Aims. The diagnosis of developmental dysplasia of the hip (DDH) is challenging owing to extensive variation in paediatric pelvic anatomy. Artificial intelligence (AI) may represent an effective diagnostic tool for DDH. Here, we aimed to develop an anteroposterior pelvic radiograph deep learning system for diagnosing DDH in children and analyze the feasibility of its application. Methods. In total, 10,219 anteroposterior pelvic radiographs were retrospectively collected from April 2014 to December 2018. Clinicians labelled each radiograph using a uniform standard method. Radiographs were grouped according to age and into ‘dislocation’ (dislocation and subluxation) and ‘non-dislocation’ (normal cases and those with dysplasia of the acetabulum) groups based on clinical diagnosis. The deep learning system was trained and optimized using 9,081 radiographs; 1,138 test radiographs were then used to compare the diagnoses made by deep learning system and clinicians. The accuracy of the deep learning system was determined using a receiver operating characteristic curve, and the consistency of acetabular index measurements was evaluated using Bland-Altman plots. Results. In all, 1,138 patients (242 males; 896 females; mean age 1.5 years (SD 1.79; 0 to 10) were included in this study. The area under the receiver operating characteristic curve, sensitivity, and specificity of the deep learning system for diagnosing hip dislocation were 0.975, 276/289 (95.5%), and 1,978/1,987 (99.5%), respectively. Compared with clinical diagnoses, the Bland-Altman 95% limits of agreement for acetabular index, as determined by the deep learning system from the radiographs of non-dislocated and dislocated hips, were -3.27° - 2.94° and -7.36° - 5.36°, respectively (p < 0.001). Conclusion. The deep learning system was highly consistent, more convenient, and more effective for diagnosing DDH compared with clinician-led diagnoses. Deep learning systems should be considered for analysis of anteroposterior pelvic radiographs when diagnosing DDH. The deep learning system will improve the current artificially complicated screening referral process. Cite this article: Bone Joint J 2020;102-B(11):1574–1581

Aim. Iliopsoas tendinopathy occurs due to friction of the iliopsoas tendon on the iliopectineal bar or the hip capsule causing pain and snapping of the hip. In adolescent cases this condition is generally treated conservatively with physiotherapy, stretching and NSAIDs. Our aim was to study the outcome of non-operative management of iliopsoas tendinopathy. Method. A retrospective 4-year study identified adolescent patients with a clinical diagnosis of psoas tendinopathy managed non-operatively. These patients were followed up by postal questionnaire, which included functional assessment using the Non-Arthritic Hip Score (NAHS). A custom study questionnaire assessed current symptoms and the effects of physiotherapy. All patients not treated conservatively were removed from the study. Results. 36 patients were treated conservatively for psoas tendinopathy. 28 completed and returned the questionnaires to a satisfactory standard. Mean NAHS was 77.72 (CI: 69.91 to 85.54) at a mean follow up of 37 months (Range: 14 to 58 months; CI 31 to 43 months). Pain was the least disabling NAHS domain at final follow up with a significant improvement over the follow up period (p<0.001). 11 patients suffered from recurrence of symptoms (clicking, stiffness, decreased range of motion). 7 patients (25%) complained of significant pain following conservative management. A Numbers Needed to Treat analysis (NNT) was performed, comparing our data with that of surgically managed patients in previously published studies. This analysis suggests that for every 6 surgical releases, 5 would have recovered anyway with non-operative management. Conclusion. Non-operative management is successful in managing psoas tendinopathy in about 75% of adolescent patients. It is especially effective in males, and patients who are more active prior to development of symptoms

The purpose of this study was to investigate whether patient age of 16 years and under is a valid “red flag” for back pain, by determining how often magnetic resonance imaging (MRI) investigations in these patients demonstrated significant pathology. This was a retrospective review of cases over a five-year period (2008–12). The radiology database was interrogated to identify all patients aged 16 and under who had undergone an MRI scan of their lumbar spine for a primary complaint of low back pain. All emergency and inpatient admissions were excluded from the study. Casenotes of each of these patients were analysed for demographics, clinical features, diagnosis and outcome. After exclusions, 98 eligible cases were identified. The age range of these patients was 2–16 years (mean age 12.63 years). The MRI scan found no abnormalities in 71.4% of cases. In the scans with positive findings, there were 8 cases of spondylolysis, 3 spondylolistheses, 9 cases of disc degeneration and 5 cases of Scheuermann's. Tumour or infection were found in only 3% of cases, (2 cases sacroilitis, 1 sacral chondroblastoma); there had been sacral or sacroiliac tenderness in each of these cases. In keeping with other recent studies, this study shows that the diagnostic yield of MRI in patients under the age of 16 with low back pain is relatively high (28.6%). However, scan findings did not significantly alter management in the vast majority of cases (97%). Serious pathology (infection or tumour) was found in only 3% of cases. We therefore suggest that an age of 16 years or less, in isolation, should not be a “red flag” indicator for low back pain. We do however advise a lower threshold for imaging in patients presenting with sacral region pain and tenderness

Aims

The aim of this prospective cohort study was to evaluate the effectiveness of the neonatal hip instability screening programme.

The aim of this retrospective multicentre study was to report the continued occurrence of compartment syndrome secondary to paediatric supracondylar humeral fractures in the period 1995 to 2005. The inclusion criteria were children with a closed, low-energy supracondylar fracture with no associated fractures or vascular compromise, who subsequently developed compartment syndrome. There were 11 patients (seven girls and four boys) identified from eight hospitals in three countries. Ten patients with severe elbow swelling documented at presentation had a mean delay before surgery of 22 hours (6 to 64). One patient without severe swelling documented at presentation suffered arterial entrapment following reduction, with a subsequent compartment syndrome requiring fasciotomy 25 hours after the index procedure.

This series is noteworthy, as all patients had low-energy injuries and presented with an intact radial pulse. Significant swelling at presentation and delay in fracture reduction may be important warning signs for the development of a compartment syndrome in children with supracondylar fractures of the humerus.

We examined 204 children (137 boys and 67 girls) aged 12 years and under with septic arthritis. Their mean age was 31.1 months (1 to 144; SD 41.6). The most common joints affected were the knees and shoulders. Joints in the upper limb were affected more often in younger children and in the lower limb in those who were older. The mean age for an infection was 12 months in the shoulder and 73 months in the hip. The most common organisms cultured were species of Salmonella.