Diagnostic accuracy of a commercially available deep-learning algorithm in supine chest radiographs following trauma.

Jacob Gipson¹, Victor Tang^1,2, Jarrel Seah^1,3, Helen Kavnoudias^1,4, Adil Zia¹, Robin Lee¹, Biswadev Mitra^5,6,7, Warren Clements^1,4,5

¹Department of Radiology, Alfred Health, Melbourne, Victoria, Australia.

²Faculty of Medicine, University of Queensland, Brisbane, Queensland, Australia.

³Harrison.ai, Sydney, NSW, Australia.

⁴Department of Surgery, Monash University, Melbourne, Victoria, Australia.

⁵National Trauma Research Institute, Melbourne, Victoria, Australia.

⁶Emergency & Trauma Centre, The Alfred Hospital, Melbourne, Victoria, Australia.

⁷School of Public Health & Preventive Medicine, Monash University, Melbourne, Victoria, Australia.

PubMed PMC DOI PDF

Abstract

OBJECTIVES: Trauma chest radiographs may contain subtle and time-critical pathology. Artificial intelligence (AI) may aid in accurate reporting, timely identification and worklist prioritisation. However, few AI programs have been externally validated. This study aimed to evaluate the performance of a commercially available deep convolutional neural network - Annalise CXR V1.2 (Annalise.ai) - for…

Create a free account to keep reading

Free members get 10 full research views every month across publications, clinical trials, FDA clearances, adverse events, and NIH grants. No credit card required.

Create Free Account Sign In

Want unlimited research access? See Pro plans

Data Accuracy Notice: Research intelligence on Health AI Central is aggregated from public sources (PubMed, ClinicalTrials.gov, FDA, NIH, CMS, and others) and refreshed nightly. Classifications and derived metrics are produced by automated methods described in our Methodology. We recommend verifying critical data points against the primary sources before making decisions.