Hsu Dionne, Persitz Jonathan, Noori Atefeh, Zhang Haochi, Mashouri Pouria, Shah Rishi, Chan Andrea, Madani Amin, Paul Ryan
Temerty Faculty of Medicine, University of Toronto, Ontario, Canada.
Temerty Faculty of Medicine, University of Toronto, Ontario, Canada; Division of Plastic, Reconstructive and Aesthetic Surgery, Department of Surgery, University Health Network, Toronto Western Hand Program, Toronto, Ontario, Canada; Division of Orthopaedic Surgery, Department of Surgery, University Health Network, Toronto, Ontario, Canada.
J Hand Surg Am. 2025 Jul;50(7):781-789. doi: 10.1016/j.jhsa.2025.04.015. Epub 2025 May 26.
Distal radius fractures (DRFs) represent up to 20% of the fractures in the emergency department. Delays to surgery of more than 14 days are associated with poorer functional outcomes and increased health care utilization/costs. At our institution, the average time to surgery is more than 19 days because of the separation of surgical and nonsurgical care pathways and a lengthy referral process. To address this challenge, we aimed to create a convolutional neural network (CNN) capable of automating DRF x-ray analysis and triaging. We hypothesize that this model will accurately predict whether an acute isolated DRF fracture in a patient under the age of 60 years will be treated surgically or nonsurgically at our institution based on the radiographic input.
We included 163 patients under the age of 60 years who presented to the emergency department between 2018 and 2023 with an acute isolated DRF and who were referred for clinical follow-up. Radiographs taken within 4 weeks of injury were collected in posterior-anterior and lateral views and then preprocessed for model training. The surgeons' decision to treat surgically or nonsurgically at our institution was the reference standard for assessing the model prediction accuracy.
We included 723 radiographic posterior-anterior and lateral pairs (385 surgical and 338 nonsurgical) for model training. The best-performing model (seven CNN layers, one fully connected layer, an image input size of 256 × 256 pixels, and a 1.5× weighting for volarly displaced fractures) achieved 88% accuracy and 100% sensitivity. Values for true positive (100%), true negative (72.7%), false positive (27.3%), and false negative (0%) were calculated.
After training based on institution-specific indications, a CNN-based algorithm can predict with 88% accuracy whether treatment of an acute isolated DRF in a patient under the age of 60 years will be treated surgically or nonsurgically.
By promptly identifying patients who would benefit from expedited surgical treatment pathways, this model can reduce times for referral.
桡骨远端骨折（DRF）占急诊科骨折的比例高达20%。手术延迟超过14天与较差的功能结局以及医疗保健利用率/成本增加相关。在我们机构，由于手术和非手术护理途径的分离以及漫长的转诊过程，平均手术时间超过19天。为应对这一挑战，我们旨在创建一个能够自动进行DRF X光分析和分诊的卷积神经网络（CNN）。我们假设该模型将基于X光片输入准确预测60岁以下患者的急性孤立性DRF骨折在我们机构将接受手术治疗还是非手术治疗。
我们纳入了163例60岁以下的患者，他们在2018年至2023年期间因急性孤立性DRF到急诊科就诊，并被转诊进行临床随访。收集受伤后4周内拍摄的前后位和侧位X光片，然后进行预处理以用于模型训练。外科医生在我们机构进行手术或非手术治疗的决定是评估模型预测准确性的参考标准。
我们纳入了723对X光前后位和侧位片（385例手术治疗和338例非手术治疗）用于模型训练。表现最佳的模型（七个CNN层、一个全连接层、图像输入大小为256×256像素以及对掌侧移位骨折采用1.5倍加权）的准确率达到88%，灵敏度达到100%。计算了真阳性（100%）、真阴性（72.7%）、假阳性（27.3%）和假阴性（0%）的值。
基于机构特定指征进行训练后，基于CNN的算法能够以88%的准确率预测60岁以下患者的急性孤立性DRF骨折将接受手术治疗还是非手术治疗。
通过迅速识别将从加速手术治疗途径中获益的患者，该模型可以减少转诊时间。
