Automated real-time detection of lung sliding using artificial intelligence: a prospective diagnostic accuracy study.

BACKGROUND: Rapid evaluation for pneumothorax (PTX) is a common clinical priority. Although lung ultrasound (LUS) is often used to assess for PTX, its diagnostic accuracy varies based on patient and provider factors. To enhance the performance of LUS for pulmonary pathology, artificial intelligence (AI) assisted imaging has been adopted, however, the diagnostic accuracy of AI-Assisted LUS (AI-LUS) deployed in real-time to diagnose PTX remains unknown.

RESEARCH QUESTION: In patients with suspected PTX, what is the real-time diagnostic accuracy of AI-LUS to recognize the absence of lung sliding?

STUDY DESIGN AND METHODS: We performed a prospective AI-assisted diagnostic accuracy study of AI-LUS to recognize the absence of lung sliding in a convenience sample of patients with suspected pneumothorax. After calibrating the model parameters and imaging settings for bedside deployment, we prospectively evaluated its diagnostic accuracy for lung sliding compared to a reference standard of expert consensus.

RESULTS: 241 lung sliding evaluations were derived from 62 patients. AI-LUS had a sensitivity of 0.921 (95% CI 0.792, 0.973), specificity of 0.802 (95% CI 0.735 - 0.856), area under the curve of the receiver operating characteristic (AUC) of 0.885 (95% CI 0.828, 0.956), and accuracy of 0.824 (95% CI 0.766 - 0.870) for the diagnosis of absent lung sliding.

INTERPRETATION: Real-time AI-LUS has high sensitivity and moderate specificity to identify the absence of lung sliding. Further research to improve model performance and optimize the integration of AI-LUS into existing diagnostic pathways is warranted.

CLINICAL TRIAL REGISTRATION: N/A.