Automated Real-Time Detection of Lung Sliding Using Artificial Intelligence: A Prospective Diagnostic Accuracy Study

Hans Clausdorff Fiedler; Ross Prager; Delaney Smith; Derek Wu; Chintan Dave; Jared Tschirhart; Ben Wu; Blake Van Berlo; Richard Malthaner; Robert Arntfield

doi:10.1016/j.chest.2024.02.011

Automated Real-Time Detection of Lung Sliding Using Artificial Intelligence: A Prospective Diagnostic Accuracy Study

Chest. 2024 Feb 15:S0012-3692(24)00157-0. doi: 10.1016/j.chest.2024.02.011. Online ahead of print.

Authors

Affiliations

¹ Sección de Medicina de Urgencia, Pontificia Universidad Católica de Chile, Santiago, Chile. Electronic address: hjclausd@uc.cl.
² Division of Critical Care Medicine, Western University, London, ON, Canada.
³ Lawson Health Research Institute, London, ON, Canada.
⁴ Departments of Surgery, Oncology, and Epidemiology and Biostatistics, Schulich School of Medicine, Western University, London, ON, Canada.
⁵ Faculty of Mathematics, University of Waterloo, Waterloo, ON, Canada.
⁶ Division of Thoracic Surgery, Western University, London, ON, Canada.

PMID: 38365174
DOI: 10.1016/j.chest.2024.02.011

Abstract

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

Research question: In patients with suspected pneumothorax, 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 with a reference standard of expert consensus.

Results: Two hundred forty-one lung sliding evaluations were derived from 62 patients. AI-LUS showed a sensitivity of 0.921 (95% CI, 0.792-0.973), specificity of 0.802 (95% CI, 0.735-0.856), area under the receiver operating characteristic curve 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 shows 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.

Keywords: artificial intelligence; lung sliding; lung ultrasound; pneumothorax.