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

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 detection of traumatic injuries on supine chest radiographs. Methods: Chest radiographs with a CT performed within 24 h in the setting of trauma were retrospectively identified at a level one adult trauma centre between January 2009 and June 2019. Annalise.ai assessment of the chest radiograph was compared to the radiologist report of the chest radiograph. Contemporaneous CT report was taken as the ground truth. Agreement with CT was measured using Cohen’s κ and sensitivity/specificity for both AI and radiologists were calculated. Results: There were 1404 cases identified with a median age of 52 (IQR 33–69) years, 949 male. AI demonstrated superior performance compared to radiologists in identifying pneumothorax (p = 0.007) and segmental collapse (p = 0.012) on chest radiograph. Radiologists performed better than AI for clavicle fracture (p = 0.002), humerus fracture (p < 0.0015) and scapula fracture (p = 0.014). No statistical difference was found for identification of rib fractures and pneumomediastinum. Conclusion: The evaluated AI performed comparably to radiologists in interpreting chest radiographs. Further evaluation of this AI program has the potential to enable it to be safely incorporated in clinical processes. Advances in knowledge: Clinically useful AI programs represent promising decision support tools.

Telehealth consultation before inter‐hospital transfer after falls in a subacute hospital (the PREVENT‐2 study)

“…Increased availability of CT scanning and clinical and artificial intelligence tools that can assess radiology images in real-time has the potential to further reduce times to clearance of cervical spines. 26,27 Efforts to translate this evidence to practice should consider the limitations of remote assessment and the present study. Patients in the present study were within a hospital environment where the mechanism of injury was low falls.…”

“…The primary contributors to delays in clearance are the availability of a CT scan, particularly overnight and reporting of the scan. Increased availability of CT scanning and clinical and artificial intelligence tools that can assess radiology images in real‐time has the potential to further reduce times to clearance of cervical spines 26,27 …”

Deep learning for pneumothorax diagnosis: a systematic review and meta-analysis

“…Among the 63 studies, 56 studies identified pneumothorax on chest radiography [ 26 – 81 ], four studies on computed tomography [ 82 – 85 ], one study on ECG [ 86 ], one study used chest radiography and photography using a smartphone [ 87 ], and one study used chest radiography and tabular data [ 88 ]. Six studies developed and internally tuned DLs [ 37 , 52 , 63 , 67 , 74 , 76 ], 25 studies also internally tested their DLs [ 32 , 33 , 35 , 38 , 40 , 41 , 43 , 45 , 47 , 48 , 50 , 55 , 60 , 65 , 69 , 70 , 73 , 75 , 79 – 83 , 85 , 86 ] and 32 studies externally tested the DLs [ 26 – 31 , 34 , 36 , 39 , 42 , 44 , 46 , 49 , 51 , 53 , 54 , 56 – 59 , 61 , 62 , 64 , 66 , 68 , 71 , 72 , 77 , 78 , 84 , 87 , 88 ].…”

“…In studies that performed external model validation, the median dataset size was 1137 (range 175–112 120). 17 studies included localisation of pneumothorax in model output to improve end-user interpretability [ 26 – 28 , 30 – 33 , 36 – 38 , 40 , 47 , 56 , 59 , 68 , 84 , 85 ]. Detailed DL characteristics are shown in supplementary table S3 .…”

“…We extracted 89 contingency tables from 32 studies that provided sufficient information to calculate contingency tables for pneumothorax classification [ 27 – 36 , 38 , 39 , 42 – 46 , 48 , 51 , 53 – 56 , 58 , 61 , 68 , 70 , 71 , 75 , 78 , 80 , 87 ]. 68 contingency tables were extracted for reported DL performance and 21 contingency tables were extracted for physician performance.…”