An Informatics Approach to Facilitate Clinical Management of Patients With Retrievable Inferior Vena Cava Filters

Inferior Vena Cava Filters and Complications: A Systematic Review

Inferior vena cava (IVC) filters have been used since the 1960s to treat patients with acute risk of pulmonary embolism (PE) to prevent migration of thrombus by trapping it within the filter. Traditional usage has been in patients with contraindication to anticoagulation that carry a significant mortality risk. In this systematic review, we sought to evaluate complications associated with placement of inferior vena cava filters based on published data from the past 20 years. A search was performed on October 6th, 2022, in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines for systematic reviews, using three databases (ProQuest, PubMed and ScienceDirect) for articles published between the dates of February 1, 2002 and October 1, 2022. Results were filtered to include full-text, clinical studies, and randomized trials written in English pertaining to keywords "IVC filter AND complications", "Inferior Vena Cava Filter AND complications", "IVC filter AND thrombosis" and "Inferior Vena Cava Filter AND thrombosis". Articles identified by the three databases were pooled and further screened for relevance based on inclusion and exclusion criteria. Initial search results yielded 33,265 hits from all three databases combined. Screening criteria were applied, with 7721 results remaining. After further manual screening, including removal of duplicate hits, a total of 117 articles were selected for review. While there are no consensus guidelines for best practice, there is compelling evidence that IVC filters can provide significant protection against PE with minimal complications if the treatment window is appropriate. Increase in the variety of filter models has led to broader availability, but skepticism remains about their efficacy and safety, with ongoing controversy surrounding appropriate indications. Further research is needed to establish clear guidelines on appropriate indications for IVC placement and to determine time course of complications versus benefits for indwelling filters.

Automated detection of IVC filters on radiographs with deep convolutional neural networks

PURPOSE

To create an algorithm able to accurately detect IVC filters on radiographs without human assistance, capable of being used to screen radiographs to identify patients needing IVC filter retrieval.

METHODS

A primary dataset of 5225 images, 30% of which included IVC filters, was assembled and annotated. 85% of the data was used to train a Cascade R-CNN (Region Based Convolutional Neural Network) object detection network incorporating a pre-trained ResNet-50 backbone. The remaining 15% of the data, independently annotated by three radiologists, was used as a test set to assess performance. The algorithm was also assessed on an independently constructed 1424-image dataset, drawn from a different institution than the primary dataset.

RESULTS

On the primary test set, the algorithm achieved a sensitivity of 96.2% (95% CI 92.7-98.1%) and a specificity of 98.9% (95% CI 97.4-99.5%). Results were similar on the external test set: sensitivity 97.9% (95% CI 96.2-98.9%), specificity 99.6 (95% CI 98.9-99.9%).

CONCLUSION

Fully automated detection of IVC filters on radiographs with high sensitivity and excellent specificity required for an automated screening system can be achieved using object detection neural networks. Further work will develop a system for identifying patients for IVC filter retrieval based on this algorithm.

Analysis of Costs and Payments for Inferior Vena Cava Filter Retrieval in the Medicare Population

Over the past decade, inferior vena cava (IVC) filter retrieval has been increasing, in part due to Food and Drug Administration recommendations and legal pressure. The costs and margin of IVC filter removal are poorly understood. Medicare claims data from 2016 for the 103 highest volume centers for IVC filter retrieval were examined. Pooled mean charges, costs, payments, and margin were calculated by institution. Mean ± SD charges, costs, and payments were $14,138.00 ± $8,400.48, $3,693.28 ± $2,294.27, and $1,949.82 ± $702.91, respectively. Average (range) margin was -$1,706.18 (-$7,509.93 to $362.77). The margin was negative in 99 of the 103 (96%) institutions evaluated. The most significant contributors to the total procedure cost were operating room, supplies, and recovery (44.5%, 23.5%, and 10.4%, respectively). While IVC filter retrieval is often medically indicated, it is typically associated with a financial loss under current reimbursement structure.

Role of Inferior Vena Cava Filter Retrieval in Patients on Chronic Anticoagulation Therapy

Purpose of review

Describe the role of inferior vena cava filter (IVCF) retrieval in patients on chronic anticoagulation given the overlap of these treatment options in the management of patients with venous thromboembolic disease.

Recent findings

Despite the increase in IVCF retrievals since the Food and Drug Administration safety communications in 2010 and 2014, retrieval rates remain low. Previous studies have shown that longer filter dwell times are associated with greater risk for filter complications and more difficulty with filter retrievals. Recent findings suggest that complications are more frequent in the first 30 days after placement.

Summary

The decision to retrieve an optional IVCF is individualized and requires diligent follow-up with consistent re-evaluation of the need for the indwelling IVCF, particularly in those on long-term anticoagulation therapy.