AI-Based Analysis of Port Catheter Tip Position

NCT07791875 | Not Yet Recruiting

• 1 other identifier: E-10840098-50.04-1975
• Study Type: observational
• Target: 100
• Locations: 1 country
• Sites: 1

Brief Summary

This prospective, single-center observational study will evaluate the performance of an artificial intelligence (AI)-based automated image-analysis method that will be developed, internally tested, and locked before prospective enrollment. The method will estimate the position of totally implantable venous access port catheter tips in adults undergoing right internal jugular vein port implantation as part of routine care. The automated estimate will be compared with a prespecified manual measurement method. Reference measurements of the catheter tip and the cavoatrial junction will be obtained from clinically indicated chest computed tomography images when both structures are visible. No additional chest radiography or computed tomography will be performed for research purposes, and the automated output will not guide catheter placement or alter clinical decisions. The primary performance measure will be the mean absolute error of the automated estimate in the prospective cohort.

Conditions

Vascular Access Devices

Keywords

Port Catheter; Deep Learning; Cavoatrial Junction; Chest Radiography; Computed Tomography

Outcome Measures

Primary Outcomes (1)

• Mean Absolute Error of Catheter Advancement Length Estimated by the AI-Based Automated A+B+Delta Method

  Mean absolute error (MAE), in millimeters, will be calculated as the arithmetic mean of the absolute differences between the catheter advancement length estimated by the locked AI-based automated A+B+Delta method and the reference catheter advancement length derived from the first eligible post-implantation noncontrast chest computed tomography examination. The analysis population will include participants with both a valid automated output and an evaluable reference measurement. Lower values indicate smaller estimation error. A 95% confidence interval will be estimated using 10,000 participant-level bias-corrected and accelerated bootstrap resamples.

  At the first eligible post-implantation noncontrast chest computed tomography examination obtained during routine care, before any documented catheter manipulation or revision

Secondary Outcomes (20)

• Median Absolute Error of Catheter Advancement Length Estimated by the AI-Based Automated A+B+Delta Method

  At the first eligible post-implantation noncontrast chest computed tomography examination obtained during routine care, before any documented catheter manipulation or revision

• Root Mean Squared Error of Catheter Advancement Length Estimated by the AI-Based Automated A+B+Delta Method

  At the first eligible post-implantation noncontrast chest computed tomography examination obtained during routine care, before any documented catheter manipulation or revision

• Mean Signed Error of Catheter Advancement Length Estimated by the AI-Based Automated A+B+Delta Method

  At the first eligible post-implantation noncontrast chest computed tomography examination obtained during routine care, before any documented catheter manipulation or revision

• Mean Paired Difference in Absolute Error Between the AI-Based Automated A+B+Delta and Manual A+B Methods

  At the first eligible post-implantation noncontrast chest computed tomography examination obtained during routine care, before any documented catheter manipulation or revision

• Proportion of AI-Based Automated A+B+Delta Estimates With Absolute Error Within 10 mm

  At the first eligible post-implantation noncontrast chest computed tomography examination obtained during routine care, before any documented catheter manipulation or revision

Other Outcomes (2)

• Huber Regression Slope for the Association Between the Port Implantation-to-CT Interval and Signed Error

  At the first eligible post-implantation noncontrast chest computed tomography examination obtained during routine care, before any documented catheter manipulation or revision

• Huber Regression Slope for the Association Between the Port Implantation-to-CT Interval and Absolute Error

  At the first eligible post-implantation noncontrast chest computed tomography examination obtained during routine care, before any documented catheter manipulation or revision

Study Arms (1)

Prospective Port Catheter Cohort

Adults aged 18 years or older undergoing totally implantable venous access port implantation through the right internal jugular vein as part of routine clinical care will be enrolled in a single prospective observational cohort. In each evaluable participant, the locked AI-based automated A+B+Delta method and the prespecified manual A+B measurement method will be assessed using reference measurements from clinically indicated post-implantation noncontrast chest computed tomography. No research-specific imaging will be performed, and the automated output will not guide port implantation or alter clinical decisions.

Diagnostic Test: AI-Based Automated Image Analysis; Diagnostic Test: Manual A+B Measurement Method

Interventions

AI-Based Automated Image Analysis DIAGNOSTIC_TEST

The locked automated method will use chest radiographic image analysis and a patient-specific Delta adjustment to estimate port catheter tip position. The method will be evaluated offline using reference measurements derived from clinically indicated post-implantation noncontrast chest computed tomography. Its output will not be provided to the clinical team and will not guide port implantation or alter clinical decisions.

Prospective Port Catheter Cohort

Manual A+B Measurement Method DIAGNOSTIC_TEST

The prespecified manual A+B method will estimate port catheter tip position using surface and chest radiographic measurements. It will be applied as a comparator in the same participants. The manual research measurement will not guide port implantation or alter clinical care.

Prospective Port Catheter Cohort

Eligibility Criteria

• Age: 18 Years+
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

Adults aged 18 years or older scheduled for totally implantable venous access port placement through the right internal jugular vein at Bagcilar Training and Research Hospital will be screened consecutively for a single-center prospective observational cohort. Participants will enter the enrolled cohort after written informed consent and confirmation of the participant-level eligibility criteria. Availability and evaluability of a clinically indicated post-implantation noncontrast chest computed tomography examination, absence of documented catheter manipulation or revision before the selected examination, and generation of a valid automated output will define the relevant analysis populations and will not be prerequisites for enrollment. No imaging will be performed solely for research purposes.

You may qualify if:

• Age 18 years or older.
• Planned placement of a totally implantable venous access port through the right internal jugular vein as part of routine clinical care.
• Availability of a suitable pre-implantation chest radiograph obtained as part of routine clinical care.
• Provision of written informed consent.

You may not qualify if:

• Age younger than 18 years.
• Cancellation of the routine clinical port implantation plan.
• Planned or performed port placement through a venous access route other than the right internal jugular vein.
• No suitable pre-implantation chest radiograph available for study assessment.
• Advanced thoracic deformity or mediastinal distortion precluding the required study measurements.
• Inability or unwillingness to provide written informed consent.

Sponsors & Collaborators

• Bagcilar Training and Research Hospital: lead

Study Sites (1)

Bagcilar Training and Research Hospital

Bağcılar, Istanbul, 34200, Turkey (Türkiye)

Location

Central Study Contacts

Balamir Utku Seker

CONTACT

+90 539 433 79 62; b.utku.seker@gmail.com

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: PROSPECTIVE
• Sponsor Type: OTHER GOV
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: August 24, 2026
• First Posted: August 28, 2026
• Study Start (Estimated): October 5, 2026
• Primary Completion (Estimated): January 1, 2027
• Study Completion (Estimated): February 1, 2027
• Last Updated: August 28, 2026

Record last verified: 2026-08

Locations

TU (1)