Aims. Rheumatoid arthritis (RA) is a common chronic immune disease. Berberine, as its main active ingredient, was also contained in a variety of medicinal plants such as Berberaceae, Buttercup, and Rutaceae, which are widely used in digestive system diseases in traditional Chinese medicine with anti-inflammatory and antibacterial effects. The aims of this article were to explore the therapeutic effect and mechanism of berberine on rheumatoid arthritis. Methods. Cell Counting Kit-8 was used to evaluate the effect of berberine on the proliferation of RA fibroblast-like synoviocyte (RA-FLS) cells. The effect of berberine on matrix metalloproteinase (MMP)-1, MMP-3, receptor activator of nuclear factor kappa-Β ligand (RANKL), tumour necrosis factor alpha (TNF-α), and other factors was determined by enzyme-linked immunoassay (ELISA) kit. Transcriptome technology was used to screen related pathways and the potential targets after berberine treatment, which were verified by reverse transcription-polymerase chain reaction (RT-qPCR) and Western blot (WB) technology. Results. Berberine inhibited proliferation and adhesion of RA-FLS cells, and significantly reduced the expression of MMP-1, MMP-3, RANKL, and TNF-α. Transcriptional results suggested that berberine intervention mainly regulated forkhead box O (FOXO) signal pathway, prolactin signal pathway, neurotrophic factor signal pathway, and hypoxia-inducible factor 1 (HIF-1) signal pathway. Conclusion. The effect of berberine on RA was related to the regulation of RAS/mitogen-activated protein kinase/FOXO/HIF-1 signal pathway in RA-FLS cells. Cite this article: Bone Joint Res 2023;12(2):91–102

Aims. Postoperative length of stay (LOS) and discharge dispositions following arthroplasty can be used as surrogate measurements for improvements in patients’ pathways and costs. With the increasing use of robotic technology in arthroplasty, it is important to assess its impact on LOS. The aim of this study was to identify factors associated with decreased LOS following robotic arm-assisted total hip arthroplasty (RO THA) compared with the conventional technique (CO THA). Methods. This large-scale, single-institution study included 1,607 patients of any age who underwent 1,732 primary THAs for any indication between May 2019 and January 2023. The data which were collected included the demographics of the patients, LOS, type of anaesthetic, the need for treatment in a post-anaesthesia care unit (PACU), readmission within 30 days, and discharge disposition. Univariate and multivariate logistic regression models were used to identify factors and the characteristics of patients which were associated with delayed discharge. Results. The multivariate model identified that age, female sex, admission into a PACU, American Society of Anesthesiologists grade > II, and CO THA were associated with a significantly higher risk of a LOS of > two days. The median LOS was 54 hours (interquartile range (IQR) 34 to 78) in the RO THA group compared with 60 hours (IQR 51 to 100) in the CO THA group (p < 0.001). The discharge dispositions were comparable between the two groups. A higher proportion of patients undergoing CO THA required PACU admission postoperatively, although without reaching statistical significance (7.2% vs 5.2%, p = 0.238). Conclusion. We found that among other baseline characteristics and comorbidities, RO THA was associated with a significantly shorter LOS, with no difference in discharge destination. With the increasing demand for THA, these findings suggest that robotic assistance in THA could reduce costs. However, randomized controlled trials are required to investigate the cost-effectiveness of this technology. Cite this article: Bone Joint J 2024;106-B(3 Supple A):24–30

Understanding spinopelvic mechanics is important for the success of total hip arthroplasty (THA). Despite significant advancements in appreciating spinopelvic balance, numerous challenges remain. It is crucial to recognize the individual variability and postoperative changes in spinopelvic parameters and their consequential impact on prosthetic component positioning to mitigate the risk of dislocation and enhance postoperative outcomes. This review describes the integration of advanced diagnostic approaches, enhanced technology, implant considerations, and surgical planning, all tailored to the unique anatomy and biomechanics of each patient. It underscores the importance of accurately predicting postoperative spinopelvic mechanics, selecting suitable imaging techniques, establishing a consistent nomenclature for spinopelvic stiffness, and considering implant-specific strategies. Furthermore, it highlights the potential of artificial intelligence to personalize care. Cite this article: Bone Joint J 2024;106-B(11):1206–1215

