How Can a Deep Learning Algorithm Improve Fracture Detection on X-rays in the Emergency Room?

Abstract

The growing need for emergency imaging has greatly increased the number of conventional X-rays, particularly for traumatic injury. Deep learning (DL) algorithms could improve fracture screening by radiologists and emergency room (ER) physicians. We used an algorithm developed for the detection of appendicular skeleton fractures and evaluated its performance for detecting traumatic fractures on conventional X-rays in the ER, without the need for training on local data. This algorithm was tested on all patients (N = 125) consulting at the Louis Mourier ER in May 2019 for limb trauma. Patients were selected by two emergency physicians from the clinical database used in the ER. Their X-rays were exported and analyzed by a radiologist. The prediction made by the algorithm and the annotation made by the radiologist were compared. For the 125 patients included, 25 patients with a fracture were identified by the clinicians, 24 of whom were identified by the algorithm (sensitivity of 96%). The algorithm incorrectly predicted a fracture in 14 of the 100 patients without fractures (specificity of 86%). The negative predictive value was 98.85%. This study shows that DL algorithms are potentially valuable diagnostic tools for detecting fractures in the ER and could be used in the training of junior radiologists.

No-code machine learning in radiology: implementation and validation of a platform that allows clinicians to train their own models

“…The performance of the clavicle fracture classification model trained with our system is similar or better than models reported in the literature (see table 1. [33, 34] For example, Guermazi et al reported their AI model for identifying shoulder and clavicle fractures had a performance of 84% sensitivity, 83% specificity, and 0.90 AUC (95% CI 0.79-0.96). [14] Jones et al reported on a deep learning system for identifying clavicle fractures, using an ensemble of 10 convolutional networks, which obtained 90% sensitivity, 91% specificity, and an AUC of 0.96.…”

Insights and trends review: artificial intelligence in hand surgery

“…Radiology has received much attention within clinical AI (Topol, 2019) and is the most advanced area of AI within orthopaedics (Langerhuizen et al., 2019). There is obvious appeal for the use of AI within hand and wrist surgery; for example, improving detection of scaphoid fractures (Yoon and Chung, 2021), which continue to elude clinicians, or for flagging hand and wrist fractures in general within emergency departments (Reichert et al., 2021). Such interventions could reduce the burden of emergency reporting in cases of binary decisions (fracture present or not present), reducing missed fractures and streamlining referral to orthopaedic clinics or automating further radiological investigations.…”

Clinical applications of artificial intelligence in radiology

“…The radiologists’ performance was better than the AI’s for more severe diseases such as complete dislocations and aggressive FBL, whereas benign FBL and diastasis were rarely reported by them, likely because of their low clinical relevance. 46 In a separate study that examined whether deep learning can be used to improve fracture detection on X-rays in the Emergency Room, Reichert et al 47 used Azmed’s Rayvolve to detect traumatic fractures on the X-ray images of 125 patients. These patients were selected by two emergency physicians and the X-rays were also analyzed by a radiologist.…”