Related Experiment Video
Updated: Aug 6, 2026
05:33
Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System
Published on: July 11, 2025
Clinical integration of an inferior vena cava filter alert system using an artificial intelligence application
Josiah Hardy1, Omar Ahmed1, Ian Malinow1
1University of Maryland School of Medicine, Baltimore, MD, USA.
Clinical Imaging
|July 18, 2026
Summary
The Filter Alert System (FAS), using AI, improves identification and scheduling for inferior vena cava (IVC) filter removal. This leads to higher retrieval rates without increasing complications, enhancing patient safety.
Area of Science:
- Medical Informatics
- Radiology
- Artificial Intelligence in Medicine
Background:
- Inferior vena cava (IVC) filters require timely retrieval to prevent complications.
- Current methods for tracking patients with IVC filters can be inefficient.
Purpose of the Study:
- To evaluate the performance and clinical impact of the Filter Alert System (FAS).
- To assess if FAS improves the identification and retrieval of IVC filters.
Main Methods:
- Developed an AI-powered natural language processing (NLP) tool (FAS) to scan CT radiology reports for IVC filter mentions.
- Conducted a prospective study integrating FAS into clinical workflow for 9 months.
- Compared IVC filter retrieval rates and complication rates pre- and post-FAS integration.
Main Results:
- FAS demonstrated high accuracy (99.7%), sensitivity (85.7%), and specificity (99.9%).
- Post-FAS integration, eligible patients scheduled for clinic evaluation increased significantly (58.0% vs 21.6%).
- Subsequent IVC filter retrieval rates also significantly increased (44.0% vs 21.6%) with similar complication rates.
Conclusions:
- The Filter Alert System (FAS) is effective for clinical integration.
- FAS promotes active surveillance of patients with IVC filters, improving management and safety.
