Diagnostic performance of an artificial intelligence algorithm for detecting pneumoperitoneum on abdominal CT scans.
Artificial intelligence algorithm detects pneumoperitoneum on CT scans with excellent accuracy
Diagnostic performance of an artificial intelligence algorithm for detecting pneumoperitoneum on abdominal CT scans.
This study aims to evaluate the diagnostic performance of an artificial intelligence (artificial intelligence) algorithm for detection, segmentation, and volumetric quantification of pneumoperitoneum on abdominal CT scans.
Multi-center CT imaging series from 2072 patients were collected and randomly divided into training and testing sets at an approximate 7:3 ratio.
AUC of 0.97 for detecting free air on CT; 1.0 is perfect, 0.5 is chance
In the external validation cohort (n = 214), the model maintained robust performance with sensitivity 84.3% (95% CI: 76.2-90.5%), specificity 89.6% (95% CI: 82.3-94.6%), accuracy 86.9% (81.6-91.2%), positive predictive value 89.2% (95% CI: 81.8-94.3%), and negative predictive value 84.8% (95% CI: 77.1-90.7%).
After excluding cases with minimal free gas (<1 mL), the model's sensitivity improved to 96%.
Artificial intelligence-derived volumes showed strong agreement with the reference standard (intraclass correlation coefficient 0.996, 95% CI: 0.994-0.997).
The artificial intelligence model attained high diagnostic accuracy for pneumoperitoneum on abdominal CT scans, promising to expedite emergency workflows.
KEY POINTS: Question Reliable artificial intelligence detection of pneumoperitoneum, particularly for small-volume free air, on emergency CT remains an unmet need for rapid and accurate emergency triage.
Findings The artificial intelligence model shows high sensitivity and specificity for clinically relevant pneumoperitoneum volumes, although trace-volume detection on CT scans remains challenging.