To explore a novel machine learning model to evaluate the vertebral fracture risk using Decision Tree model and train the model by Bone Mineral Density (BMD) of different compartments of vertebral body. We collected a Computed Tomography image dataset, including 10 patients with osteoporotic fracture and 10 patients without osteoporotic fracture. 40 non-fracture Vertebral bodies from T11 to L5 were segmented from 10 patients with osteoporotic fracture in the CT database and 53 non-fracture Vertebral bodies from T11 to L5 were segmented from 10 patients without osteoporotic fracture in the CT database. Based on the biomechanical properties, 93 vertebral bodies were further segmented into 11 compartments: eight trabecular bone, cortical shell, top and bottom endplate. BMD of these 11 compartments was calculated based on the HU value in CT images. Decision tree model was used to build fracture prediction model, and Support Vector Machine was built as a compared model. All BMD data was shuffled to a random order. 70% of data was used as training data, and 30% left was used as test data. Then, training prediction accuracy and testing prediction accuracy were calculated separately in the two models. The training accuracy of Decision Tree model is 100% and testing accuracy is 92.14% after trained by BMD data of 11 compartments of the vertebral body. The type I error is 7.14% and type II error is 0%. The training accuracy of Support Vector Machine model is 100% and the testing accuracy is 78.57%. The type I error is 17.86% and type II error is 3.57%. The performance of vertebral body fracture prediction using Decision Tree is significantly higher than using Support Vector Machine. The Decision Tree model is a potential risk assessment method for clinical application. The pilot evidence showed that Decision Tree prediction model overcomes the overfitting drawback of Support Vector Machine Model. However, larger dataset and cohort study should be conducted for further evidence

Economic evaluation provides a framework for assessing the costs and consequences of alternative programmes or interventions. One common vehicle for economic evaluations in the healthcare context is the decision-analytic model, which synthesizes information on parameter inputs (for example, probabilities or costs of clinical events or health states) from multiple sources and requires application of mathematical techniques, usually within a software program. A plethora of decision-analytic modelling-based economic evaluations of orthopaedic interventions have been published in recent years. This annotation outlines a number of issues that can help readers, reviewers, and decision-makers interpret evidence from decision-analytic modelling-based economic evaluations of orthopaedic interventions.

Cite this article: Bone Joint J 2023;105-B(1):17–20.

Background and Purpose. The STarT Back approach comprises subgrouping of LBP patients according to risk of persistent LBP-related disability, and matches patients to appropriate treatments. In a clinical trial and implementation study, this stratified care approach was clinically and cost-effective compared to usual non-stratified care. However, the long-term cost- effectiveness is unknown, and could be established with decision modelling. A systematic review of model-based economic evaluations in LBP found shortcomings with existing models, including inadequate characterisation of the condition in health states and absence of long-term modelling. This study conceptualises the first decision model of this stratified care approach for LBP management, and assesses long-term cost-effectiveness. Methods. A cost-utility analysis from the NHS perspective compared stratified care with usual care, in patients consulting in primary care with non-specific LBP. A Markov state-transition model was constructed where long-term patient prognosis over ten years was dependent upon physical function achieved at twelve months. Consultation with experts helped define condition health states, inform the long-term modelling, and choice of sensitivity analyses. Results. Preliminary base-case results indicate this model of stratified care is cost-effective over a ten-year time horizon, delivering 0.10 additional quality-adjusted life years (QALYs) at a cost-saving of £100.27 per patient. Sensitivity analyses indicate the approach is likely to be cost-effective in all scenarios, and cost-saving in most, although sensitive to assumptions regarding long-term patient prognosis. Analysis from the societal perspective improved the associated cost-savings. Conclusion. It is likely that implementation of this stratified care model will help reduce unnecessary healthcare usage, whilst improving patient quality of life. No conflicts of interest. Funding: Research stipend for JAH by the Institute for Primary Care & Health Sciences, Keele University

Is Non-Weight-Bearing Necessary? (INWN) is a pragmatic multicentre randomised controlled trial comparing immediate protected weight-bearing (IWB) with non-weight-bearing cast immobilisation (NWB) following ankle fracture fixation (ORIF). This trial compares; functional outcomes, complication rates and performs an economic analysis to estimate cost-utility. IWB within 24hrs was compared to NWB, following ORIF of all types of unstable ankle fractures. Skeletally immature patients and tibial plafond fractures were excluded. Functional outcomes were assessed by the Olerud-Molander Ankle Score (OMAS) and RAND-36 Item Short Form Survey (SF-36) taken at regular follow-up intervals up to one year. A cost-utility analysis via decision tree modelling was performed to derive an incremental cost effectiveness ratio (ICER). A standard gamble health state valuation model utilising SF-36 scores was used to calculate Quality Adjusted Life Years (QALYs) for each arm. We recruited 160 patients (80 per arm), aged 15 to 94 years (M = 45.5), 54% female. Complication rates were similar in both groups. IWB demonstrated a consistently higher OMAS score, with significant values at 6 weeks (MD=10.4, p=0.005) and 3 months (MD 12.0, p=0.003). Standard gamble utility values demonstrated consistently higher values (a score of 1 equals perfect health) with IWB, significant at 3 months (Ẋ = 0.75 [IWB] / 0.69 [NWB], p=0.018). Cost-utility analysis demonstrated NWB is €798.02 more expensive and results in 0.04 fewer QALYs over 1 year. This results in an ICER of −€21,682.42/QALY. This negative ICER indicates cost savings of €21,682.42 for every QALY (25 patients = 1 QALY gain) gained implementing an IWB regime. IWB demonstrates a superior functional outcome, greater cost savings and similar complication rates, compared to NWB following ankle fracture fixation

Aims. The routine use of dual-mobility (DM) acetabular components in total hip arthroplasty (THA) may not be cost-effective, but an increasing number of patients undergoing THA have a coexisting spinal disorder, which increases the risk of postoperative instability, and these patients may benefit from DM articulations. This study seeks to examine the cost-effectiveness of DM components as an alternative to standard articulations in these patients. Patients and Methods. A decision analysis model was used to evaluate the cost-effectiveness of using DM components in patients who would be at high risk for dislocation within one year of THA. Direct and indirect costs of dislocation, incremental costs of using DM components, quality-adjusted life-year (QALY) values, and the probabilities of dislocation were derived from published data. The incremental cost-effectiveness ratio (ICER) was established with a willingness-to-pay threshold of $100 000/QALY. Sensitivity analysis was used to examine the impact of variation. Results. In the base case, patients with a spinal deformity were modelled to have an 8% probability of dislocation following primary THA based on published clinical ranges. Sensitivity analysis revealed that, at its current average price ($1000), DM is cost-effective if it reduces the probability of dislocation to 0.9%. The threshold cost at which DM ceased being cost-effective was $1180, while the ICER associated with a DM THA was $71 000 per QALY. Conclusion. These results indicate that under specific clinical and economic thresholds, DM components are a cost-effective form of treatment for patients with spinal deformity who are at high risk of dislocation after THA. Cite this article: Bone Joint J 2018;100-B:1297–1302

Introduction: Fondaparinux, a selective inhibitor of activated factor X, has been shown to reduce further the risk of venous thromboembolism (VTE) in major orthopaedic surgery compared to the low molecular weight heparin enoxaparin, when both were applied for 7 days after surgery. Aims: To compare the expected costs and clinical outcomes of fondaparinux with enoxaparin applied for 7 days after surgery, we conducted a cost-consequence analysis in patients undergoing major orthopaedic surgery, i.e. total hip replacement, total knee replacement and hip fracture repair. Methods: Our decision model included endpoints relevant in routine clinical practice and the natural history of VTE over a long term period of 5 years. Costs for prevention, diagnosis and treatment of VTE and its complications were estimated from the Belgian health care payer perspective. Analyses were conducted for different time horizons and for the three indications, separately, and then combined. Results: Overall, our results indicated that the initial investment in fondaparinux (cost per day: 10.39 Euros versus 3.74 Euros for enoxaparin) was soon compensated by savings due to avoided VTE events, with cost neutrality being achieved after 90 days and further savings being incurred over longer time periods mainly due to avoided post-thrombotic syndromes. These findings were most pronounced in patients undergoing hip fracture repair. Sensitivity analyses showed these findings to be robust for the three indications separately, and combined. Conclusions: We conclude that our analysis of health and economic consequences over a long term period, demonstrates the value for money of fondaparinux versus enoxaparin for the prevention of VTE events after total hip replacement, total knee replacement and hip fracture repair

Background: The rates of primary and revision knee arthroplasty in the United States have been increasing. Simultaneously, several studies have reported increased complication rates when these procedures are performed at low-volume centers. One innovation designed to improve knee arthroplasty outcomes is computer navigation, which aims to reduce revision rates by improving the alignment achieved at surgery. The purpose of this study was to examine the impact of hospital volume on the costeffectiveness of this new technology in order to determine its feasibility and the level of evidence that should be sought prior to its adoption. Methods: A Markov decision model was used to evaluate the cost-effectiveness of computer-assisted knee arthroplasty, in relation to hospital volume. Transition probabilities were estimated from the arthroplasty literature, and costs were based on the average reimbursement for primary and revision knee arthroplasty at out institution. Outcomes were measured in quality adjusted life years. Results: The results demonstrate that computer-assisted surgery becomes less cost-effective as the annual hospital volume decreases, as the cost of navigation increases, and as the impact on revision rates decreases. If a center performs 250 cases per year, computer navigation will be cost-effective if the annual revision rate is reduced by 2% per year over a twenty-year period. If a center performs 150 cases per year, computer navigation is cost-effective if it results in a 2.5% reduction in the annual revision rate over a twenty-year period. If a center performs only 25 cases per year, the annual reduction in revision rates must be 13% for computer navigation to be cost-effective. Conclusion: This analysis demonstrates that computer navigation is not likely to be a cost-effective investment in health care improvement in low volume joint replacement centers, where its benefit is most likely to be realized. However, it may be a cost-effective technology for higher volume joint replacement centers, where the decrease in the rate of knee revision needed to make the investment cost-effective is modest, if improvements in revisions rates with the use of this technology can be realized. This illustrates that hospital volume can have a substantial impact on the cost-effectiveness of new technology in surgery, and this should be carefully considered by any center considering such a large capital investment

Antibiotic-impregnated bone cement (ABC) is infrequently used in the North America for primary total hip arthroplasty (THA) due to concerns with cost, performance, and the possible development of antibiotic resistance. The purpose of this study is to examine the cost-effectiveness of using ABC in primary THA for osteoarthritis compared to the use of cement without antibiotics. A Markov decision model was used to determine if ABC is a cost-effective strategy for primary THA in patients with osteoarthritis. The model tabulates costs and quality adjusted life years (QALYs) accumulated by each patient to evaluate the cost-effectiveness of each strategy. Rates of revision for infection and aseptic loosening were estimated from the Norwegian Arthroplasty Register, and were used to determine the probability of transitioning to a revision arthroplasty for either infection or aseptic loosening. The model was also used to evaluate the cost-effectiveness of ABC when only revisions for infection are considered. Peri-operative mortality rates, utilities, and disutilities were estimated from the arthroplasty literature. Costs were also estimated from the literature using in-hospital resource use as the method of measurement for primary THA. The additional cost of using ABC ($600) was then added to the average cost of the initial procedure ($21,654). ABC is less expensive and more effective than standard cement when all revisions are considered, making the use of ABC the dominant strategy. When only revision for infection is considered, the use of ABC has an incremental cost-effectiveness ratio (ICER) of $37.335 per QALY compared to cement without antibiotics – which compares favorably with the cost-effectiveness of accepted medical procedures. Sensitivity analyses reveal that for all revisions the additional cost of ABC would need to be greater than $1500, or the average age of patients undergoing primary THA would need to be greater than eighty-three before the use of ABC would cost more than $50,000 per QALY gained. When only revision for infection is considered, the additional cost of ABC would need to exceed $650 before the cost of ABC would exceed $50,000 per QALY gained. Use of ABC for primary THA is cost-effective over a wide range of assumptions. Notably, when all revisions are considered, ABC is less costly and more effective than use of standard cement over the life span of the patients

Background. Prosthetic implants used in primary total hip replacements have a range of bearing surface combinations (metal-on-polyethylene, ceramic-on-polyethylene, ceramic-on-ceramic, metal-on-metal); head sizes (small <36mm, large 36mm+); and fixation techniques (cemented, uncemented, hybrid, reverse hybrid), which influence prosthesis survival, patient quality of life, and healthcare costs. This study compared the lifetime cost-effectiveness of implants to determine the optimal choice for patients of different age and gender profiles. Methods. In an economic decision Markov model, the probability that patients required one or more revision surgeries was estimated from analyses of UK and Swedish hip joint registries, for males and females aged <55, 55–64, 65–74, 75–84, and 85+ years. Implant and healthcare costs were estimated from hospital procurement prices, national tariffs, and the literature. Quality-adjusted life years were calculated using utility estimates, taken from Patient-Reported Outcome Measures data for hip procedures in the UK. Results. Optimal choices varied between traditionally used cemented metal-on-polyethylene and cemented ceramic-on-polyethylene implants. Small head cemented ceramic-on-polyethylene implants were optimal for males and females aged under 65. The optimal choice for adults aged 65 and older was small head cemented metal-on-polyethylene implants. Conclusions. The older the patient, the higher the probability that small head cemented metal-on-polyethylene implants are optimal. Small head cemented ceramic-on-polyethelyne implants are optimal for adults aged under 65. Our findings can influence NICE guidance, clinical practice, and commissioning of services. Funding. NIHR Research for Patient Benefit programme PB-PG-0613-31032

Pedicle screw fixation is a technically demanding procedure with potential difficulties and reoperation rates are currently on the order of 11%. The most common intraoperative practice for position assessment of pedicle screws is biplanar fluoroscopic imaging that is limited to two- dimensions and is associated to low accuracies. We have previously introduced a full-dimensional position assessment framework based on registering intraoperative X-rays to preoperative volumetric images with sufficient accuracies. However, the framework requires a semi-manual process of pedicle screw segmentation and the intraoperative X-rays have to be taken from defined positions in space in order to avoid pedicle screws' head occlusion. This motivated us to develop advancements to the system to achieve higher levels of automation in the hope of higher clinical feasibility. In this study, we developed an automatic segmentation and X-ray adequacy assessment protocol. An artificial neural network was trained on a dataset that included a number of digitally reconstructed radiographs representing pedicle screw projections from different points of view. This model was able to segment the projection of any pedicle screw given an X-ray as its input with accuracy of 93% of the pixels. Once the pedicle screw was segmented, a number of descriptive geometric features were extracted from the isolated blob. These segmented images were manually labels as ‘adequate’ or ‘not adequate’ depending on the visibility of the screw axis. The extracted features along with their corresponding labels were used to train a decision tree model that could classify each X-ray based on its adequacy with accuracies on the order of 95%. In conclusion, we presented here a robust, fast and automated pedicle screw segmentation process, combined with an accurate and automatic algorithm for classifying views of pedicle screws as adequate or not. These tools represent a useful step towards full automation of our pedicle screw positioning assessment system

The April 2024 Shoulder & Elbow Roundup³⁶⁰ looks at: Acute rehabilitation following traumatic anterior shoulder dislocation (ARTISAN): pragmatic, multicentre, randomized controlled trial; Prevalence and predisposing factors of neuropathic pain in patients with rotator cuff tears; Are two plates better than one? The clavicle fracture reimagined; A single cell atlas of frozen shoulder capsule identifies features associated with inflammatory fibrosis resolution; Complication rates and deprivation go hand in hand with total shoulder arthroplasty; Longitudinal instability injuries of the forearm; A better than “best-fit circle” method for glenoid bone loss assessment; 3D supraspinatus muscle volume and intramuscular fatty infiltration after arthroscopic rotator cuff repair.

Aims

To determine the major risk factors for unplanned reoperations (UROs) following corrective surgery for adult spinal deformity (ASD) and their interactions, using machine learning-based prediction algorithms and game theory.

Prediction tools are instruments which are commonly used to estimate the prognosis in oncology and facilitate clinical decision-making in a more personalized manner. Their popularity is shown by the increasing numbers of prediction tools, which have been described in the medical literature. Many of these tools have been shown to be useful in the field of soft-tissue sarcoma of the extremities (eSTS). In this annotation, we aim to provide an overview of the available prediction tools for eSTS, provide an approach for clinicians to evaluate the performance and usefulness of the available tools for their own patients, and discuss their possible applications in the management of patients with an eSTS.

Cite this article: Bone Joint J 2022;104-B(9):1011–1016.

Background. The management of the patella during primary total knee arthroplasty (TKA) is controversial. Despite the majority of patients reporting excellent outcomes following TKA, a common complaint is anterior knee pain. Resurfacing of the patella at the time of initial surgery has been proposed as a means of preventing anterior knee pain, however current evidence, including four recent meta-analyses, has failed to show clear superiority of patellar resurfacing. Therefore, the purpose of this study was to estimate the cost-effectiveness of patellar resurfacing compared to non-resurfacing in TKA. Methods. We conducted a cost-effectiveness analysis using a decision analytic model to represent a hypothetical patient cohort undergoing primary TKA. Each patient will receive a TKA either with the Patella Resurfaced or Not Resurfaced. Following surgery, patients can transition to one of three chronic health states: 1) Well Post-operative, 2) Patellofemoral Pain (PFP), or 3) Serious Adverse Event (AE), which we have defined as any event requiring Revision TKA, including: loosening/lysis, infection, instability, or fracture (Figure 1). We obtained revision rates following TKA for both resurfaced and unresurfaced cohorts using data from the 2014 Australian Registry. This data was chosen due to similarities between Australian and North American practice patterns and patient demographics, as well as the availability of longer term follow up data, up to 14 years postoperative. Our effectiveness outcome for the model was the quality-adjusted life year (QALY). We used utility scores obtained from the literature to calculate QALYs for each health state. Direct procedure costs were obtained from our institution's case costing department, and the billing fees for each procedure. We estimated cost-effectiveness from a Canadian publicly funded health care system perspective. All costs and quality of life outcomes were discounted at a rate of 5%. All costs are presented in 2015 Canadian dollars. Results. Our cost-effectiveness analysis suggests that TKA with patella resurfacing is a dominant procedure. Patients who receive primary TKA with non-resurfaced patella had higher associated costs over the first 14 years postoperative ($16,182 vs $15,720), and slightly lower quality of life (5.37 QALYs vs 6.01 QALYs). The revision rate for patellar resurfacing was 1.3%. If the rate of secondary resurfacing procedures is 0.5% or less, there is no difference in costs between the two procedures. Discussion. Our results suggest that, up to 14 years postoperative, resurfacing the patella in primary TKA is cost-effective compared to primary TKA without patellar resurfacing, due to the higher revision rate in this cohort of patients for secondary resurfacing. Our sensitivity analysis suggests that, among surgical practices that do not routinely perform secondary resurfacing procedures (estimated rate at our institution is 0.3%) there is no significant difference in costs. Although our results suggest that patella resurfacing results in higher quality of life, our model is limited by the availability and validity of utility outcome estimates reported in the literature for the long term follow up of patients following TKA with or without patella resurfacing and secondary resurfacing procedures

Introduction and Aims: Practice standards vary considerably for prophylactic pinning the contralateral hip opposite a scfe. This work provides a data-driven framework with which to analyse the risks, benefits, and costs of two modes of treatment: prophylactic pinning the normal side contralateral to a scfe versus observation; and pinning of subsequent slips. Method: A decision analysis model was constructed using the English language literature to estimate SCFE incidence and severity. The model framework assumes that if a hip is pinned prophylactically it will not slip. The benefits of prophylactic pinning are therefore determined by identifying the percentage of contralateral hips that will subsequently slip and then develop early osteoarthritis requiring total hip arthroplasty at a young age. In our cost analysis model, the cost of diagnosis, treatment, and follow-up was developed for the two treatment modes using actual hospital costs and standardised medicare reimbursement schedules for professional fees. Results: If a hip is not pinned prophylactically, there is a 7% risk of requiring a total hip arthroplasty in the contralateral hip at an early age due to osteoarthritis. This 7% is a combination of patients whose contralateral femoral epiphysis slipped moderately or severely and was pinned in a non-anatomic position (1.5% of the initial population) and patients whose substantial slip was not detected (5.5%). The risk of prophylactic pinning appears to be associated with a 0.3% chance of developing avascular necrosis. Other risks would include chances of infection or chondrolysis, although these have not been reported to date. If every patient is managed by the prophylactic pinning protocol, the total cost per patient, not including lost time at work or school, for pinning a slipped capital femoral epiphysis, prophylactically pinning the contra lateral side, and post-operative follow-up is $6266. Conversely, the total cost per patient for the second mode, pinning a slipped capital femoral epiphysis, post-operative follow-up and pinning of subsequent contralateral slips that are detected is $6864. Costs of later hip arthroplasty were not included. This analysis suggests that costs to a national health care system for treatment of SCFE would not increase by prophylactic contralateral pinning. Conclusions: Prophylactic pinning of the contralateral side is merited on the basis of both risk/benefit and cost-effectiveness analyses. Ultimately, the decision must incorporate the physician’s assessment of patient risk factors including: age, weight, co-morbidities, sports activities, the likelihood and feasibility of regular follow-up, and the patient’s and parents’ acceptance of prophylactic surgery

Aims

A pilon fracture is a severe ankle joint injury caused by high-energy trauma, typically affecting men of working age. Although relatively uncommon (5% to 7% of all tibial fractures), this injury causes among the worst functional and health outcomes of any skeletal injury, with a high risk of serious complications and long-term disability, and with devastating consequences on patients’ quality of life and financial prospects. Robust evidence to guide treatment is currently lacking. This study aims to evaluate the clinical and cost-effectiveness of two surgical interventions that are most commonly used to treat pilon fractures.

Aims

The use of technology to assess balance and alignment during total knee surgery can provide an overload of numerical data to the surgeon. Meanwhile, this quantification holds the potential to clarify and guide the surgeon through the surgical decision process when selecting the appropriate bone recut or soft tissue adjustment when balancing a total knee. Therefore, this paper evaluates the potential of deploying supervised machine learning (ML) models to select a surgical correction based on patient-specific intra-operative assessments.

Aims

The primary aim of the study was to perform an analysis to identify the cost per quality-adjusted life-year (QALY) of robot-assisted unicompartmental knee arthroplasty (rUKA) relative to manual total knee arthroplasty (TKA) and unicompartmental knee arthroplasty (UKA) for patients with isolated medial compartment osteoarthritis (OA) of the knee. Secondary aims were to assess how case volume and length of hospital stay influenced the relative cost per QALY.