Natural language processing system boosts IVC filter clinic scheduling and retrieval in clinical integration study

An NLP-based alert system (FAS) integrated into CT reporting achieved 99.7% accuracy for identifying IVC filter patients and increased eligible patients scheduled for clinic from 21.6% to 58.0% and filter retrieval from 21.6% to 44.0%.

• FAS had high accuracy (99.7%), sensitivity (85.7%), specificity (99.9%), and PPV (94.7%) on CT reports.
• Post-integration, significantly more eligible patients were scheduled for clinic (58.0% vs 21.6%) and filter retrieval (44.0% vs 21.6%), with similar complication rates.
• Mean filter dwell times were similar between pre- and post-FAS groups (38.9 vs 65.6 months).

Automated summary

RadPigeon summaries are original and for information only. They are not clinical advice.