Real-time x-ray abnormality alerts for emergency departments using a radiographer comment model - a multisite pilot...

Area of Science:

• Medical Imaging
• Radiology
• Emergency Medicine

Background:

• Effective communication of significant imaging findings to Emergency Departments (ED) is crucial for patient care.
• Current Australian reliance on verbal communication is limited, prone to misinterpretation, and lacks transparency.

Purpose of the Study:

• To design and pilot a model for real-time communication of image abnormalities to ED referrers.
• To assess the precision and reliability of radiographer comments in identifying significant findings.

Main Methods:

• A multidisciplinary group developed a radiographer alert and comment model for general ED imaging.
• Protocols were established for documenting critical, urgent, and significant comments, with direct communication for critical findings.
• Five hospitals piloted the model, with auditors comparing radiographer comments to radiology reports to calculate Positive Predictive Value (PPV) and False Positive (FP) rates.

Main Results:

• Radiographers provided comments for 1102 cases across five pilot sites.
• The pooled average PPV for true positives was 0.96 (95% CI: 0.947-0.971).
• The weighted mean error (FP comments) was low at 3.9% (95% CI: 2.9%-5.3%).

Conclusions:

• The radiographer comment model demonstrated consistent precision and reproducibility across diverse hospital settings.
• The low False Positive rate indicates the model's reliability in communicating clinically significant imaging information.