• Jan Rudolph, Christian Huemmer, Alexander Preuhs, Guiulia Buizza, Boj F Hoppe, Julien Dinkel, Vanessa Koliogiannis, Nicola Fink, Sophia S Goller, Vincent Schwarze, Nabeel Mansour, Vanessa F Schmidt, Maximilian Fischer, Maximilian Jörgens, Najib Ben Khaled, Thomas Liebig, Jens Ricke, Johannes Rueckel, and Bastian O Sabel.
• Department of Radiology, University Hospital, LMU Munich, Munich, Germany. Electronic address: jan.rudolph@med.uni-muenchen.de.
• Chest. 2024 Jan 29.

BackgroundChest radiographs (CXRs) are still of crucial importance in primary diagnostics, but their interpretation poses difficulties at times.Research QuestionCan a convolutional neural network-based artificial intelligence (AI) system that interprets CXRs add value in an emergency unit setting?Study Design And MethodsA total of 563 CXRs acquired in the emergency unit of a major university hospital were retrospectively assessed twice by three board-certified radiologists, three radiology residents, and three emergency unit-experienced nonradiology residents (NRRs). They used a two-step reading process: (1) without AI support (woAI); and (2) with AI support (wAI) providing additional images with AI overlays. Suspicion of four suspected pathologies (pleural effusion, pneumothorax, consolidations suspicious for pneumonia, and nodules) was reported on a five-point confidence scale. Confidence scores of the board-certified radiologists were converted into four binary reference standards (RFS I-IV) of different sensitivities. Performance by radiology residents and NRRs woAI/wAI were statistically compared by using receiver-operating characteristics (ROCs), Youden statistics, and operating point metrics derived from fitted ROC curves.ResultsNRRs could significantly improve performance, sensitivity, and accuracy wAI in all four pathologies tested. In the most sensitive RFS IV, NRR consensus improved the area under the ROC curve (mean, 95% CI) in the detection of the time-critical pathology pneumothorax from 0.846 (0.785-0.907) woAI to 0.974 (0.947-1.000) wAI (P < .001), which represented a gain of 30% in sensitivity and 2% in accuracy (while maintaining an optimized specificity). The most pronounced effect was observed in nodule detection, with NRR wAI improving sensitivity by 53% and accuracy by 7% (area under the ROC curve woAI, 0.723 [0.661-0.785]; wAI, 0.890 [0.848-0.931]; P < .001). The RR consensus wAI showed smaller, mostly nonsignificant gains in performance, sensitivity, and accuracy.InterpretationIn an emergency unit setting without 24/7 radiology coverage, the presented AI solution features an excellent clinical support tool to nonradiologists, similar to a second reader, and allows for a more accurate primary diagnosis and thus earlier therapy initiation.Copyright © 2024 The Author(s). Published by Elsevier Inc. All rights reserved.

4 keywords...

hide…