14467
>
clinical study

Reducing Exam-to-Needle Time in Pulmonary Embolism Thrombectomy Using an AI-Based Mobile Alert System

Materials & Methods
This single-center retrospective study evaluated patients undergoing percutaneous thrombectomy for acute pulmonary embolism (PE) before and after implementation of an AI-based mobile alert (Aidoc, Tel Aviv, Israel). The system provided automated PE detection and real-time notifications to the Pulmonary Embolism Response Team (PERT). Exam-to-needle time — defined as the interval from CT diagnosis to thrombectomy start—  was compared between the pre-alert (2019–2020) and post-alert (2023–2024) periods.

Results
Seventy-seven patients were included: 38 pre-alert and 39 post-alert. The mean exam-to-needle time significantly decreased from 148 to 119 minutes following AI alert implementation (p = 0.028). Although subgroup analysis by risk category (high versus intermediate-high) didn’t reach statistical significance, a consistent trend toward faster intervention was observed.

Conclusions
The AI-driven mobile alert system significantly reduced exam-to-needle time for PE thrombectomy. These findings suggest improved coordination between radiology, interventional and critical care teams, enhancing responsiveness and workflow efficiency in acute PE management.

Disclaimer: This links to a third-party website, which may require credentials to review.

Explore the Latest AI Insights, Trends and Research