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

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