In recent years, machine learning (ML) and artificial neural networks (ANNs), a particular subset of ML, have been adopted by various areas of healthcare. A number of diagnostic and prognostic algorithms have been designed and implemented across a range of orthopaedic sub-specialties to date, with many positive results. However, the methodology of many of these studies is flawed, and few compare the use of ML with the current approach in clinical practice. Spinal surgery has advanced rapidly over the past three decades, particularly in the areas of implant technology, advanced surgical techniques, biologics, and enhanced recovery protocols. It is therefore regarded an innovative field. Inevitably, spinal surgeons will wish to incorporate ML into their practice should models prove effective in diagnostic or prognostic terms. The purpose of this article is to review published studies that describe the application of neural networks to spinal surgery and which actively compare ANN models to contemporary clinical standards allowing evaluation of their efficacy, accuracy, and relatability. It also explores some of the limitations of the technology, which act to constrain the widespread adoption of neural networks for diagnostic and prognostic use in spinal care. Finally, it describes the necessary considerations should institutions wish to incorporate ANNs into their practices. In doing so, the aim of this review is to provide a practical approach for spinal surgeons to understand the relevant aspects of neural networks. Cite this article:
Previous studies support the important role of
vascular endothelial growth factor (VEGF) and syndecan-4 in the pathogenesis
of osteoarthritis (OA). Both VEGF and syndecan-4 are expressed by
chondrocytes and both are involved in the regulation of matrix metalloproteinase-3,
resulting in the activation of aggrecanase II (ADAMTS-5), which
is essential in the pathogenesis of OA. However, the relationship
between VEGF and syndecan-4 has not been established. As a pilot
study, we assayed the expression of VEGF and syndecan-4 in cartilage
samples and cultured chondrocytes from osteoarthritic knee joints
and analysed the relationship between these two factors. Specimens were collected from 21 female patients (29 knees) who
underwent total knee replacement due to severe medial OA of the
knee (Kellgren–Lawrence grade 4). Articular cartilage samples, obtained
from bone and cartilage excised during surgery, were analysed and
used for chondrocyte culture. We found that the levels of expression
of VEGF and syndecan-4 mRNA did not differ significantly between
medial femoral cartilage with severe degenerative changes and lateral
femoral cartilage that appeared grossly normal (p = 0.443 and 0.622,
respectively). Likewise, the levels of expression of VEGF and syndecan-4
mRNA were similar in cultured chondrocytes from medial and lateral
femoral cartilage. The levels of expression of VEGF and syndecan-4
mRNAs were significantly and positively correlated in cartilage
explant (r = 0.601, p = 0.003) but not in cultured chondrocytes.
These results suggest that there is a close relationship between
VEGF and syndecan-4 in the cartilage of patients with OA. Further
studies are needed to determine the exact pathway by which these
two factors interact in the pathogenesis of OA. Cite this article:
We evaluated the top 13 journals in trauma and
orthopaedics by impact factor and looked at the longer-term effect regarding
citations of their papers. All 4951 papers published in these journals during 2007 and 2008
were reviewed and categorised by their type, subspecialty and super-specialty.
All citations indexed through Google Scholar were reviewed to establish
the rate of citation per paper at two, four and five years post-publication.
The top five journals published a total of 1986 papers. Only three
(0.15%) were on operative orthopaedic surgery and none were on trauma.
Most (n = 1084, 54.5%) were about experimental basic science. Surgical
papers had a lower rate of citation (2.18) at two years than basic science
or clinical medical papers (4.68). However, by four years the rates
were similar (26.57 for surgery, 30.35 for basic science/medical),
which suggests that there is a considerable time lag before clinical
surgical research has an impact. We conclude that high impact journals do not address clinical
research in surgery and when they do, there is a delay before such
papers are cited. We suggest that a rate of citation at five years
post-publication might be a more appropriate indicator of importance
for papers in our specialty. Cite this article:
The aim of this study was to determine whether subchondral bone influences in situ chondrocyte survival. Bovine explants were cultured in serum-free media over seven days with subchondral bone excised from articular cartilage (group A), subchondral bone left attached to articular cartilage (group B), and subchondral bone excised but co-cultured with articular cartilage (group C). Using confocal laser scanning microscopy, fluorescent probes and biochemical assays, in situ chondrocyte viability and relevant biophysical parameters (cartilage thickness, cell density, culture medium composition) were quantified over time (2.5 hours vs seven days). There was a significant increase in chondrocyte death over seven days, primarily within the superficial zone, for group A, but not for groups B or C (p <
0.05). There was no significant difference in cartilage thickness or cell density between groups A, B and C (p >
0.05). Increases in the protein content of the culture media for groups B and C, but not for group A, suggested that the release of soluble factors from subchondral bone may have influenced chondrocyte survival. In conclusion, subchondral bone significantly influenced chondrocyte survival in articular cartilage during explant culture. The extrapolation of bone-cartilage interactions in vitro to the clinical situation must be made with caution, but the findings from these experiments suggest that future investigation into in vivo mechanisms of articular cartilage survival and degradation must consider the interactions of cartilage with subchondral bone.