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: Bone Joint J 2021;103-B(9):1442–1448.
Study design Systematic Review Objectives Vertebral Artery Injury (VAI) is a potentially serious complication of cervical spine fractures. As many patients can be asymptomatic at the time of injury, the identification and diagnosis of VAI can often prove difficult. Due to the high rates of morbidity and mortality associated with VAI, high clinical suspicion is paramount. The purpose of this review is to elucidate incidence, diagnosis, treatment and outcomes of VAI associated with cervical spine injuries. Methods A systematic search of electronic databases was performed using ‘PUBMED’, ‘EMBASE’,‘Medline (OVID)’, and ‘Web of Science, for articles pertaining to traumatic cervical fractures with associated VAI. Results 24 studies were included in this systematic review. Data was included from 48 744 patients. In regards to the demographics of the focus groups that highlighted information on VAI, the mean average age was 46.6 (32.1-62.6). 75.1% (169/225) were male and 24.9% (56/225) were female. Overall incidence of VAI was 596/11 479 (5.19%). 190/420 (45.2%) of patients with VAI had fractures involving the transverse foramina. The right vertebral artery was the most commonly injured 114/234 (48.7%). V3 was the most common section injured (16/36 (44.4%)). Grade I was the most common (103/218 (47.2%)) injury noted. Collective acute hospital mortality rate was 32/226 (14.2%), ranging from 0-26.2% across studies. Conclusion VAI secondary to cervical spine trauma has a notable incidence and high associated mortality rates. The current available literature is limited by a low quality of evidence. In order to optimise diagnostic protocols and treatment strategies, in addition to reducing mortality rates associated with VAI, robust quantitative and qualitative studies are needed.
Intussusception through a prolapsed end colostomy is amongst the rarest of stoma complications. In this case report, we discuss the therapeutic approach to this complication and provide an update of the existing literature. A 66-year-old male presented with a prolapsed colostomy that was ischaemic in appearance. Intraoperatively, a small bowel intussusception within the prolapsed colon was identified. A subtotal colectomy was subsequently performed to prevent further volvulus formation. When patients present with a prolapsing oedematous enterostomy that cannot be reduced, careful clinical examination is required. If there is vascular compromise, exploratory laparotomy is mandatory.
Background Chyle leak/fistula is a rare complication of oesophageal surgery, usually consequent on an unintended breach of the thoracic duct, its tributaries, or the cisterna chyli. For high volume persistent leaks further surgery has been the traditional approach, however two cases have resulted in a new management approach at this Centre. Case Series The first patient, a 49-year-old, developed high volume drain output post three stage oesophagectomy. His jejunostomy feeding was discontinued, total parenteral nutrition and a somatostatin analogue, were commenced. Despite these measures, the drain output remained >1.5litres per day and an exploratory thoracotomy was performed. The second patient, an 81-year-old underwent a transhiatal-oesophagectomy. On postoperative day 10 he developed acute onset shortness of breath, CXR demonstrated a large left sided pleural effusion. CT thorax demonstrated multiloculated complex pleural effusions. US guided pig tail drain was placed in the largest targetable effusion. The fluid was chylous in appearance. In both cases, an interventional radiological approach, not previously performed at this centre, provided definitive management. Lymphangiography was performed via injection of 1mL of Lipoidol® every 5 minutes into the inguinal lymph nodes to identify the cisterna chyli. A guidewire was advanced via the cisterna chyli with coils and glue used to embolize the leaking tracts. Discussion The lessons from this experience provide an algorithm for the management of chyle leaks, that will change practice at this centre. Embolization or disruption of thoracic duct and cisterna chyli leaks will be first line therapy for complex chyle leaks, with surgery reserved for where this fails.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.