Impact of AI-Triage on Radiologist Report Turnaround Time: Real-World Time-Savings and Insights from Model Predictions

2025-10-16

AI Summary

This study evaluates the impact of an AI triage system on turnaround time (TAT) for pulmonary embolism (PE) reporting in chest CT pulmonary angiography (CTPA). Method: A retrospective cohort design integrates real-world PACS workflow data with computational modeling, uniquely incorporating clinical temporal factors (i.e., working vs. non-working hours), examination priority rules, and human–AI collaboration parameters into the AI triage performance model. Contribution/Results: During working hours, AI triage significantly reduced median TAT by 22.2 minutes (p < 0.05), with strong concordance between modeled predictions and empirical measurements; no significant improvement was observed during non-working hours. The study introduces the first quantitative framework for assessing AI triage benefit that explicitly models dynamic radiology workflow characteristics. This advances the accuracy and contextual fidelity of clinical AI deployment impact prediction, establishing a methodological paradigm and empirical foundation for AI-driven optimization of diagnostic imaging workflows.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Humans and AI: Planning and Decision Support for Human-Machine Teams
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Objective: To quantify the impact of workflow parameters on time-savings in report turnaround time (TAT) due to an AI-triage device that prioritized pulmonary embolism (PE) in chest CT pulmonary angiography (CTPA) exams. Methods: This retrospective study analyzed 11252 adult CTPA exams conducted for suspected PE at a single tertiary academic medical center. Data was divided into two periods: pre-AI and post-AI. For PE-positive exams, TAT - defined as the duration from patient scan completion to the first preliminary report completion - was compared between the two periods. Time-savings were reported separately for work-hour and off-hour cohorts. To characterize radiologist workflow, 527234 records were retrieved from the PACS and workflow parameters such as exam inter-arrival time and radiologist read-time extracted. These parameters were input into a computational model to predict time-savings following deployment of an AI-triage device and to study the impact of workflow parameters. Results: The pre-AI dataset included 4694 chest CTPA exams with 13.3% being PE-positive. The post-AI dataset comprised 6558 exams with 16.2% being PE-positive. The mean TAT for pre-AI and post-AI during work hours are 68.9 [95% CI" 55.0, 82.8] and 46.7 [38.1, 55.2] minutes respectively, and those during off-hours are 44.8 [33.7, 55.9] and 42.0 [33.6, 50.3] minutes. Clinically-observed time-savings during work hours (22.2 [95% CI: 5.85, 38.6] minutes) were significant (p=0.004), while off-hour (2.82 [-11.1, 16.7] minutes) were not (p=0.345). Observed time-savings aligned with model predictions (29.6 [95% range: 23.2, 38.1] minutes for work hours; 2.10 [1.76, 2.58] minutes for off-hours). Discussion: Consideration and quantification of clinical workflow contribute to an accurate assessment of the expected time-savings in TAT following deployment of an AI-triage device.

Problem

• Quantifying AI triage impact on radiologist report turnaround time
• Analyzing workflow parameters affecting time-savings for pulmonary embolism detection
• Comparing model predictions with real-world clinical time-savings observations

Innovation

• AI-triage device prioritizes pulmonary embolism in CTPA exams
• Computational model predicts time-savings using workflow parameters
• Retrospective analysis compares pre-AI and post-AI report turnaround times