Aims. This study used an artificial neural network (ANN) model to determine the most important pre- and perioperative variables to predict same-day discharge in patients undergoing total knee arthroplasty (TKA). Methods. Data for this study were collected from the National Surgery Quality Improvement Program (NSQIP) database from the year 2018. Patients who received a primary, elective, unilateral TKA with a diagnosis of primary osteoarthritis were included. Demographic, preoperative, and intraoperative variables were analyzed. The ANN model was compared to a logistic regression model, which is a conventional machine-learning algorithm. Variables collected from 28,742 patients were analyzed based on their contribution to hospital length of stay. Results. The predictability of the ANN model, area under the curve (AUC) = 0.801, was similar to the logistic regression model (AUC = 0.796) and identified certain variables as important factors to predict same-day discharge. The ten most important factors favouring same-day discharge in the ANN model include preoperative sodium, preoperative international normalized ratio, BMI, age, anaesthesia type, operating time, dyspnoea status, functional status, race, anaemia status, and chronic obstructive pulmonary disease (COPD). Six of these variables were also found to be significant on logistic regression analysis. Conclusion. Both ANN modelling and logistic regression analysis revealed clinically important factors in predicting patients who can undergo safely undergo same-day discharge from an outpatient TKA. The ANN model provides a beneficial approach to help determine which perioperative factors can predict same-day discharge as of 2018 perioperative recovery protocols. Cite this article: Bone Joint J 2021;103-B(8):1358–1366

Aims. The volume of ambulatory total hip arthroplasty (THA) procedures is increasing due to the emphasis on value-based care. The purpose of the study is to identify the causes for failed same-day discharge (SDD) and perioperative factors leading to failed SDD. Methods. This retrospective cohort study followed pre-selected patients for SDD THA from 1 August 2018 to 31 December 2020. Inclusion criteria were patients undergoing unilateral THA with appropriate social support, age 18 to 75 years, and BMI < 37 kg/m. 2. Patients with opioid dependence, coronary artery disease, and valvular heart disease were excluded. Demographics, comorbidities, and perioperative data were collected from the electronic medical records. Possible risk factors for failed SDD were identified using multivariate logistic regression. Results. In all, 278 patients were identified with a mean age of 57.1 years (SD 8.1) and a mean BMI of 27.3 kg/m. 2. (SD 4.5). A total of 96 patients failed SDD, with the most common reasons being failure to clear physical therapy (26%), dizziness (22%), and postoperative nausea and vomiting (11%). Risk factors associated with failed SDD included smokers (odds ratio (OR) 6.24; p = 0.009), a maximum postoperative pain score > 8 (OR 4.76; p = 0.004), and procedures starting after 11 am (OR 2.28; p = 0.015). A higher postoperative tolerable pain goal (numerical rating scale 4 to 10) was found to be associated with successful SDD (OR 2.7; p = 0.001). Age, BMI, surgical approach, American Society of Anesthesiologists grade, and anaesthesia type were not associated with failed SDD. Conclusion. SDD is a safe and viable option for pre-selected patients interested in rapid recovery THA. The most common causes for failure to launch were failing to clear physical thereapy and patient symptomatology. Risk factors associated with failed SSD highlight the importance of preoperative counselling regarding smoking cessation and postoperative pain to set reasonable expectations. Future interventions should aim to improve patient postoperative mobilization, pain control, and decrease symptomatology. Cite this article: Bone Jt Open 2022;3(9):684–691

Aims. To identify variables independently associated with same-day discharge (SDD) of patients following revision total knee arthroplasty (rTKA) and to develop machine learning algorithms to predict suitable candidates for outpatient rTKA. Methods. Data were obtained from the American College of Surgeons National Quality Improvement Programme (ACS-NSQIP) database from the years 2018 to 2020. Patients with elective, unilateral rTKA procedures and a total hospital length of stay between zero and four days were included. Demographic, preoperative, and intraoperative variables were analyzed. A multivariable logistic regression (MLR) model and various machine learning techniques were compared using area under the curve (AUC), calibration, and decision curve analysis. Important and significant variables were identified from the models. Results. Of the 5,600 patients included in this study, 342 (6.1%) underwent SDD. The random forest (RF) model performed the best overall, with an internally validated AUC of 0.810. The ten crucial factors favoring SDD in the RF model include operating time, anaesthesia type, age, BMI, American Society of Anesthesiologists grade, race, history of diabetes, rTKA type, sex, and smoking status. Eight of these variables were also found to be significant in the MLR model. Conclusion. The RF model displayed excellent accuracy and identified clinically important variables for determining candidates for SDD following rTKA. Machine learning techniques such as RF will allow clinicians to accurately risk-stratify their patients preoperatively, in order to optimize resources and improve patient outcomes. Cite this article: Bone Jt Open 2023;4(6):399–407

Aims. Day-case arthroplasty is gaining popularity in Europe. We report outcomes from the first 12 months following implementation of a day-case pathway for unicompartmental knee arthroplasty (UKA) and total hip arthroplasty (THA) in an NHS hospital. Methods. A total of 47 total hip arthroplasty (THA) and 24 unicompartmental knee arthroplasty (UKA) patients were selected for the day-case arthroplasty pathway, based on preoperative fitness and agreement to participate. Data were likewise collected for a matched control group (n = 58) who followed the standard pathway three months prior to the implementation of the day-case pathway. We report same-day discharge (SDD) success, reasons for delayed discharge, and patient-reported outcomes. Overall length of stay (LOS) for all lower limb arthroplasty was recorded to determine the wider impact of implementing a day-case pathway. Results. Patients on the day-case pathway achieved SDD in 47% (22/47) of THAs and 67% (16/24) of UKAs. The most common reasons for failed SDD were nausea, hypotension, and pain, which were strongly associated with the use of fentanyl in the spinal anaesthetic. Complications and patient-reported outcomes were not significantly different between groups. Following the introduction of the day-case pathway, the mean LOS reduced significantly by 0.7, 0.6, and 0.5 days respectively in THA, UKA, and total knee arthroplasty cases (p < 0.001). Conclusion. Day-case pathways are feasible in an NHS set-up with only small changes required. We do not recommend fentanyl in the spinal anaesthetic for day-case patients. An important benefit seen in our unit is the so-called ‘day-case effect’, with a significant reduction in mean LOS seen across all lower limb arthroplasty. Cite this article: Bone Jt Open 2021;2(11):900–908

Aims. This study aimed to evaluate whether an enhanced recovery protocol (ERP) for arthroplasty established during the COVID-19 pandemic at a safety net hospital can be associated with a decrease in hospital length of stay (LOS) and an increase in same-day discharges (SDDs) without increasing acute adverse events. Methods. A retrospective review of 124 consecutive primary arthroplasty procedures performed after resuming elective procedures on 11 May 2020 were compared to the previous 124 consecutive patients treated prior to 17 March 2020, at a single urban safety net hospital. Revision arthroplasty and patients with < 90-day follow-up were excluded. The primary outcome measures were hospital LOS and the number of SDDs. Secondary outcome measures included 90-day complications, 90-day readmissions, and 30day emergency department (ED) visits. Results. The mean LOS was significantly reduced from 2.02 days (SD 0.80) in the pre-COVID cohort to 1.03 days (SD 0.65) in the post-COVID cohort (p < 0.001). No patients in the pre-COVID group were discharged on the day of surgery compared to 60 patients (48.4%) in the post-COVID group (p < 0.001). There were no significant differences in 90-day complications (13.7% (n = 17) vs 9.7% (n = 12); p = 0.429), 30-day ED visits (1.6% (n = 2) vs 3.2% (n = 4); p = 0.683), or 90-day readmissions (2.4% (n = 3) vs 1.6% (n = 2); p = 1.000) between the pre-COVID and post-COVID groups, respectively. Conclusion. Through use of an ERP, arthroplasty procedures were successfully resumed at a safety net hospital with a shorter LOS and increased SDDs without a difference in acute adverse events. The resulting increase in healthcare value therefore may be considered a ‘silver lining’ to the moratorium on elective arthroplasty during the COVID-19 pandemic. These improved efficiencies are expected to continue in post-pandemic era. Cite this article: Bone Jt Open 2021;2(10):871–878

Aims. Intra-articular administration of antibiotics during primary total knee arthroplasty (TKA) may represent a safe, cost-effective strategy to reduce the risk of acute periprosthetic joint infection (PJI). Vancomycin with an aminoglycoside provides antimicrobial cover for most organisms isolated from acute PJI after TKA. However, the intra-articular doses required to achieve sustained therapeutic intra-articular levels while remaining below toxic serum levels is unknown. The purpose of this study is to determine the intra-articular and serum levels of vancomycin and tobramycin over the first 24 hours postoperatively after intra-articular administration in primary cementless TKA. Methods. A prospective cohort study was performed. Patients were excluded if they had poor renal function, known allergic reaction to vancomycin or tobramycin, received intravenous vancomycin, or were scheduled for same-day discharge. All patients received 600 mg tobramycin and 1 g of vancomycin powder suspended in 25 cc of normal saline and injected into the joint after closure of the arthrotomy. Serum from peripheral venous blood and drain fluid samples were collected at one, four, and 24 hours postoperatively. All concentrations are reported in µg per ml. Results. A total of 22 patients were included in final analysis. At one, four, and 24 hours postoperatively, mean (95% confidence interval (CI)) serum concentrations were 2.4 (0.7 to 4.1), 5.0 (3.1 to 6.9), and 4.8 (2.8 to 6.9) for vancomycin and 4.9 (3.4 to 6.3), 7.0 (5.8 to 8.2), and 1.3 (0.8 to 1.8) for tobramycin; intra-articular concentrations were 1,900.6 (1,492.5 to 2,308.8), 717.9 (485.5 to 950.3), and 162.2 (20.5 to 304.0) for vancomycin and 2,105.3 (1,389.9 to 2,820.6), 403.2 (266.6 to 539.7), and 98.8 (0 to 206.5) for tobramycin. Conclusion. Intra-articular administration of 1 g of vancomycin and 600 mg of tobramycin as a solution after closure of the arthrotomy in primary cementless TKA achieves therapeutic intra-articular concentrations over the first 24 hours postoperatively and does not reach sustained toxic levels in peripheral blood. Cite this article: Bone Joint J 2021;103-B(11):1702–1708

Aims. The proportion of arthroplasties performed in the ambulatory setting has increased considerably. However, there are concerns whether same-day discharge may increase the risk of complications. The aim of this study was to compare 90-day outcomes between inpatient arthroplasties and outpatient arthroplasties performed at an ambulatory surgery centre (ASC), and determine whether there is a learning curve associated with performing athroplasties in an ASC. Methods. Among a single-surgeon cohort of 970 patients who underwent arthroplasty at an ASC, 854 (88.0%) were matched one-to-one with inpatients based on age, sex, American Society of Anesthesiologists (ASA) grade, BMI, and procedure (105 could not be adequately matched and 11 lacked 90-day follow-up). The cohort included 281 total hip arthroplasties (THAs) (32.9%), 267 unicompartmental knee arthroplasties (31.3%), 242 primary total knee arthroplasties (TKAs) (28.3%), 60 hip resurfacings (7.0%), two revision THAs (0.3%), and two revision TKAs (0.3%). Outcomes included readmissions, reoperations, visits to the emergency department, unplanned clinic visits, and complications. Results. The inpatient and outpatient groups were similar in all demographic variables, reflecting successful matching. The reoperation rate was 0.9% in both cohorts (p = 1.000). Rates of readmission (2.0% inpatient vs 1.6% outpatient), any complications (5.9% vs 5.6%), minor complications (4.2% vs 3.9%), visits to the emergency department (2.7% vs 1.4%), and unplanned clinic visits (5.7% vs 5.5%) were lower in the outpatient group but did not reach significance with the sample size studied. A learning curve may exist, as seen by significant reductions in the reoperation and overall complication rates among outpatient arthroplasties over time (p = 0.032 and p = 0.007, respectively), despite those in this group becoming significantly older and heavier (both p < 0.001) during the study period. Conclusion. Arthroplasties performed at ASCs appear to be safe in appropriately selected patients, but may be associated with a learning curve as shown by the significant decrease in complication and reoperation rates during the study period. Cite this article: Bone Joint J 2021;103-B(7 Supple B):84–90

Aims. The aim of this prospective multicentre study was to describe trends in length of stay and early complications and readmissions following unicompartmental knee arthroplasty (UKA) performed at eight different centres in Denmark using a fast-track protocol and to compare the length of stay between centres with high and low utilization of UKA. Methods. We included data from eight dedicated fast-track centres, all reporting UKAs to the same database, between 2010 and 2018. Complete ( > 99%) data on length of stay, 90-day readmission, and mortality were obtained during the study period. Specific reasons for a length of stay of > two days, length of stay > four days, and 30- and 90-day readmission were recorded. The use of UKA in the different centres was dichotomized into ≥ 20% versus < 20% of arthroplasties which were undertaken being UKAs, and ≥ 52 UKAs versus < 52 UKAs being undertaken annually. Results. A total of 3,927 procedures were included. Length of stay (mean 1.1 days (SD 1.1), median 1 (IQR 0 to 1)) was unchanged during the study period. The proportion of procedures with a length of stay > two days was also largely unchanged during this time. The percentage of patients discharged on the day of surgery varied greatly between centres (0% to 50% (0 to 481)), with centres with high UKA utilization (both usage and volume) having a larger proportion of same-day discharges. The 30- and 90-day readmissions were 166 (4.2%) and 272 (6.9%), respectively; the 90-day mortality was 0.08% (n = 3). Conclusion. Our findings suggest general underutilization of the potential for quicker recovery following UKA in a fast-track setup. Cite this article: Bone Joint J 2020;102-B(9):1167–1175

The August 2023 Research Roundup³⁶⁰ looks at: Can artificial intelligence improve the readability of patient education materials?; What is the value of radiology input during a multidisciplinary orthopaedic oncology conference?; Periprosthetic joint infection in patients with multiple arthroplasties; Orthopedic Surgery and Anesthesiology Surgical Improvement Strategies Project - Phase III outcomes; Knot tying in arthroplasty and arthroscopy causes lesions to surgical gloves: a potential risk of infection; Vascular calcification of the ankle in plain radiographs equals diabetes mellitus?

Aims

This study aims to determine difference in annual rate of early-onset (≤ 90 days) deep surgical site infection (SSI) following primary total knee arthroplasty (TKA) for osteoarthritis, and to identify risk factors that may be associated with infection.

The February 2023 Spine Roundup³⁶⁰ looks at: S2AI screws: At what cost?; Just how good is spinal deformity surgery?; Is 80 years of age too late in the day for spine surgery?; Factors affecting the accuracy of pedicle screw placement in robot-assisted surgery; Factors causing delay in discharge in patients eligible for ambulatory lumbar fusion surgery; Anterior cervical discectomy or fusion and selective laminoplasty for cervical spondylotic myelopathy; Surgery for cervical radiculopathy: what is the complication burden?; Hypercholesterolemia and neck pain; Return to work after surgery for cervical radiculopathy: a nationwide registry-based observational study.

The June 2024 Hip & Pelvis Roundup³⁶⁰ looks at: Machine learning did not outperform conventional competing risk modelling to predict revision arthroplasty; Unravelling the risks: incidence and reoperation rates for femoral fractures post-total hip arthroplasty; Spinal versus general anaesthesia for hip arthroscopy: a COVID-19 pandemic- and opioid epidemic-driven study; Development and validation of a deep-learning model to predict total hip arthroplasty on radiographs; Ambulatory centres lead in same-day hip and knee arthroplasty success; Exploring the impact of smokeless tobacco on total hip arthroplasty outcomes: a deeper dive into postoperative complications.

The February 2023 Knee Roundup³⁶⁰ looks at: Machine-learning models: are all complications predictable?; Positive cultures can be safely ignored in revision arthroplasty patients that do not meet the 2018 International Consensus Meeting Criteria; Spinal versus general anaesthesia in contemporary primary total knee arthroplasty; Preoperative pain and early arthritis are associated with poor outcomes in total knee arthroplasty; Risk factors for infection and revision surgery following patellar tendon and quadriceps tendon repairs; Supervised versus unsupervised rehabilitation following total knee arthroplasty; Kinematic alignment has similar outcomes to mechanical alignment: a systematic review and meta-analysis; Lifetime risk of revision after knee arthroplasty influenced by age, sex, and indication; Risk factors for knee osteoarthritis after traumatic knee injury.

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.

The December 2023 Knee Roundup³⁶⁰ looks at: Obesity is associated with greater improvement in patient-reported outcomes following primary total knee arthroplasty; Does mild flexion of the femoral prosthesis in total knee arthroplasty result in better early postoperative outcomes?; Robotic or manual total knee arthroplasty: a randomized controlled trial; Patient-relevant outcomes following first revision total knee arthroplasty, by diagnosis: an analysis of implant survivorship, mortality, serious medical complications, and patient-reported outcome measures using the National Joint Registry data set; Sagittal alignment in total knee arthroplasty: are there any discrepancies between robotic-assisted and manual axis orientation?; Tourniquet use does not impact recovery trajectory in total knee arthroplasty; Impact of proximal tibial varus anatomy on survivorship after medial unicondylar knee arthroplasty; Bone cement directly to the implant in primary total knee arthroplasty?; Maintaining joint line obliquity optimizes outcomes in patients with constitutionally varus knees.

Aims

The rate of day-case total knee arthroplasty (TKA) in the UK is currently approximately 0.5%. Reducing length of stay allows orthopaedic providers to improve efficiency, increase operative throughput, and tackle the rising demand for joint arthroplasty surgery and the COVID-19-related backlog. Here, we report safe delivery of day-case TKA in an NHS trust via inpatient wards with no additional resources.

The use of artificial intelligence (AI) is rapidly growing across many domains, of which the medical field is no exception. AI is an umbrella term defining the practical application of algorithms to generate useful output, without the need of human cognition. Owing to the expanding volume of patient information collected, known as ‘big data’, AI is showing promise as a useful tool in healthcare research and across all aspects of patient care pathways. Practical applications in orthopaedic surgery include: diagnostics, such as fracture recognition and tumour detection; predictive models of clinical and patient-reported outcome measures, such as calculating mortality rates and length of hospital stay; and real-time rehabilitation monitoring and surgical training. However, clinicians should remain cognizant of AI’s limitations, as the development of robust reporting and validation frameworks is of paramount importance to prevent avoidable errors and biases. The aim of this review article is to provide a comprehensive understanding of AI and its subfields, as well as to delineate its existing clinical applications in trauma and orthopaedic surgery. Furthermore, this narrative review expands upon the limitations of AI and future direction.

Cite this article: Bone Joint Res 2023;12(7):447–454.

Aims

Total hip arthroplasty (THA) is a common procedure to address pain and enhance function in hip disorders such as osteoarthritis. Despite its success, postoperative patient recovery exhibits considerable heterogeneity. This study aimed to investigate whether patients follow distinct pain trajectories following THA and identify the patient characteristics linked to suboptimal trajectories.

Literature surrounding artificial intelligence (AI)-related applications for hip and knee arthroplasty has proliferated. However, meaningful advances that fundamentally transform the practice and delivery of joint arthroplasty are yet to be realized, despite the broad range of applications as we continue to search for meaningful and appropriate use of AI. AI literature in hip and knee arthroplasty between 2018 and 2021 regarding image-based analyses, value-based care, remote patient monitoring, and augmented reality was reviewed. Concerns surrounding meaningful use and appropriate methodological approaches of AI in joint arthroplasty research are summarized. Of the 233 AI-related orthopaedics articles published, 178 (76%) constituted original research, while the rest consisted of editorials or reviews. A total of 52% of original AI-related research concerns hip and knee arthroplasty (n = 92), and a narrative review is described. Three studies were externally validated. Pitfalls surrounding present-day research include conflating vernacular (“AI/machine learning”), repackaging limited registry data, prematurely releasing internally validated prediction models, appraising model architecture instead of inputted data, withholding code, and evaluating studies using antiquated regression-based guidelines. While AI has been applied to a variety of hip and knee arthroplasty applications with limited clinical impact, the future remains promising if the question is meaningful, the methodology is rigorous and transparent, the data are rich, and the model is externally validated. Simple checkpoints for meaningful AI adoption include ensuring applications focus on: administrative support over clinical evaluation and management; necessity of the advanced model; and the novelty of the question being answered.

Cite this article: Bone Joint J 2022;104-B(12):1292–1303.