Aims. This study aimed to compare the performance of survival prediction models for bone metastases of the extremities (BM-E) with pathological fractures in an Asian cohort, and investigate patient characteristics associated with survival. Methods. This retrospective cohort study included 469 patients, who underwent surgery for BM-E between January 2009 and March 2022 at a tertiary hospital in South Korea. Postoperative survival was calculated using the PATHFx3.0, SPRING13, OPTIModel, SORG, and IOR models. Model performance was assessed with area under the curve (AUC), calibration curve, Brier score, and decision curve analysis. Cox regression analyses were performed to evaluate the factors contributing to survival. Results. The SORG model demonstrated the highest discriminatory accuracy with AUC (0.80 (95% confidence interval (CI) 0.76 to 0.85)) at 12 months. In calibration analysis, the PATHfx3.0 and OPTIModel models underestimated survival, while the SPRING13 and IOR models overestimated survival. The SORG model exhibited excellent calibration with intercepts of 0.10 (95% CI -0.13 to 0.33) at 12 months. The SORG model also had lower Brier scores than the null score at three and 12 months, indicating good overall performance. Decision curve analysis showed that all five survival prediction models provided greater net benefit than the default strategy of operating on either all or no patients. Rapid growth cancer and low serum albumin levels were associated with three-, six-, and 12-month survival. Conclusion. State-of-art survival prediction models for BM-E (PATHFx3.0, SPRING13, OPTIModel, SORG, and IOR models) are useful clinical tools for orthopaedic surgeons in the decision-making process for the treatment in Asian patients, with SORG models offering the best predictive performance. Rapid growth cancer and serum albumin level are independent, statistically significant factors contributing to survival following surgery of BM-E. Further refinement of survival prediction models will bring about informed and patient-specific treatment of BM-E. Cite this article: Bone Joint J 2024;106-B(2):203–211

Aims. To develop and internally validate a preoperative clinical prediction model for acute adjacent vertebral fracture (AVF) after vertebral augmentation to support preoperative decision-making, named the after vertebral augmentation (AVA) score. Methods. In this prognostic study, a multicentre, retrospective single-level vertebral augmentation cohort of 377 patients from six Japanese hospitals was used to derive an AVF prediction model. Backward stepwise selection (p < 0.05) was used to select preoperative clinical and imaging predictors for acute AVF after vertebral augmentation for up to one month, from 14 predictors. We assigned a score to each selected variable based on the regression coefficient and developed the AVA scoring system. We evaluated sensitivity and specificity for each cut-off, area under the curve (AUC), and calibration as diagnostic performance. Internal validation was conducted using bootstrapping to correct the optimism. Results. Of the 377 patients used for model derivation, 58 (15%) had an acute AVF postoperatively. The following preoperative measures on multivariable analysis were summarized in the five-point AVA score: intravertebral instability (≥ 5 mm), focal kyphosis (≥ 10°), duration of symptoms (≥ 30 days), intravertebral cleft, and previous history of vertebral fracture. Internal validation showed a mean optimism of 0.019 with a corrected AUC of 0.77. A cut-off of ≤ one point was chosen to classify a low risk of AVF, for which only four of 137 patients (3%) had AVF with 92.5% sensitivity and 45.6% specificity. A cut-off of ≥ four points was chosen to classify a high risk of AVF, for which 22 of 38 (58%) had AVF with 41.5% sensitivity and 94.5% specificity. Conclusion. In this study, the AVA score was found to be a simple preoperative method for the identification of patients at low and high risk of postoperative acute AVF. This model could be applied to individual patients and could aid in the decision-making before vertebral augmentation. Cite this article: Bone Joint J 2022;104-B(1):97–102

Over 300,000 total hip arthroplasties (THA) are performed annually in the USA. Surgical Site Infections (SSI) are one of the most common complications and are associated with increased morbidity, mortality and cost. Risk factors for SSI include obesity, diabetes and smoking, but few studies have reported on the predictive value of pre-operative blood markers for SSI. The purpose of this study was to create a clinical prediction model for acute SSI (classified as either superficial, deep and overall) within 30 days of THA based on commonly ordered pre-operative lab markers and using data from the American College of Surgeons National Surgical Quality Improvement Program (ACS-NSQIP) database. All adult patients undergoing an elective unilateral THA for osteoarthritis from 2011–2016 were identified from the NSQIP database using Current Procedural Terminology (CPT) codes. Patients with active or chronic, local or systemic infection/sepsis or disseminated cancer were excluded. Multivariate logistic regression was used to determine coefficients, with manual stepwise reduction. Receiver Operating Characteristic (ROC) curves were also graphed. The SSI prediction model included the following covariates: body mass index (BMI) and sex, comorbidities such as congestive heart failure (CHF), chronic obstructive pulmonary disease (COPD), smoking, current/previous steroid use, as well as pre-operative blood markers, albumin, alkaline phosphate, blood urea nitrogen (BUN), creatinine, hematocrit, international normalized ratio (INR), platelets, prothrombin time (PT), sodium and white blood cell (WBC) levels. Since the data met logistic assumption requirements, bootstrap estimation was used to measure internal validity. The area under the ROC curve for final derivations along with McFadden's R-squared were utilized to compare prediction models. A total of 130,619 patients were included with the median age of patients at time of THA was 67 years (mean=66.6+11.6 years) with 44.8% (n=58,757) being male. A total of 1,561 (1.20%) patients had a superficial or deep SSI (overall SSI). Of all SSI, 45.1% (n=704) had a deep SSI and 55.4% (n=865) had a superficial SSI. The incidence of SSI occurring annually decreased from 1.44% in 2011 to 1.16% in 2016. Area under the ROC curve for the SSI prediction model was 0.79 and 0.78 for deep and superficial SSI, respectively and 0.71 for overall SSI. CHF had the largest effect size (Odds Ratio(OR)=2.88, 95% Confidence Interval (95%CI): 1.56 – 5.32) for overall SSI risk. Albumin (OR=0.44, 95% CI: 0.37 – 0.52, OR=0.31, 95% CI: 0.25 – 0.39, OR=0.48, 95% CI: 0.41 – 0.58) and sodium (OR=0.95, 95% CI: 0.93 – 0.97, OR=0.94, 95% CI: 0.91 – 0.97, OR=0.95, 95% CI: 0.93 – 0.98) levels were consistently significant in all clinical prediction models for superficial, deep and overall SSI, respectively. In terms of pre-operative blood markers, hypoalbuminemia and hyponatremia are both significant risk factors for superficial, deep and overall SSI. In this large NSQIP database study, we were able to create an SSI prediction model and identify risk factors for predicting acute superficial, deep and overall SSI after THA. To our knowledge, this is the first clinical model whereby pre-operative hyponatremia (in addition to hypoalbuminemia) levels have been predictive of SSI after THA. Although the model remains without external validation, it is a vital starting point for developing a risk prediction model for SSI and can help physicians mitigate risk factors for acute SSI post THA

Total knee arthroplasty (TKA) is the most commonly performed elective orthopaedic procedure. With an increasingly aging population, the number of TKAs performed is expected to be ∼2,900 per 100,000 by 2050. Surgical Site Infections (SSI) after TKA can have significant morbidity and mortality. The purpose of this study was to construct a risk prediction model for acute SSI (classified as either superficial, deep and overall) within 30 days of a TKA based on commonly ordered pre-operative blood markers and using audited administrative data from the American College of Surgeons National Surgical Quality Improvement Program (ACS-NSQIP) database. All adult patients undergoing an elective unilateral TKA for osteoarthritis from 2011–2016 were identified from the NSQIP database using Current Procedural Terminology (CPT) codes. Patients with active or chronic, local or systemic infection/sepsis or disseminated cancer were excluded. Multivariate logistic regression was conducted to estimate coefficients, with manual stepwise reduction to construct models. Bootstrap estimation was administered to measure internal validity. The SSI prediction model included the following co-variates: body mass index (BMI) and sex, comorbidities such as congestive heart failure (CHF), chronic obstructive pulmonary disease (COPD), smoking, current/previous steroid use, as well as pre-operative blood markers, albumin, alkaline phosphatase, blood urea nitrogen (BUN), creatinine, hematocrit, international normalized ratio (INR), platelets, prothrombin time (PT), sodium and white blood cell (WBC) levels. To compare clinical models, areas under the receiver operating characteristic (ROC) curves and McFadden's R-squared values were reported. The total number of patients undergoing TKA were 210,524 with a median age of 67 years (mean age of 66.6 + 9.6 years) and the majority being females (61.9%, N=130,314). A total of 1,674 patients (0.8%) had a SSI within 30 days of the index TKA, of which N=546 patients (33.2%) had a deep SSI and N=1,128 patients (67.4%) had a superficial SSI. The annual incidence rate of overall SSI decreased from 1.60% in 2011 to 0.68% in 2016. The final risk prediction model for SSI contained, smoking (OR=1.69, 95% CI: 1.31 – 2.18), previous/current steroid use (OR=1.66, 95% CI: 1.23 – 2.23), as well as the pre-operative lab markers, albumin (OR=0.46, 95% CI: 0.37 – 0.56), blood urea nitrogen (BUN, OR=1.01, 95% CI: 1 – 1.02), international normalized ratio (INR, OR=1.22, 95% CI:1.05 – 1.41), and sodium levels (OR=0.94, 95% CI: 0.91 – 0.98;). Area under the ROC curve for the final model of overall SSI was 0.64. Models for deep and superficial SSI had ROC areas of 0.68 and 0.63, respectively. Albumin (OR=0.46, 95% CI: 0.37 – 0.56, OR=0.33, 95% CI: 0.27 – 0.40, OR=0.75, 95% CI: 0.59 – 0.95) and sodium levels (OR=0.94, 95% CI: 0.91 – 0.98, OR=0.96, 95% CI: 0.93 – 0.99, OR=0.97, 95% CI: 0.96 – 0.99) levels were consistently significant in all prediction models for superficial, deep and overall SSI, respectively. Overall, hypoalbuminemia and hyponatremia are both significant risk factors for superficial, deep and overall SSI. To our knowledge, this is the first prediction model for acute SSI post TKA whereby hyponatremia (and hypoalbuminemia) are predictive of SSI. This prediction model can help fill an important gap for predicting risk factors for SSI after TKA and can help physicians better optimize patients prior to TKA

Early and accurate prediction of hospital length-of-stay (LOS) in patients undergoing knee replacement is important for economic and operational reasons. Few studies have systematically developed a multivariable model to predict LOS. We performed a retrospective cohort study of 1609 patients aged ≥ 50 years who underwent elective, primary total or unicompartmental knee replacements. Pre-operative candidate predictors included patient demographics, knee function, self-reported measures, surgical factors and discharge plans. In order to develop the model, multivariable regression with bootstrap internal validation was used. The median LOS for the sample was four days (interquartile range 4 to 5). Statistically significant predictors of longer stay included older age, greater number of comorbidities, less knee flexion range of movement, frequent feelings of being down and depressed, greater walking aid support required, total (versus unicompartmental) knee replacement, bilateral surgery, low-volume surgeon, absence of carer at home, and expectation to receive step-down care. For ease of use, these ten variables were used to construct a nomogram-based prediction model which showed adequate predictive accuracy (optimism-corrected R. 2. = 0.32) and calibration. If externally validated, a prediction model using easily and routinely obtained pre-operative measures may be used to predict absolute LOS in patients following knee replacement and help to better manage these patients. . Cite this article: Bone Joint J 2013;95-B:1490–6

A predictive model for final kyphosis was tested by evaluating the radiographs of forty-three patients with traumatic burst fractures. Since clinical outcomes are related to final kyphosis in the ambulatory patient rather than on the initial supine injury radiograph, the ability to predict final kyphosis is beneficial in determining treatment. This study demonstrated that in the appropriately selected patient for conservative care, the limit of final-kyphosis(Kf) can be predicted from the intial-kyphosis(KI) , such that Kf= < KI+.5KI . Outliers from this equation were patients who had unrecognized posterior column fractures, superior and inferior end-plate fractures, and/or multiple level of injury. The purpose of this study was to define a prediction model that afforded clinicians the ability to define final kyphosis from initial supine films in order to guide the management of stable burst fractures. This study has demonstrated that as a rule of thumb, the final absolute kyphosis for stable burst fractures can be expected to be up to Ki (initial absolute kyphosis) + 1.5Ki. Outliers were found to be fractures with unrecognized posterior element injury, both superior and inferior endplate fractures and multiple level injuries. The final kyphosis is clinically more relevant than the initial kyphosis in terms of functional outcome after conservative management. A prediction model for final kyphosis based on initial injury films can help guide the clinician for optimal management. Retrospective radiographic analysis was performed on forty-three patients with a minimum follow up six months. All patients suffered traumatic burst fractures, which were deemed stable as to be satisfactorily managed in a brace. Serial radiographs were used to determine initial (Ki) and final (Kf), Kyphosis angles. Predicted Kf was determined using the equation Kf =Ki + 1.5 Ki. The initial absolute kyphosis was the measured kyphosis using the Cobb technique and including the loss of the expected normal lordosis of that spinal segment. Inclusion criteria included burst fractures at between levels T10 – L3 in the neurologically intact patient. The equation accurately predicted the final outcome , Kf, in 70 % of the cases. In 20% of the cases, the Kf was less than expected. (Acceptable clinical result). In 10% of the cases, Kf was greater than predicted or achieved a clinically unacceptable kyphotic angulation requiring secondary surgery. In this group of outliers, post-hoc analysis identified unrecognized posterior element injury, both superior and inferior endplate fractures and multiple level injuries. In traumatic burst fractures, the goal of management is to protect the spine during healing while maintaining an acceptable alignment, which will not lead to late pain and deformity. A final absolute kyphosis angle, Kf, from twenty to thirty degrees has been variably regarded as a threshold to obtain a good clinical outcome. Criteria for stability have been previously documented, however variables are based on initial presentation. Aside from careful classification of the fracture type, the current “rule of thumb” prediction model for Kf may further help the clinician with management decisions

Fractures through the physis account for 18–30% of all paediatric fractures, leading to growth arrest in 5.5% of cases. We have limited knowledge to predict which physeal fractures result in growth arrest and subsequent deformity or limb length discrepancy. The purpose of this study is to identify factors associated with physeal growth arrest to improve patient outcomes. This prospective cohort study was designed to develop a clinical prediction model for growth arrest after physeal injury. Patients < 1 8 years old presenting within four weeks of injury were enrolled if they had open physes and sustained a physeal fracture of the humerus, radius, ulna, femur, tibia or fibula. Patients with prior history of same-site fracture or a condition known to alter bone growth or healing were excluded. Demographic data, potential prognostic indicators and radiographic data were collected at baseline, one and two years post-injury. A total of 167 patients had at least one year of follow-up. Average age at injury was 10.4 years, 95% CI [9.8,10.94]. Reduction was required in 51% of cases. Right-sided (52.5%) and distal (90.1%) fractures were most common. After initial reduction 52.5% of fractures had some form of residual angulation and/or displacement (38.5% had both). At one year follow-up, 34 patients (21.1%) had evidence of a bony bridge on plain radiograph, 10 (6.2%) had residual angulation (average 12.6°) and three had residual displacement. Initial angulation (average 22.4°) and displacement (average 5.8mm) were seen in 16/34 patients with bony bridge (48.5%), with 10 (30.3%) both angulated and displaced. Salter-Harris type II fractures were most common across all patients (70.4%) and in those with bony bridges (57.6%). At one year, 44 (27.3%) patients had evidence of closing/closed physes. At one year follow-up, there was evidence of a bony bridge across the physis in 21.1% of patients on plain film, and residual angulation and/or displacement in 8.1%. Initial angulation and/or displacement was present in 64.7% of patients showing possible evidence of growth arrest. The incidence of growth arrest in this patient population appears higher than past literature reports. However, plain film is an unreliable modality for assessing physeal bars and the true incidence may be lower. A number of patients were approaching skeletal maturity at time of injury and any growth arrest is likely to have less clinical significance in these cases. Further prospective long-term follow-up is required to determine the true incidence and impact of growth arrest

Introduction. Previous studies have shown that third body damage to the femoral head in metal-on-polyethylene hip replacement bearings can lead to accelerated wear of the polyethylene liners. The resulting damage patterns observed on retrieved metal heads are typically scratches and scrapes. The damage created in vitro must represent the third body damage that occurs clinically. A computational model was developed to predict the acceleration of wear of polyethylene articulating against in vitro damaged femoral heads. This involved using a damage registry from retrieval femoral heads to develop standardized templates of femoral head scratches statistically representative of retrieval damage. The aim of this study was to determine the wear rates of polyethylene liners articulating against retrievals and artificially damaged metal heads for the purpose of validating a computational wear prediction model; and to develop and validate an in vitro standardised femoral head damage protocol for pre-clinical testing of hip replacements. Materials and Methods. Twenty nine, 32mm diameter, metal-on-moderately cross-linked polyethylene bearings (Marathon. TM. ) inserted into Ti-6Al-4V shells (Pinnacle. ®). were tested in this study. All products were manufactured by DePuy Synthes, Warsaw, Indiana, USA. Following a retrieval study seven different damage patterns were defined, and these were applied to the femoral heads using a four-degree-of-freedom CNC milling machine (Figure 1). The ProSim 10-station pneumatic hip joint simulator (Simulation Solutions, UK) was used for experimental wear simulation using standard gait cycles and testing each experimental group for 3 million cycles. The acetabular cups were inclined at 35° on the simulator (equivalent to 45° in vivo). The wear volumes were determined using a microbalance (Mettler-Toledo XP205, Switzerland) at one million cycle intervals. Statistical analysis used was one way ANOVA followed by a post hoc analysis with significance taken at p<0.05. Results. Different damage patterns accelerated the wear of polyethylene at different rates (Figure 2). The moderately scratched and severely scratched heads caused a 2 fold (p<0.01) and 5.5 fold (p<0.01) increase when compared to the wear rate of the undamaged head group. However, the scraped damage caused a lower increase than the scratched heads, with a 1.4 fold (p=0.2) increase for the moderately scraped heads and 2.6 fold (p<0.01) increase for the severely scraped heads. The moderate hybrid and severe hybrid groups resulted in a similar increase to the scraped heads with 1.8 fold (p<0.01) increase with the moderate hybrid and 3 fold (p<0.01) increase with the severe hybrid. The wear of polyethylene against the mild hybrid and retrieved heads was not significantly different (p= 0.9) to the wear against undamaged heads. Discussion. A standardised protocol for generating in vitro damage representative of clinically occurring damage on femoral heads for preclinical testing purposes is needed. The wear rates of polyethylene liners articulating against the retrieval heads were similar to those articulating against the undamaged femoral heads. This study has shown the variations in wear rate of polyethylene bearing under different damage patterns generated in vitro. The wear prediction computational model predict similar trends of the wear acceleration reported in the experimental study

Numerous prediction tools are available for estimating postoperative risk following spine surgery. External validation studies have shown mixed results. We present the development, validation, and comparative evaluation of novel tool (NZSpine) for modelling risk of complications within 30 days of spine surgery. Data was gathered retrospectively from medical records of patients who underwent spine surgery at Waikato Hospital between January 2019 and December 2020 (n = 488). Variables were selected a priori based on previous evidence and clinical judgement. Postoperative adverse events were classified objectively using the Comprehensive Complication Index. Models were constructed for the occurrence of any complication and significant complications (based on CCI >26). Performance and clinical utility of the novel model was compared against SpineSage (. https://depts.washington.edu/spinersk/. ), an extant online tool which we have shown in unpublished work to be valid in our local population. Overall complication rate was 34%. In the multivariate model, higher age, increased surgical invasiveness and the presence of preoperative anemia were most strongly predictive of any postoperative complication (OR = 1.03, 1.09, 2.1 respectively, p <0.001), whereas the occurrence of a major postoperative complication (CCI >26) was most strongly associated with the presence of respiratory disease (OR = 2.82, p <0.001). Internal validation using the bootstrapped models showed the model was robust, with an AUC of 0.73. Using sensitivity analysis, 80% of the model's predictions were correct. By comparison SpineSage had an AUC of 0.71, and in decision curve analysis the novel model showed greater expected benefit at all thresholds of risk. NZSpine is a novel risk assessment tool for patients undergoing acute and elective spine surgery and may help inform clinicians and patients of their prognosis. Use of an objective tool may help to provide uniformity between DHBs when completing the “clinician assessment of risk” section of the national prioritization tool

Objective: To identify institution specific risk factors for developing MRSA surgical site infection (SSI) and develop an objective mechanism to estimate the probability of MRSA infection in a given patient admitted to the orthopaedic unit.

Design: A cohort study was performed to identify risk factors in all patients who had MRSA infection during admission on the orthopaedic unit between January 2002 and December 2004. Logistic regression was used to model the likelihood of MRSA. A stepwise approach was employed to derive a model. The MRSA prediction tool was developed from the final model.

Results: Of the 11 characteristics included in the logistic regression, the features that strongly predicted a MRSA infection were ASA grade, patient’s residence and reason for admission.

110 had MRSA infection in their surgical wound. 83 of 110 (75.5%) patients were non-elective admissions, of which 49 (60%) were proximal femur fractures. 20% of proximal femur fractures admitted from nursing home and 7.8% from their own homes developed SSI with MRSA. This cohort of SSI with MRSA had an average of 5.7(1–18) previous admissions. 25 (23%) had been previously colonised with MRSA. Majority of them (76%) were between 70–90 years old and were ASA grade 3–4.

Conclusion: Through multivariate modelling technique we were able to identify the most important determinants of patients developing SSI with MRSA in our institute and develop a tool to predict the probability of MRSA in a given patient. This knowledge can be used to guide the use of appropriate prophylactic antibiotic and to take other required measures to avoid the SSI with MRSA.

Aims. To develop prediction models using machine-learning (ML) algorithms for 90-day and one-year mortality prediction in femoral neck fracture (FNF) patients aged 50 years or older based on the Hip fracture Evaluation with Alternatives of Total Hip arthroplasty versus Hemiarthroplasty (HEALTH) and Fixation using Alternative Implants for the Treatment of Hip fractures (FAITH) trials. Methods. This study included 2,388 patients from the HEALTH and FAITH trials, with 90-day and one-year mortality proportions of 3.0% (71/2,388) and 6.4% (153/2,388), respectively. The mean age was 75.9 years (SD 10.8) and 65.9% of patients (1,574/2,388) were female. The algorithms included patient and injury characteristics. Six algorithms were developed, internally validated and evaluated across discrimination (c-statistic; discriminative ability between those with risk of mortality and those without), calibration (observed outcome compared to the predicted probability), and the Brier score (composite of discrimination and calibration). Results. The developed algorithms distinguished between patients at high and low risk for 90-day and one-year mortality. The penalized logistic regression algorithm had the best performance metrics for both 90-day (c-statistic 0.80, calibration slope 0.95, calibration intercept -0.06, and Brier score 0.039) and one-year (c-statistic 0.76, calibration slope 0.86, calibration intercept -0.20, and Brier score 0.074) mortality prediction in the hold-out set. Conclusion. Using high-quality data, the ML-based prediction models accurately predicted 90-day and one-year mortality in patients aged 50 years or older with a FNF. The final models must be externally validated to assess generalizability to other populations, and prospectively evaluated in the process of shared decision-making. Cite this article: Bone Jt Open 2023;4(3):168–181

This study demonstrates a significant correlation between the American Knee Society (AKS) Clinical Rating System and the Oxford Knee Score (OKS) and provides a validated prediction tool to estimate score conversion.

A total of 1022 patients were prospectively clinically assessed five years after TKR and completed AKS assessments and an OKS questionnaire. Multivariate regression analysis demonstrated significant correlations between OKS and the AKS knee and function scores but a stronger correlation (r = 0.68, p < 0.001) when using the sum of the AKS knee and function scores. Addition of body mass index and age (other statistically significant predictors of OKS) to the algorithm did not significantly increase the predictive value.

The simple regression model was used to predict the OKS in a group of 236 patients who were clinically assessed nine to ten years after TKR using the AKS system. The predicted OKS was compared with actual OKS in the second group. Intra-class correlation demonstrated excellent reliability (r = 0.81, 95% confidence intervals 0.75 to 0.85) for the combined knee and function score when used to predict OKS.

Our findings will facilitate comparison of outcome data from studies and registries using either the OKS or the AKS scores and may also be of value for those undertaking meta-analyses and systematic reviews.

Cite this article: Bone Joint J 2015;97-B:503–9.

Aims. Machine-learning (ML) prediction models in orthopaedic trauma hold great promise in assisting clinicians in various tasks, such as personalized risk stratification. However, an overview of current applications and critical appraisal to peer-reviewed guidelines is lacking. The objectives of this study are to 1) provide an overview of current ML prediction models in orthopaedic trauma; 2) evaluate the completeness of reporting following the Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) statement; and 3) assess the risk of bias following the Prediction model Risk Of Bias Assessment Tool (PROBAST) tool. Methods. A systematic search screening 3,252 studies identified 45 ML-based prediction models in orthopaedic trauma up to January 2023. The TRIPOD statement assessed transparent reporting and the PROBAST tool the risk of bias. Results. A total of 40 studies reported on training and internal validation; four studies performed both development and external validation, and one study performed only external validation. The most commonly reported outcomes were mortality (33%, 15/45) and length of hospital stay (9%, 4/45), and the majority of prediction models were developed in the hip fracture population (60%, 27/45). The overall median completeness for the TRIPOD statement was 62% (interquartile range 30 to 81%). The overall risk of bias in the PROBAST tool was low in 24% (11/45), high in 69% (31/45), and unclear in 7% (3/45) of the studies. High risk of bias was mainly due to analysis domain concerns including small datasets with low number of outcomes, complete-case analysis in case of missing data, and no reporting of performance measures. Conclusion. The results of this study showed that despite a myriad of potential clinically useful applications, a substantial part of ML studies in orthopaedic trauma lack transparent reporting, and are at high risk of bias. These problems must be resolved by following established guidelines to instil confidence in ML models among patients and clinicians. Otherwise, there will remain a sizeable gap between the development of ML prediction models and their clinical application in our day-to-day orthopaedic trauma practice. Cite this article: Bone Jt Open 2024;5(1):9–19

Aim. This study aimed to externally validate promising preoperative PJI prediction models in a recent, multinational European cohort. Method. Three preoperative PJI prediction models (by Tan et al., Del Toro et al., and Bülow et al.) which previously demonstrated high levels of accuracy were selected for validation. A multicenter retrospective observational analysis was performed of patients undergoing total hip arthroplasty (THA) and total knee arthroplasty (TKA) between January 2020 and December 2021 and treated at centers in the Netherlands, Portugal, and Spain. Patient characteristics were compared between our cohort and those used to develop the prediction models. Model performance was assessed through discrimination and calibration. Results. A total of 2684 patients were included of whom 60 developed a PJI (2.2%). Our patient cohort differed from the models’ original cohorts in terms of demographic variables, procedural variables, and the prevalence of comorbidities. The c-statistics for the Tan, Del Toro, and Bülow models were 0.72, 0.69, and 0.72 respectively. Calibration was reasonable, but precise percentage estimates for PJI risk were most accurate for predicted risks up to 3-4%; the Tan model overestimated risks above 4%, while the Del Toro model underestimated risks above 3%. Conclusions. In this multinational cohort study, the Tan, Del Toro, and Bülow PJI prediction models were found to be externally valid for classifying high risk patients for developing a PJI. These models hold promise for clinical application to enhance preoperative patient counseling and targeted prevention strategies. Keywords. Periprosthetic Joint Infection (PJI), High Risk Groups, Prediction Models, Validation, Infection Prevention

Aims. The aims of this study were to assess mapping models to predict the three-level version of EuroQoL five-dimension utility index (EQ-5D-3L) from the Oxford Knee Score (OKS) and validate these before and after total knee arthroplasty (TKA). Methods. A retrospective cohort of 5,857 patients was used to create the prediction models, and a second cohort of 721 patients from a different centre was used to validate the models, all of whom underwent TKA. Patient characteristics, BMI, OKS, and EQ-5D-3L were collected preoperatively and one year postoperatively. Generalized linear regression was used to formulate the prediction models. Results. There were significant correlations between the OKS and EQ-5D-3L preoperatively (r = 0.68; p < 0.001) and postoperatively (r = 0.77; p < 0.001) and for the change in the scores (r = 0.61; p < 0.001). Three different models (preoperative, postoperative, and change) were created. There were no significant differences between the actual and predicted mean EQ-5D-3L utilities at any timepoint or for change in the scores (p > 0.090) in the validation cohort. There was a significant correlation between the actual and predicted EQ-5D-3L utilities preoperatively (r = 0.63; p < 0.001) and postoperatively (r = 0.77; p < 0.001) and for the change in the scores (r = 0.56; p < 0.001). Bland-Altman plots demonstrated that a lower utility was overestimated, and higher utility was underestimated. The individual predicted EQ-5D-3L that was within ± 0.05 and ± 0.010 (minimal clinically important difference (MCID)) of the actual EQ-5D-3L varied between 13% to 35% and 26% to 64%, respectively, according to timepoint assessed and change in the scores, but was not significantly different between the modelling and validation cohorts (p ≥ 0.148). Conclusion. The OKS can be used to estimate EQ-5D-3L. Predicted individual patient utility error beyond the MCID varied from one-third to two-thirds depending on timepoint assessed, but the mean for a cohort did not differ and could be employed for this purpose. Cite this article: Bone Jt Open 2022;3(7):573–581

Aim. Recurrence of bone and joint infection, despite appropriate therapy, is well recognised and stimulates ongoing interest in identifying host factors that predict infection recurrence. Clinical prediction models exist for those treated with DAIR, but to date no models with a low risk of bias predict orthopaedic infection recurrence for people with surgically excised infection and removed metalwork. The aims of this study were to construct and internally validate a risk prediction model for infection recurrence at 12 months, and to identify factors that predict recurrence. Predictive factors must be easy to check in pre-operative assessment and relevant across patient groups. Methods. Four prospectively collected datasets including 1173 participants treated in European centres between 2003 and 2021, followed up to 12 months after surgery for orthopaedic infections, were included in logistic regression modelling [1–3]. The definition of infection recurrence was identical and ascertained separately from baseline factors in three contributing cohorts. Eight predictive factors were investigated following a priori sample size calculation: age, gender, BMI, ASA score, the number of prior operations, immunosuppressive medication, glycosylated haemoglobin (HbA1c), and smoking. Missing data, including systematically missing predictors, were imputed using Multiple Imputation by Chained Equations. Weekly alcohol intake was not included in modelling due to low inter-observer reliability (mean reported intake 12 units per week, 95% CI for mean inter-rater error −16.0 to +15.4 units per week). Results. Participants were 64% male, with a median age of 60 years (range 18–95). 86% of participants had lower limb orthopaedic infections. 732 participants were treated for osteomyelitis, including FRI, and 432 for PJI. 16% of participants experienced treatment failure by 12 months. The full prediction model had moderate apparent discrimination: AUROC (C statistic) 0.67, Brier score 0.13, and reasonable apparent calibration. Of the predictors of interest, associations with failure were seen with prior operations at the same anatomical site (odds ratio for failure 1.51 for each additional prior surgery; 95% CI 1.02 to 2.22, p=0.06), and the current use of immunosuppressive medications (odds ratio for failure 2.94; 95% CI 0.89 to 9.77, p=0.08). Conclusions. This association between number of prior surgeries and treatment failure supports the urgent need to streamline referral pathways for people with orthopaedic infection to specialist multidisciplinary units

The February 2023 Children’s orthopaedics Roundup. 360. looks at: Trends in management of paediatric distal radius buckle fractures; Pelvic osteotomy in patients with previous sacral-alar-iliac fixation; Sacral-alar-iliac fixation in patients with previous pelvic osteotomy; Idiopathic toe walking: an update on natural history, diagnosis, and treatment; A prediction model for treatment decisions in distal radial physeal injuries: a multicentre retrospective study; Angular deformities after percutaneous epiphysiodesis for leg length discrepancy; MRI assessment of anterior coverage is predictive of future radiological coverage; Predictive scoring for recurrent patellar instability after a first-time patellar dislocation

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

Aims. No predictive model has been published to forecast operating time for total knee arthroplasty (TKA). The aims of this study were to design and validate a predictive model to estimate operating time for robotic-assisted TKA based on demographic data, and evaluate the added predictive power of CT scan-based predictors and their impact on the accuracy of the predictive model. Methods. A retrospective study was conducted on 1,061 TKAs performed from January 2016 to December 2019 with an image-based robotic-assisted system. Demographic data included age, sex, height, and weight. The femoral and tibial mechanical axis and the osteophyte volume were calculated from CT scans. These inputs were used to develop a predictive model aimed to predict operating time based on demographic data only, and demographic and 3D patient anatomy data. Results. The key factors for predicting operating time were the surgeon and patient weight, followed by 12 anatomical parameters derived from CT scans. The predictive model based only on demographic data showed that 90% of predictions were within 15 minutes of actual operating time, with 73% within ten minutes. The predictive model including demographic data and CT scans showed that 94% of predictions were within 15 minutes of actual operating time and 88% within ten minutes. Conclusion. The primary factors for predicting robotic-assisted TKA operating time were surgeon, patient weight, and osteophyte volume. This study demonstrates that incorporating 3D patient-specific data can improve operating time predictions models, which may lead to improved operating room planning and efficiency. Cite this article: Bone Jt Open 2022;3(5):383–389

Aims. The aim of this study was to develop and internally validate a prognostic nomogram to predict the probability of gaining a functional range of motion (ROM ≥ 120°) after open arthrolysis of the elbow in patients with post-traumatic stiffness of the elbow. Methods. We developed the Shanghai Prediction Model for Elbow Stiffness Surgical Outcome (SPESSO) based on a dataset of 551 patients who underwent open arthrolysis of the elbow in four institutions. Demographic and clinical characteristics were collected from medical records. The least absolute shrinkage and selection operator regression model was used to optimize the selection of relevant features. Multivariable logistic regression analysis was used to build the SPESSO. Its prediction performance was evaluated using the concordance index (C-index) and a calibration graph. Internal validation was conducted using bootstrapping validation. Results. BMI, the duration of stiffness, the preoperative ROM, the preoperative intensity of pain, and grade of post-traumatic osteoarthritis of the elbow were identified as predictors of outcome and incorporated to construct the nomogram. SPESSO displayed good discrimination with a C-index of 0.73 (95% confidence interval 0.64 to 0.81). A high C-index value of 0.70 could still be reached in the interval validation. The calibration graph showed good agreement between the nomogram prediction and the outcome. Conclusion. The newly developed SPESSO is a valid and convenient model which can be used to predict the outcome of open arthrolysis of the elbow. It could assist clinicians in counselling patients regarding the choice and expectations of treatment. Cite this article: Bone Joint J 2022;104-B(4):486–494