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

Aims. The number of convolutional neural networks (CNN) available for fracture detection and classification is rapidly increasing. External validation of a CNN on a temporally separate (separated by time) or geographically separate (separated by location) dataset is crucial to assess generalizability of the CNN before application to clinical practice in other institutions. We aimed to answer the following questions: are current CNNs for fracture recognition externally valid?; which methods are applied for external validation (EV)?; and, what are reported performances of the EV sets compared to the internal validation (IV) sets of these CNNs?. Methods. The PubMed and Embase databases were systematically searched from January 2010 to October 2020 according to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) statement. The type of EV, characteristics of the external dataset, and diagnostic performance characteristics on the IV and EV datasets were collected and compared. Quality assessment was conducted using a seven-item checklist based on a modified Methodologic Index for NOn-Randomized Studies instrument (MINORS). Results. Out of 1,349 studies, 36 reported development of a CNN for fracture detection and/or classification. Of these, only four (11%) reported a form of EV. One study used temporal EV, one conducted both temporal and geographical EV, and two used geographical EV. When comparing the CNN’s performance on the IV set versus the EV set, the following were found: AUCs of 0.967 (IV) versus 0.975 (EV), 0.976 (IV) versus 0.985 to 0.992 (EV), 0.93 to 0.96 (IV) versus 0.80 to 0.89 (EV), and F1-scores of 0.856 to 0.863 (IV) versus 0.757 to 0.840 (EV). Conclusion. The number of externally validated CNNs in orthopaedic trauma for fracture recognition is still scarce. This greatly limits the potential for transfer of these CNNs from the developing institute to another hospital to achieve similar diagnostic performance. We recommend the use of geographical EV and statements such as the Consolidated Standards of Reporting Trials–Artificial Intelligence (CONSORT-AI), the Standard Protocol Items: Recommendations for Interventional Trials–Artificial Intelligence (SPIRIT-AI) and the Transparent Reporting of a multivariable prediction model for Individual Prognosis or Diagnosis–Machine Learning (TRIPOD-ML) to critically appraise performance of CNNs and improve methodological rigor, quality of future models, and facilitate eventual implementation in clinical practice. Cite this article: Bone Jt Open 2021;2(10):879–885

Aims. The aim of this study was to create artificial intelligence (AI) software with the purpose of providing a second opinion to physicians to support distal radius fracture (DRF) detection, and to compare the accuracy of fracture detection of physicians with and without software support. Methods. The dataset consisted of 26,121 anonymized anterior-posterior (AP) and lateral standard view radiographs of the wrist, with and without DRF. The convolutional neural network (CNN) model was trained to detect the presence of a DRF by comparing the radiographs containing a fracture to the inconspicuous ones. A total of 11 physicians (six surgeons in training and five hand surgeons) assessed 200 pairs of randomly selected digital radiographs of the wrist (AP and lateral) for the presence of a DRF. The same images were first evaluated without, and then with, the support of the CNN model, and the diagnostic accuracy of the two methods was compared. Results. At the time of the study, the CNN model showed an area under the receiver operating curve of 0.97. AI assistance improved the physician’s sensitivity (correct fracture detection) from 80% to 87%, and the specificity (correct fracture exclusion) from 91% to 95%. The overall error rate (combined false positive and false negative) was reduced from 14% without AI to 9% with AI. Conclusion. The use of a CNN model as a second opinion can improve the diagnostic accuracy of DRF detection in the study setting. Cite this article: Bone Joint Res 2024;13(10):588–595