Orthopaedic surgeons are currently faced with an overwhelming number of choices surrounding total knee arthroplasty (TKA), not only with the latest technologies and prostheses, but also fundamental decisions on alignment philosophies. From ‘mechanical’ to ‘adjusted mechanical’ to ‘restricted kinematic’ to ‘unrestricted kinematic’ — and how constitutional alignment relates to these — there is potential for ambiguity when thinking about and discussing such concepts. This annotation summarizes the various alignment strategies currently employed in TKA. It provides a clear framework and consistent language that will assist surgeons to compare confidently and contrast the concepts, while also discussing the latest opinions about alignment in TKA. Finally, it provides suggestions for applying consistent nomenclature to future research, especially as we explore the implications of 3D alignment patterns on patient outcomes. Cite this article: Bone Joint J 2023;105-B(2):102–108

The June 2023 Research Roundup. 360. looks at: Characterizing recurrent infections after one-stage revision for periprosthetic joint infection of the knee; Predicted waiting times for orthopaedic surgery: an urgent need to address the deficit in capacity; Vascular impulse technology versus elevation for reducing the swelling of upper and lower limb joint fractures; Desperate patients will accept higher risks; How long does it take to find a positive culture in periprosthetic joint infection?

The subject of noise in the operating theatre was recognized as early as 1972 and has been compared to noise levels on a busy highway. While noise-induced hearing loss in orthopaedic surgery specifically has been recognized as early as the 1990s, it remains poorly studied. As a result, there has been renewed focus in this occupational hazard. Noise level is typically measured in decibels (dB), whereas noise adjusted for human perception uses A-weighted sound levels and is expressed in dBA. Mean operating theatre noise levels range between 51 and 75 dBA, with peak levels between 80 and 119 dBA. The greatest sources of noise emanate from powered surgical instruments, which can exceed levels as high as 140 dBA. Newer technology, such as robotic-assisted systems, contribute a potential new source of noise. This article is a narrative review of the deleterious effects of prolonged noise exposure, including noise-induced hearing loss in the operating theatre team and the patient, intraoperative miscommunication, and increased cognitive load and stress, all of which impact the surgical team’s overall performance. Interventions to mitigate the effects of noise exposure include the use of quieter surgical equipment, the implementation of sound-absorbing personal protective equipment, or changes in communication protocols. Future research endeavours should use advanced research methods and embrace technological innovations to proactively mitigate the effects of operating theatre noise. Cite this article: Bone Joint J 2024;106-B(10):1039–1043

Aims. Conventional patient-reported surveys, used for patients undergoing total hip arthroplasty (THA), are limited by subjectivity and recall bias. Objective functional evaluation, such as gait analysis, to delineate a patient’s functional capacity and customize surgical interventions, may address these shortcomings. This systematic review endeavours to investigate the application of objective functional assessments in appraising individuals undergoing THA. Methods. The Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines were applied. Eligible studies of THA patients that conducted at least one type of objective functional assessment both pre- and postoperatively were identified through Embase, Medline/PubMed, and Cochrane Central database-searching from inception to 15 September 2023. The assessments included were subgrouped for analysis: gait analysis, motion analysis, wearables, and strength tests. Results. A total of 130 studies using 15 distinct objective functional assessment methods (FAMs) were identified. The most frequently used method was instrumented gait/motion analysis, followed by the Timed-Up-and-Go test (TUG), 6 minute walk test, timed stair climbing test, and various strength tests. These assessments were characterized by their diagnostic precision and applicability to daily activities. Wearables were frequently used, offering cost-effectiveness and remote monitoring benefits. However, their accuracy and potential discomfort for patients must be considered. Conclusion. The integration of objective functional assessments in THA presents promise as a progress-tracking modality for improving patient outcomes. Gait analysis and the TUG, along with advancing wearable sensor technology, have the potential to enhance patient care, surgical planning, and rehabilitation. Cite this article: Bone Joint J 2024;106-B(8):764–774

Telehealth has the potential to change the way we approach patient care. From virtual consenting to reducing carbon emissions, costs, and waiting times, it is a powerful tool in our clinical armamentarium. There is mounting evidence that remote diagnostic evaluation and decision-making have reached an acceptable level of accuracy and can safely be adopted in orthopaedic surgery. Furthermore, patients’ and surgeons’ satisfaction with virtual appointments are comparable to in-person consultations. Challenges to the widespread use of telehealth should, however, be acknowledged and include the cost of installation, training, maintenance, and accessibility. It is also vital that clinicians are conscious of the medicolegal and ethical considerations surrounding the medium and adhere strictly to the relevant data protection legislation and storage framework. It remains to be seen how organizations harness the full spectrum of the technology to facilitate effective patient care. Cite this article: Bone Joint J 2023;105-B(8):843–849

The December 2024 Research Roundup. 360. looks at: Skeletal muscle composition, power, and mitochondrial energetics in older men and women with knee osteoarthritis; Machine-learning models to predict osteonecrosis in patients with femoral neck fractures undergoing internal fixation; Aetiology of patient dissatisfaction following primary total knee arthroplasty in the era of robotic-assisted technology; Efficacy and safety of commonly used thromboprophylaxis agents following hip and knee arthroplasty; The COVID-19 effect continues; Nickel allergy in knee arthroplasty: does self-reported sensitivity affect outcomes?; Tranexamic acid use and joint infection risk in total hip and knee arthroplasty

Aims. Robotic arm-assisted surgery offers accurate and reproducible guidance in component positioning and assessment of soft-tissue tensioning during knee arthroplasty, but the feasibility and early outcomes when using this technology for revision surgery remain unknown. The objective of this study was to compare the outcomes of robotic arm-assisted revision of unicompartmental knee arthroplasty (UKA) to total knee arthroplasty (TKA) versus primary robotic arm-assisted TKA at short-term follow-up. Methods. This prospective study included 16 patients undergoing robotic arm-assisted revision of UKA to TKA versus 35 matched patients receiving robotic arm-assisted primary TKA. In all study patients, the following data were recorded: operating time, polyethylene liner size, change in haemoglobin concentration (g/dl), length of inpatient stay, postoperative complications, and hip-knee-ankle (HKA) alignment. All procedures were performed using the principles of functional alignment. At most recent follow-up, range of motion (ROM), Forgotten Joint Score (FJS), and Oxford Knee Score (OKS) were collected. Mean follow-up time was 21 months (6 to 36). Results. There were no differences between the two treatment groups with regard to mean change in haemoglobin concentration (p = 0.477), length of stay (LOS, p = 0.172), mean polyethylene thickness (p = 0.065), or postoperative complication rates (p = 0.295). At the most recent follow-up, the primary robotic arm-assisted TKA group had a statistically significantly improved OKS compared with the revision UKA to TKA group (44.6 (SD 2.7) vs 42.3 (SD 2.5); p = 0.004) but there was no difference in the overall ROM (p = 0.056) or FJS between the two treatment groups (86.1 (SD 9.6) vs 84.1 (4.9); p = 0.439). Conclusion. Robotic arm-assisted revision of UKA to TKA was associated with comparable intraoperative blood loss, early postoperative rehabilitation, functional outcomes, and complications to primary robotic TKA at short-term follow-up. Robotic arm-assisted surgery offers a safe and reproducible technique for revising failed UKA to TKA. Cite this article: Bone Joint J 2024;106-B(7):680–687

Aims. While residual fixed flexion deformity (FFD) in unicompartmental knee arthroplasty (UKA) has been associated with worse functional outcomes, limited evidence exists regarding FFD changes. The objective of this study was to quantify FFD changes in patients with medial unicompartmental knee arthritis undergoing UKA, and investigate any correlation with clinical outcomes. Methods. This study included 136 patients undergoing robotic arm-assisted medial UKA between January 2018 and December 2022. The study included 75 males (55.1%) and 61 (44.9%) females, with a mean age of 67.1 years (45 to 90). Patients were divided into three study groups based on the degree of preoperative FFD: ≤ 5°, 5° to ≤ 10°, and > 10°. Intraoperative optical motion capture technology was used to assess pre- and postoperative FFD. Clinical FFD was measured pre- and postoperatively at six weeks and one year following surgery. Preoperative and one-year postoperative Oxford Knee Scores (OKS) were collected. Results. Overall, the median preoperative navigated (NAV) FFD measured 6.0° (IQR 3.1 to 8), while the median postoperative NAV FFD was 3.0° (IQR 1° to 4.4°), representing a mean correction of 49.2%. The median preoperative clinical FFD was 5° (IQR 0° to 9.75°) for the entire cohort, which decreased to 3.0° (IQR 0° to 5°) and 2° (IQR 0° to 3°) at six weeks and one year postoperatively, respectively. A statistically significant improvement in PROMs compared with baseline was evident in all groups (p < 0.001). Regression analyses showed that participants who experienced a larger FFD correction, showed greater improvement in PROMs (β = 0.609, p = 0.049; 95% CI 0.002 to 1.216). Conclusion. This study found that UKA was associated with an approximately 50% improvement in preoperative FFD across all three examined groups. Participants with greater correction of FFD also demonstrated larger OKS gains. These findings could prove a useful augment to clinical decision-making regarding candidacy for UKA and anticipated improvements in FFD

Aims. In-hospital length of stay (LOS) and discharge dispositions following arthroplasty could act as surrogate measures for improvement in patient pathways, and have major cost saving implications for healthcare providers. With the ever-growing adoption of robotic technology in arthroplasty, it is imperative to evaluate its impact on LOS. The objectives of this study were to compare LOS and discharge dispositions following robotic arm-assisted total knee arthroplasty (RO TKA) and unicompartmental arthroplasty (RO UKA) versus conventional technique (CO TKA and UKA). Methods. This large-scale, single-institution study included patients of any age undergoing primary TKA (n = 1,375) or UKA (n = 337) for any cause between May 2019 and January 2023. Data extracted included patient demographics, LOS, need for post anaesthesia care unit (PACU) admission, anaesthesia type, readmission within 30 days, and discharge dispositions. Univariate and multivariate logistic regression models were also employed to identify factors and patient characteristics related to delayed discharge. Results. The median LOS in the RO TKA group was 76 hours (interquartile range (IQR) 54 to 104) versus 82.5 (IQR 58 to 127) in the CO TKA group (p < 0.001) and 54 hours (IQR 34 to 77) in the RO UKA versus 58 (IQR 35 to 81) in the CO UKA (p = 0.031). Discharge dispositions were comparable between the two groups. A higher percentage of patients undergoing CO TKA required PACU admission (8% vs 5.2%; p = 0.040). Conclusion. Our study showed that robotic arm assistance was associated with a shorter LOS in patients undergoing primary UKA and TKA, and no difference in the discharge destinations. Our results suggest that robotic arm assistance could be advantageous in partly addressing the upsurge of knee arthroplasty procedures and the concomitant healthcare burden; however, this needs to be corroborated by long-term cost-effectiveness analyses and data from randomized controlled studies. Cite this article: Bone Jt Open 2023;4(10):791–800

Continuous technical improvement in spinal surgical procedures, with the aim of enhancing patient outcomes, can be assisted by the deployment of advanced technologies including navigation, intraoperative CT imaging, and surgical robots. The latest generation of robotic surgical systems allows the simultaneous application of a range of digital features that provide the surgeon with an improved view of the surgical field, often through a narrow portal. There is emerging evidence that procedure-related complications and intraoperative blood loss can be reduced if the new technologies are used by appropriately trained surgeons. Acceptance of the role of surgical robots has increased in recent years among a number of surgical specialities including general surgery, neurosurgery, and orthopaedic surgeons performing major joint arthroplasty. However, ethical challenges have emerged with the rollout of these innovations, such as ensuring surgeon competence in the use of surgical robotics and avoiding financial conflicts of interest. Therefore, it is essential that trainees aspiring to become spinal surgeons as well as established spinal specialists should develop the necessary skills to use robotic technology safely and effectively and understand the ethical framework within which the technology is introduced. Traditional and more recently developed platforms exist to aid skill acquisition and surgical training which are described. The aim of this narrative review is to describe the role of surgical robotics in spinal surgery, describe measures of proficiency, and present the range of training platforms that institutions can use to ensure they employ confident spine surgeons adequately prepared for the era of robotic spinal surgery. Cite this article: Bone Joint J 2020;102-B(5):568–572

Aims. The purpose of this study was to determine the access to and ability to use telemedicine technology in adult patients undergoing total hip arthroplasty (THA) and total knee arthroplasty (TKA), and to determine associations with the socioeconomic characteristics of the patients, including age, sex, race, and education. We also sought to understand the patients’ perceived benefits, risks, and preferences when dealing with telemedicine. Methods. We performed a cross-sectional survey involving patients awaiting primary THA and TKA by one of six surgeons at a single academic institution. Patients were included and called for a telephone-administered survey if their surgery was scheduled to be between 23 March and 2 June 2020, and were aged > 18 years. Results. The response rate was 52% (189 of 363 patients). A total of 170 patients (90.4%) reported using the internet, 177 (94.1%) reported owning a device capable of videoconferencing, and 143 (76.1%) had participated in a video call in the past year. When asked for their preferred method for a consultation, 155 (82.8%) and 26 (13.9%) ranked in-person and a videoconference as their first choice, respectively. The perceived benefits of telemedicine consultations included reduced travel to appointments (165 (88.2%) agreed) and reduced cost of attending appointments (123 (65.8%) agreed). However, patients were concerned that they would not establish the same patient-physician connection (100 (53.8%) agreed), and would not receive the same level of care (52 (33.2%) agreed) using telemedicine consultations compared with in-person consultations. Conclusion. Most patients undergoing arthroplasty have access to and are capable of using the technology required for telemedicine consultations. However, they still prefer in-person consultations due to concerns that they will not establish the same patient-physician connection and will not receive the same level of care, despite the benefits of reducing the time spent in travelling and the cost of attending appointments, and the appointments being easier to attend. Cite this article: Bone Joint J 2021;103-B(7 Supple B):98–102

Aims. Manual impaction, with a mallet and introducer, remains the standard method of installing cementless acetabular cups during total hip arthroplasty (THA). This study aims to quantify the accuracy and precision of manual impaction strikes during the seating of an acetabular component. This understanding aims to help improve impaction surgical techniques and inform the development of future technologies. Methods. Posterior approach THAs were carried out on three cadavers by an expert orthopaedic surgeon. An instrumented mallet and introducer were used to insert cementless acetabular cups. The motion of the mallet, relative to the introducer, was analyzed for a total of 110 strikes split into low-, medium-, and high-effort strikes. Three parameters were extracted from these data: strike vector, strike offset, and mallet face alignment. Results. The force vector of the mallet strike, relative to the introducer axis, was misaligned by an average of 18.1°, resulting in an average wasted strike energy of 6.1%. Furthermore, the mean strike offset was 19.8 mm from the centre of the introducer axis and the mallet face, relative to the introducer strike face, was misaligned by a mean angle of 15.2° from the introducer strike face. Conclusion. The direction of the impact vector in manual impaction lacks both accuracy and precision. There is an opportunity to improve this through more advanced impaction instruments or surgical training. Cite this article: Bone Joint Res 2024;13(4):193–200

Artificial intelligence (AI) is, in essence, the concept of ‘computer thinking’, encompassing methods that train computers to perform and learn from executing certain tasks, called machine learning, and methods to build intricate computer models that both learn and adapt, called complex neural networks. Computer vision is a function of AI by which machine learning and complex neural networks can be applied to enable computers to capture, analyze, and interpret information from clinical images and visual inputs. This annotation summarizes key considerations and future perspectives concerning computer vision, questioning the need for this technology (the ‘why’), the current applications (the ‘what’), and the approach to unlocking its full potential (the ‘how’). Cite this article: Bone Joint J 2022;104-B(8):911–914

Aims. The diagnosis of periprosthetic joint infection (PJI) continues to present a significant clinical challenge. New biomarkers have been proposed to support clinical decision-making; among them, synovial fluid alpha-defensin has gained interest. Current research methodology suggests reference methods are needed to establish solid evidence for use of the test. This prospective study aims to evaluate the diagnostic accuracy of high-performance liquid chromatography coupled with the mass spectrometry (LC-MS) method to detect alpha-defensin in synovial fluid. Methods. Between October 2017 and September 2019, we collected synovial fluid samples from patients scheduled to undergo revision surgery for painful total knee arthroplasty (TKA). The International Consensus Meeting criteria were used to classify 33 PJIs and 92 aseptic joints. LC-MS assay was performed to measure alpha-defensin in synovial fluid of all included patients. Sensitivity, specificity, positive predictive value, negative predictive value, and the area under the receiver operating characteristic curve (AUC) were calculated to define the test diagnostic accuracy. Results. The AUC was 0.99 (95% confidence interval (CI) 0.98 to 1.00). Receiver operating characteristic (ROC) analysis showed that the optimal cut-off value of synovial fluid alpha-defensin was 1.0 μg/l. The sensitivity of alpha-defensin was 100% (95% CI 96 to 100), the specificity was 97% (95% CI 90 to 98), the positive predictive value was 89.2% (95% CI 82 to 94), and negative predictive value was 100% (95% CI 96 to 100). ROC analysis demonstrated an AUC of 0.99 (95% CI 0.98 to 1.0). Conclusion. The present study confirms the utility of alpha-defensin in the synovial fluid in patients with painful TKA to select cases of PJI. Since LC-MS is still a time-consuming technology and is available in highly specialized laboratories, further translational research studies are needed to take this evidence into routine procedures and promote a new diagnostic approach. Cite this article: Bone Joint J 2022;104-B(9):1047–1051

Aims. Computer-based applications are increasingly being used by orthopaedic surgeons in their clinical practice. With the integration of technology in surgery, augmented reality (AR) may become an important tool for surgeons in the future. By superimposing a digital image on a user’s view of the physical world, this technology shows great promise in orthopaedics. The aim of this review is to investigate the current and potential uses of AR in orthopaedics. Materials and Methods. A systematic review of the PubMed, MEDLINE, and Embase databases up to January 2019 using the keywords ‘orthopaedic’ OR ‘orthopedic AND augmented reality’ was performed by two independent reviewers. Results. A total of 41 publications were included after screening. Applications were divided by subspecialty: spine (n = 15), trauma (n = 16), arthroplasty (n = 3), oncology (n = 3), and sports (n = 4). Out of these, 12 were clinical in nature. AR-based technologies have a wide variety of applications, including direct visualization of radiological images by overlaying them on the patient and intraoperative guidance using preoperative plans projected onto real anatomy, enabling hands-free real-time access to operating room resources, and promoting telemedicine and education. Conclusion. There is an increasing interest in AR among orthopaedic surgeons. Although studies show similar or better outcomes with AR compared with traditional techniques, many challenges need to be addressed before this technology is ready for widespread use. Cite this article: Bone Joint J 2019;101-B:1479–1488

Aims. Alternative alignment concepts, including kinematic and restricted kinematic, have been introduced to help improve clinical outcomes following total knee arthroplasty (TKA). The purpose of this study was to evaluate the clinical results, along with patient satisfaction, following TKA using the concept of restricted kinematic alignment. Methods. A total of 121 consecutive TKAs performed between 11 February 2018 to 11 June 2019 with preoperative varus deformity were reviewed at minimum one-year follow-up. Three knees were excluded due to severe preoperative varus deformity greater than 15°, and a further three due to requiring revision surgery, leaving 109 patients and 115 knees to undergo primary TKA using the concept of restricted kinematic alignment with advanced technology. Patients were stratified into three groups based on the preoperative limb varus deformity: Group A with 1° to 5° varus (43 knees); Group B between 6° and 10° varus (56 knees); and Group C with varus greater than 10° (16 knees). This study group was compared with a matched cohort of 115 TKAs and 115 patients using a neutral mechanical alignment target with manual instruments performed from 24 October 2016 to 14 January 2019. Results. Mean overall patient satisfaction for the entire cohort was 4.7 (SE 0.1) on a 5-point Likert scale, with 93% being either very satisfied or satisfied compared with a Likert of 4.3 and patient satisfaction of 81% in the mechanical alignment group (p < 0.001 and p < 0.006 respectively). At mean follow-up of 17 months (11 to 27), the mean overall Likert, Knee Injury and Osteoarthritis Outcome Score for Joint Replacement, Western Ontario and McMaster Universities Osteoarthritis Index, Forgotten Joint Score, and Knee Society Knee and Function Scores were significantly better in the kinematic group than in the neutral mechanical alignment group. The most common complication in both groups was contracture requiring manipulation under anaesthesia, involving seven knees (6.1%) in the kinematic group and nine knees (7.8%) in the mechanical alignment group. Conclusion. With the advent of advanced technology, and the ability to obtain accurate bone cuts, the target limb alignment, and soft-tissue balance within millimetres, using a restricted kinematic alignment concept demonstrated excellent patient satisfaction following primary TKA. Longer-term analysis is required as to the durability of this method. Cite this article: Bone Joint J 2021;103-B(6 Supple A):59–66

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