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:
Injuries to the hamstring muscle complex are common in athletes, accounting for between 12% and 26% of all injuries sustained during sporting activities. Acute hamstring injuries often occur during sports that involve repetitive kicking or high-speed sprinting, such as American football, soccer, rugby, and athletics. They are also common in watersports, including waterskiing and surfing. Hamstring injuries can be career-threatening in elite athletes and are associated with an estimated risk of recurrence in between 14% and 63% of patients. The variability in prognosis and treatment of the different injury patterns highlights the importance of prompt diagnosis with magnetic resonance imaging (MRI) in order to classify injuries accurately and plan the appropriate management. Low-grade hamstring injuries may be treated with nonoperative measures including pain relief, eccentric lengthening exercises, and a graduated return to sport-specific activities. Nonoperative management is associated with highly variable times for convalescence and return to a pre-injury level of sporting function. Nonoperative management of high-grade hamstring injuries is associated with poor return to baseline function, residual muscle weakness and a high-risk of recurrence. Proximal hamstring avulsion injuries, high-grade musculotendinous tears, and chronic injuries with persistent weakness or functional compromise require surgical repair to enable return to a pre-injury level of sporting function and minimize the risk of recurrent injury. This article reviews the optimal diagnostic imaging methods and common classification systems used to guide the treatment of hamstring injuries. In addition, the indications and outcomes for both nonoperative and operative treatment are analyzed to provide an evidence-based management framework for these patients. Cite this article:
Periprosthetic joint infection (PJI) is one of
the most feared and challenging complications following total knee arthroplasty.
We provide a detailed description of our current understanding regarding
the management of PJI of the knee, including diagnostic aids,
pre-operative planning, surgical treatment, and outcome. Cite this article:
