Large academic institution cuts incidental pulmonary embolism radiologist wait time by 78% with Aidoc AI triage
“Large academic institution cuts incidental pulmonary embolism radiologist wait time by 78% with Aidoc AI triage” documents a Medical Imaging & Radiology deployment in Hospital & Health System at Large Academic Institution (unnamed). www.aidoc.com reports wait time reduction: 78%; this directory has not independently verified that result.
Evidence at a glance
- Evidence status:
- Automated evidence gate passed
- Deployment timeframe:
- Not reported by source
- Reported outcome metrics:
- 3 cited below
- Directory entry published:
- Source link checked:
The source-link check confirms reachability, not independent re-verification of every claim.
Source-reported figures — cited source: www.aidoc.com
The Challenge
Incidental pulmonary embolisms (iPE) detected on routine outpatient abdominal CT scans — which do not include dedicated chest imaging — faced prolonged wait times before radiologist review. Delayed identification of these potentially life-threatening findings risked delayed intervention for patients.
The Solution
Aidoc's AI-driven system was deployed to analyze 4,447 contrast-enhanced abdominal CT scans performed between January and July 2023. The system automatically flagged suspected iPE cases (3.2% of scans) and triggered priority notifications to radiologists, enabling faster triage without requiring dedicated chest CT protocols.
Results
AI-flagged cases achieved a median radiologist review wait time of 37.7 minutes, compared to 168.5 minutes for non-flagged cases — a 78% reduction. The study concluded that AI-triggered notifications significantly enhance workflow efficiency and expedite reporting of incidental PE, potentially enabling more timely clinical interventions.
Key Takeaways
- AI prioritization can dramatically reduce time-to-review for incidental, life-threatening findings identified outside their primary imaging protocol.
- Deploying AI on routine abdominal CT scans extends vascular detection coverage beyond dedicated PE imaging workflows.
- A 3.2% flag rate suggests the system targets a clinically meaningful subset without overwhelming radiologist queues with false positives.
Vendor
Details
- Industry
- Hospital & Health System
- Use Case
- Medical Imaging & Radiology
- AI Technology
- Computer Vision & Medical Imaging
- Company Size
- Enterprise
- Company
- Large Academic Institution (unnamed)
- Evidence status
- Automated evidence gate passed
- Deployment timeframe
- Not reported by source
- Directory entry published
- Source link checked
Cited source
www.aidoc.comHave a similar implementation?
Share your customer's AI results and link it to your vendor profile.
Submit a case study →