Tennis elbow (lateral epicondylitis or lateral elbow tendinopathy) is a self-limiting condition in most patients. Surgery is often offered to patients who fail to improve with conservative treatment. However, there is no evidence to support the superiority of surgery over continued nonoperative care or no treatment. New evidence also suggests that the prognosis of tennis elbow is not influenced by the duration of symptoms, and that there is a 50% probability of recovery every three to four months. This finding challenges the belief that failed nonoperative care is an indication for surgery. In this annotation, we discuss the clinical and research implications of the benign clinical course of tennis elbow. Cite this article: Bone Joint J 2023;105-B(2):109–111

Initial treatment of traumatic spinal cord injury remains as controversial in 2023 as it was in the early 19th century, when Sir Astley Cooper and Sir Charles Bell debated the merits or otherwise of surgery to relieve cord compression. There has been a lack of high-class evidence for early surgery, despite which expeditious intervention has become the surgical norm. This evidence deficit has been progressively addressed in the last decade and more modern statistical methods have been used to clarify some of the issues, which is demonstrated by the results of the SCI-POEM trial. However, there has never been a properly conducted trial of surgery versus active conservative care. As a result, it is still not known whether early surgery or active physiological management of the unstable injured spinal cord offers the better chance for recovery. Surgeons who care for patients with traumatic spinal cord injuries in the acute setting should be aware of the arguments on all sides of the debate, a summary of which this annotation presents. Cite this article: Bone Joint J 2023;105-B(4):347–355

Artificial intelligence and machine-learning analytics have gained extensive popularity in recent years due to their clinically relevant applications. A wide range of proof-of-concept studies have demonstrated the ability of these analyses to personalize risk prediction, detect implant specifics from imaging, and monitor and assess patient movement and recovery. Though these applications are exciting and could potentially influence practice, it is imperative to understand when these analyses are indicated and where the data are derived from, prior to investing resources and confidence into the results and conclusions. In this article, we review the current benefits and potential limitations of machine-learning for the orthopaedic surgeon with a specific emphasis on data quality