clinical study

How artificial intelligence improves radiological interpretation in suspected pulmonary embolism

Materials & Methods

A retrospective multicentric study including patients with suspected PE from Sept. to Dec. 2019 (i.e., during a preliminary evaluation period of an approved AI algorithm). CTPA quality and conclusions by emergency radiologists were retrieved from radiological reports. The gold standard was a retrospective review of CTPA, radiological and clinical reports, AI outputs, and patient outcomes. Diagnostic performance metrics for AI and radiologists were assessed in the entire cohort and depending on CTPA quality.


1,202 patients were included. PE prevalence was 15.8% (190/1202). The AI algorithm detected 219 suspicious PEs, of which 176 were true PEs, including 19 true PEs missed by radiologists. In the cohort, the highest sensitivity and negative predictive values (NPVs) were obtained with AI (92.6% versus 90% and 98.6% versus 98.1%, respectively), while the highest specificity and positive predictive value (PPV) were found with radiologists (99.1% versus 95.8% and 95% versus 80.4%, respectively). Accuracy, specificity, and PPV were significantly higher for radiologists except in subcohorts with poor-to-average injection quality. Radiologists positively evaluated the AI algorithm to improve their diagnostic comfort (55/79 [69.6%]).


The AI algorithm showed excellent performance in diagnosing PE on CTPA (sensitivity and specificity 92.6% and 95.8%; accuracy ≥ 95%) and increased the sensitivity and NPV of emergency radiologists in clinical practice, especially in cases of poor-to-moderate injection quality.

Explore the Latest AI Insights, Trends and Research