The study is completed, but results are not available in the source record. That does not mean the treatment did or did not work.
How can a doctor refer a patient or contact the research team?
The record lists no contact. The official record names the sponsor, who can be asked directly. AzTrials does not enrol participants or take referrals.
What does the primary outcome measure?
Peripheral Intravenous Catheter-Related Phlebitis Occurrence (time frame: From peripheral intravenous catheter insertion until catheter removal or up to 7 days after insertion, whichever occurs first). The study lists 2 primary outcomes in all. It is what the study was designed to measure, not a finding.
Where can I read the original study information?
Does a listing mean the treatment is approved or proven to work?
No. A listing means the study is registered. It does not show that the treatment is safe, works, or is approved by a regulator.
How often is this information updated?
AzTrials copies changed records from ClinicalTrials.gov every night and reloads the whole registry every week. The sponsor last updated this record on 22 Oct 2026.