Despite the vast quantities of published artificial intelligence (AI) algorithms that target trauma and orthopaedic applications, very few progress to inform clinical practice. One key reason for this is the lack of a clear pathway from development to deployment. In order to assist with this process, we have developed the Clinical Practice Integration of Artificial Intelligence (CPI-AI) framework – a five-stage approach to the clinical practice adoption of AI in the setting of trauma and orthopaedics, based on the IDEAL principles (https://www.ideal-collaboration.net/). Adherence to the framework would provide a robust evidence-based mechanism for developing trust in AI applications, where the underlying algorithms are unlikely to be fully understood by clinical teams.

Cite this article: Bone Joint Res 2024;13(9):507–512.

Aims

Disorders of bone integrity carry a high global disease burden, frequently requiring intervention, but there is a paucity of methods capable of noninvasive real-time assessment. Here we show that miniaturized handheld near-infrared spectroscopy (NIRS) scans, operated via a smartphone, can assess structural human bone properties in under three seconds.

Aims

The ongoing COVID-19 pandemic has disrupted and delayed medical and surgical examinations where attendance is required in person. Our article aims to outline the validity of online assessment, the range of benefits to both candidate and assessor, and the challenges to its implementation. In addition, we propose pragmatic suggestions for its introduction into medical assessment.

Femoral lengthening using the Intramedullary Skeletal Kinetic Distractor is a new technique. However, with intramedullary distraction the surgeon has less control over the lengthening process. Therefore, 33 femora lengthened with this device were assessed to evaluate the effect of operative variables under the surgeon’s control on the course of lengthening. The desired lengthening was achieved in 32 of 33 limbs. Problems encountered included difficulty in achieving length in eight femora (24%) and uncontrolled lengthening in seven (21%). Uncontrolled lengthening was more likely if the osteotomy was placed with less than 80 mm of the thick portion of the nail in the distal fragment (p = 0.052), and a failure to lengthen was more likely if there was over 125 mm in the distal fragment (p = 0.008). The latter problem was reduced with over-reaming by 2.5 mm to 3 mm. Previous intramedullary nailing also predisposed to uncontrolled lengthening (p = 0.042), and these patients required less reaming.

Using the Intramedullary Skeletal Kinetic Distractor, good outcomes were obtained; problems were minimised by optimising the position of the osteotomy and the amount of over-reaming performed.

Magnification of anteroposterior radiographs of the pelvis is variable. To improve the accuracy of templating, reliable and radiographer-friendly methods of scaling are necessary. We assessed two methods of scaling digital radiographs of the pelvis: placing a coin of known diameter in the plane of interest between the patient’s thighs, and using a caliper to measure the bony width of the pelvis. A total of 39 patients who had recently undergone hemiarthroplasty of the hip or total hip replacement were enrolled in the study. The accuracy of the methods was assessed by comparing the actual diameter of the head of the prosthesis with the measured on-screen value. The coin method was within a mean of 1.12% (0% to 2.38%) of the actual measurement, the caliper group within 6.99% (0% to 16.67%). The coin method was significantly more accurate (p < 0.001). It was also reliable and radiographer friendly. We recommend it as the method of choice for scaling radiographs of the pelvis before hip surgery.