Aims. To investigate if preoperative CT improves detection of unstable trochanteric hip fractures. Methods. A single-centre prospective study was conducted. Patients aged 65 years or older with trochanteric hip fractures admitted to Stavanger University Hospital (Stavanger, Norway) were consecutively included from September 2020 to January 2022. Radiographs and CT images of the fractures were obtained, and surgeons made individual assessments of the fractures based on these. The assessment was conducted according to a systematic protocol including three classification systems (AO/Orthopaedic Trauma Association (OTA), Evans Jensen (EVJ), and Nakano) and questions addressing specific fracture patterns. An expert group provided a gold-standard assessment based on the CT images. Sensitivities and specificities of surgeons’ assessments were estimated and compared in regression models with correlations for the same patients. Intra- and inter-rater reliability were presented as Cohen’s kappa and Gwet’s agreement coefficient (AC1). Results. We included 120 fractures in 119 patients. Compared to radiographs, CT increased the sensitivity of detecting unstable trochanteric fractures from 63% to 70% (p = 0.028) and from 70% to 76% (p = 0.004) using AO/OTA and EVJ, respectively. Compared to radiographs alone, CT increased the sensitivity of detecting a large posterolateral trochanter major fragment or a comminuted trochanter major fragment from 63% to 76% (p = 0.002) and from 38% to 55% (p < 0.001), respectively. CT improved intra-rater reliability for stability assessment using EVJ (AC1 0.68 to 0.78; p = 0.049) and for detecting a large posterolateral trochanter major fragment (AC1 0.42 to 0.57; p = 0.031). Conclusion. A preoperative CT of trochanteric fractures increased detection of unstable fractures using the AO/OTA and EVJ classification systems. Compared to radiographs, CT improved intra-rater reliability when assessing fracture stability and detecting large posterolateral trochanter major fragments. Cite this article: Bone Jt Open 2024;5(6):524–531

The use of artificial intelligence (AI) is rapidly growing across many domains, of which the medical field is no exception. AI is an umbrella term defining the practical application of algorithms to generate useful output, without the need of human cognition. Owing to the expanding volume of patient information collected, known as ‘big data’, AI is showing promise as a useful tool in healthcare research and across all aspects of patient care pathways. Practical applications in orthopaedic surgery include: diagnostics, such as fracture recognition and tumour detection; predictive models of clinical and patient-reported outcome measures, such as calculating mortality rates and length of hospital stay; and real-time rehabilitation monitoring and surgical training. However, clinicians should remain cognizant of AI’s limitations, as the development of robust reporting and validation frameworks is of paramount importance to prevent avoidable errors and biases. The aim of this review article is to provide a comprehensive understanding of AI and its subfields, as well as to delineate its existing clinical applications in trauma and orthopaedic surgery. Furthermore, this narrative review expands upon the limitations of AI and future direction.

Cite this article: Bone Joint Res 2023;12(7):447–454.

Aims

To evaluate whether an ultra-low-dose CT protocol can diagnose selected limb fractures as well as conventional CT (C-CT).

The incidence and long-term outcome of undisplaced fatigue fractures of the femoral neck treated conservatively were examined in Finnish military conscripts between 1970 and 1990.

From 106 cases identified, 66 patients with 70 fractures were followed for a mean of 18.3 years (11 to 32). The original medical records and radiographs were studied and physical and radiological follow-up data analysed for evidence of risk factors for this injury. The development of avascular necrosis and osteoarthritis was determined from the follow-up radiographs and MR scans.

The impact of new military instructions on the management of hip-related pain was assessed following their introduction in 1986. The preventive regimen (1986) improved awareness and increased the detected incidence from 13.2 per 100 000 service-years (1970 to 1986) to 53.2 per 100 000 (1987 to 1990). No patient developed displacement of the fracture or avascular necrosis of the femoral head, or suffered from adverse complications. No differences were found in MRI-measured hip joint spaces at final follow-up. The mean Harris Hip Score was 97 (70 to 100) and the Visual Analogue Scale 5.85 mm (0 to 44).

Non-operative treatment, including avoidance of or reduced weight-bearing, gave favourable short- and long-term outcomes. Undisplaced fatigue fractures of the femoral neck neither predispose to avascular necrosis nor the subsequent development of osteoarthritis of the hip.