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:
Antibiotic resistance represents a threat to human health. It has been suggested that by 2050, antibiotic-resistant infections could cause ten million deaths each year. In orthopaedics, many patients undergoing surgery suffer from complications resulting from implant-associated infection. In these circumstances secondary surgery is usually required and chronic and/or relapsing disease may ensue. The development of effective treatments for antibiotic-resistant infections is needed. Recent evidence shows that bacteriophage (phages; viruses that infect bacteria) therapy may represent a viable and successful solution. In this review, a brief description of bone and joint infection and the nature of bacteriophages is presented, as well as a summary of our current knowledge on the use of bacteriophages in the treatment of bacterial infections. We present contemporary published in vitro and in vivo data as well as data from clinical trials, as they relate to bone and joint infections. We discuss the potential use of bacteriophage therapy in orthopaedic infections. This area of research is beginning to reveal successful results, but mostly in nonorthopaedic fields. We believe that bacteriophage therapy has potential therapeutic value for implant-associated infections in orthopaedics. Cite this article:
Stem cells are defined by their potential for self-renewal and the ability to differentiate into numerous cell types, including cartilage and bone cells. Although basic laboratory studies demonstrate that cell therapies have strong potential for improvement in tissue healing and regeneration, there is little evidence in the scientific literature for many of the available cell formulations that are currently offered to patients. Numerous commercial entities and ‘regenerative medicine centres’ have aggressively marketed unproven cell therapies for a wide range of medical conditions, leading to sometimes indiscriminate use of these treatments, which has added to the confusion and unpredictable outcomes. The significant variability and heterogeneity in cell formulations between different individuals makes it difficult to draw conclusions about efficacy. The ‘minimally manipulated’ preparations derived from bone marrow and adipose tissue that are currently used differ substantially from cells that are processed and prepared under defined laboratory protocols. The term ‘stem cells’ should be reserved for laboratory-purified, culture-expanded cells. The number of cells in uncultured preparations that meet these defined criteria is estimated to be approximately one in 10 000 to 20 000 (0.005% to 0.01%) in native bone marrow and 1 in 2000 in adipose tissue. It is clear that more refined definitions of stem cells are required, as the lumping together of widely diverse progenitor cell types under the umbrella term ‘mesenchymal stem cells’ has created confusion among scientists, clinicians, regulators, and our patients. Validated methods need to be developed to measure and characterize the ‘critical quality attributes’ and biological activity of a specific cell formulation. It is certain that ‘one size does not fit all’ – different cell formulations, dosing schedules, and culturing parameters will likely be required based on the tissue being treated and the desired biological target. As an alternative to the use of exogenous cells, in the future we may be able to stimulate the intrinsic vascular stem cell niche that is known to exist in many tissues. The tremendous potential of cell therapy will only be realized with further basic, translational, and clinical research. Cite this article:
