header advert
Results 1 - 2 of 2
Results per page:
Bone & Joint Research
Vol. 12, Issue 7 | Pages 423 - 432
6 Jul 2023
Xie H Wang N He H Yang Z Wu J Yang T Wang Y

Aims

Previous studies have suggested that selenium as a trace element is involved in bone health, but findings related to the specific effect of selenium on bone health remain inconclusive. Thus, we performed a meta-analysis by including all the relevant studies to elucidate the association between selenium status (dietary intake or serum selenium) and bone health indicators (bone mineral density (BMD), osteoporosis (OP), or fracture).

Methods

PubMed, Embase, and Cochrane Library were systematically searched to retrieve relevant articles published before 15 November 2022. Studies focusing on the correlation between selenium and BMD, OP, or fracture were included. Effect sizes included regression coefficient (β), weighted mean difference (WMD), and odds ratio (OR). According to heterogeneity, the fixed-effect or random-effect model was used to assess the association between selenium and bone health.


The Bone & Joint Journal
Vol. 102-B, Issue 11 | Pages 1574 - 1581
2 Nov 2020
Zhang S Sun J Liu C Fang J Xie H Ning B

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.