Aims. The purpose of this study was to develop a convolutional neural network (CNN) for fracture detection, classification, and identification of greater tuberosity displacement ≥ 1 cm, neck-shaft angle (NSA) ≤ 100°, shaft translation, and articular fracture involvement, on plain radiographs. Methods. The CNN was trained and tested on radiographs sourced from 11 hospitals in Australia and externally validated on radiographs from the Netherlands. Each radiograph was paired with corresponding CT scans to serve as the reference standard based on dual independent evaluation by trained researchers and attending orthopaedic surgeons. Presence of a fracture, classification (non- to minimally displaced; two-part, multipart, and glenohumeral dislocation), and four characteristics were determined on 2D and 3D CT scans and subsequently allocated to each series of radiographs. Fracture characteristics included greater tuberosity displacement ≥ 1 cm, NSA ≤ 100°, shaft translation (0% to < 75%, 75% to 95%, > 95%), and the extent of articular involvement (0% to < 15%, 15% to 35%, or > 35%). Results. For detection and classification, the algorithm was trained on 1,709 radiographs (n = 803), tested on 567 radiographs (n = 244), and subsequently externally validated on 535 radiographs (n = 227). For characterization, healthy shoulders and glenohumeral dislocation were excluded. The overall accuracy for fracture detection was 94% (area under the receiver operating characteristic curve (AUC) = 0.98) and for classification 78% (AUC 0.68 to 0.93). Accuracy to detect greater tuberosity fracture displacement ≥ 1 cm was 35.0% (AUC 0.57). The CNN did not recognize NSAs ≤ 100° (AUC 0.42), nor fractures with ≥ 75% shaft translation (AUC 0.51 to 0.53), or with ≥ 15% articular involvement (AUC 0.48 to 0.49). For all objectives, the model’s performance on the external dataset showed similar accuracy levels. Conclusion. CNNs proficiently rule out proximal humerus fractures on plain radiographs. Despite rigorous training methodology based on CT imaging with multi-rater consensus to serve as the reference standard, artificial intelligence-driven classification is insufficient for clinical implementation. The CNN exhibited poor diagnostic ability to detect greater tuberosity displacement ≥ 1 cm and failed to identify NSAs ≤ 100°, shaft translations, or articular fractures. Cite this article: Bone Joint J 2024;106-B(11):1348–1360

A fracture of the tuberosity is associated with 16% of anterior glenohumeral dislocations. Manipulation of these injuries in the emergency department is safe with less than 1% risk of fracture propagation. However, there is a risk of associated neurological injury, recurrent instability and displacement of the greater tuberosity fragment. The risks and outcomes of these complications have not previously been reported. The purpose of this study was to establish the incidence and outcome of complications associated with this pattern of injury. We reviewed 339 consecutive glenohumeral dislocations with associated greater tuberosity fractures from a prospective trauma database. Documentation and radiographs were studied and the incidence of neurovascular compromise, greater tuberosity fragment migration and intervention and recurrent instability recorded. The mean age was 61 years (range, 18–96) with a female preponderance (140:199 male:female). At presentation 24% (n=78) patients had a nerve injury, with axillary nerve being most common (n=43, 55%). Of those patients with nerve injuries 15 (19%) did not resolve. Greater tuberosity displacement >5mm was observed in 36% (n=123) of patients with 40 undergoing acute surgery, the remainder did not due to comorbidities or patient choice. Persistent displacement after reduction accounted for 60 cases, later displacement within 6 weeks occurred in 63 patients. Recurrent instability occurred in 4 (1%) patients. Patient reported outcomes were poor with average EQ5D being 0.73, QDASH score of 16 and Oxford Shoulder Score of 41. Anterior glenohumeral dislocation with associated greater tuberosity fracture is common with poor long term patient reported outcomes. Our results demonstrate there is a high rate of neurological deficits at presentation with the majority resolving spontaneously. Recurrent instability is rare. Late tuberosity fragment displacement occurs in 18% of patients and regular follow-up for 6 weeks is recommended to detect this

Aims

The aim of this study was to explore why some calcar screws are malpositioned when a proximal humeral fracture is treated by internal fixation with a locking plate, and to identify risk factors for this phenomenon. Some suggestions can be made of ways to avoid this error.

The February 2014 Trauma Roundup³⁶⁰ looks at: predicting nonunion; compartment Syndrome; octogenarian RTCs; does HIV status affect decision making in open tibial fractures?; flap timing and related complications; proximal humeral fractures under the spotlight; restoration of hip architecture with bipolar hemiarthroplasty in the elderly; and short versus long cephalomedullary nails for the treatment of intertrochanteric hip fractures in patients over 65 years.