Prospective Silent Evaluation of AI for Retained Foreign Object Detection
ConditionRetained Foreign Object
Trial statusRecruiting
Trial phaseNot listed
Trial typeObservational
Biological sexAll
Age18+
SponsorUniversity of Colorado, Denver
About this trial
Retained foreign objects, such as surgical sponges, needles, or instruments, are rare but potentially serious complications of surgery. When there is concern that an object may have been left behind, an intraoperative radiograph may be obtained while the patient is still in the operating room. These radiographs can be difficult to interpret because of overlapping surgical equipment, patient positioning, and the need for rapid interpretation.
This prospective observational study evaluates an artificial intelligence (AI) system designed to detect retained foreign objects on intraoperative radiographs. Eligible radiographs obtained during routine clinical care will be automatically processed by the AI system in real time for approximately one year. The AI results will not be shown to radiologists, surgeons, or other members of the clinical care team and will not affect patient care.
The study will evaluate how accurately the AI system detects retained foreign objects and how reliably and quickly the system operates in a real-world clinical environment.
Eligibility criteria
This trial does not accept healthy volunteersQualifiers
Age 18 years or older.
Undergoing intraoperative radiography during routine clinical care for evaluation of a possible retained foreign object.
Radiographic examination identified using the institutional OR count imaging protocol, including "XR OR COUNT PROTOCOL W/WO POSITIVE CONTROL" or an equivalent institutional protocol label used for OR count imaging during the study period.
Disqualifiers
Radiographic examination lacking usable imaging data.
Insufficient clinical or imaging information to establish an adequate reference standard for analysis.
Trial population
The study population consists of consecutive adult patients undergoing intraoperative OR count radiography as part of routine clinical care at University of Colorado/UCHealth. Eligible examinations are prospectively identified using institutional OR count imaging protocol labels and processed by the AI system in real time. AI outputs are collected for research purposes only and are not shown to the clinical care team or used to guide patient management.
Trial design
Design model
Cohort
Time perspective
Prospective
Treatments tested in this trial
Not listed
Trial groups
120 Participants
are grouped into 1 trial groupGroup A: Silent AI Analysis of OR Count Radiographs
Trial outcomes
Primary outcomes
1
Sensitivity of the AI System for Retained Foreign Object Detection
Sensitivity will be calculated as the proportion of reference-standard positive examinations containing a retained foreign object that are correctly identified as positive by the AI system. The reference standard will be established using available clinical information, including finalized radiology reports, operative documentation, follow-up imaging when available, and expert adjudication of discordant cases when needed.
Time frame
Through completion of the 12-month prospective study periodSecondary outcomes
1
Specificity of the AI System for Retained Foreign Object Detection
Specificity will be calculated as the proportion of reference-standard negative examinations without a retained foreign object that are correctly identified as negative by the AI system.
Time frame
Through completion of the 12-month prospective study period2
Area Under the Receiver Operating Characteristic Curve for RFO Detection
The area under the receiver operating characteristic curve (AUROC) will be calculated using AI-generated detection scores and the reference-standard classification of examinations as positive or negative for a retained foreign object. AUROC ranges from 0 to 1, with higher values indicating greater discrimination between positive and negative examinations.
Time frame
Through completion of the 12-month prospective study period3
System Latency
System latency will be measured as the elapsed time between availability of an eligible radiographic examination for processing and availability of the corresponding AI output. Latency will be summarized across prospectively processed examinations to evaluate operational feasibility in the real-world clinical workflow.
Time frame
Through completion of the 12-month prospective study period4
Diagnostic Accuracy of the AI System for Retained Foreign Object Detection
Diagnostic accuracy will be calculated as the proportion of all prospectively evaluated examinations that are correctly classified by the AI system as positive or negative for a retained foreign object compared with the reference standard.
Time frame
Through completion of the 12-month prospective study periodSponsors and contacts
Click on the lead sponsor to view all of their trials.
Source ClinicalTrials.gov