Osteoporotic femoral neck fractures (OFNFs) pose a significant orthopedic challenge in the elderly population, accounting for up to 40% of all osteoporotic fractures and leading to considerable health deterioration and increased mortality. In addressing the critical need for early identification of osteoporosis through routine screening of femoral neck bone mineral density (FNBMD), this study developed a user-friendly prediction model aimed at men aged 50 years and older, a demographic often overlooked in osteoporosis screening. Utilizing data from the National Health and Nutrition Examination Survey (NHANES), the study involved outlier detection and handling, missing value imputation via the K nearest neighbor (KNN) algorithm, and data normalization and encoding. The dataset was split into training and test sets with a 7:3 ratio, followed by feature screening through the least absolute shrinkage and selection operator (LASSO) and the Boruta algorithm. Eight different machine learning algorithms were then employed to construct predictive models, with their performance evaluated through a comprehensive metric suite. The random forest regressor (RFR) emerged as the most effective model, characterized by key predictors such as age, body mass index (BMI), poverty income ratio (PIR), serum calcium, and race, achieving a coefficient of determination (R²) of 0.218 and maintaining robustness in sensitivity analyses. Notably, excluding race from the model resulted in sustained high performance, underscoring the model’s adaptability. Interpretations using Shapley additive explanations (SHAP) highlighted the influence of each feature on FNBMD. These findings indicate that our predictive model effectively aids in the early detection of osteoporosis, potentially reducing the incidence of OFNFs in this high-risk population.

Postoperative sore throat (POST) isa prevalent complication after general anesthesia and targeting high-risk patients helps in its prevention. This study developed and validated a machine learning model to predict POST. A total number of 834 patients who underwent general anesthesia with endotracheal intubation were included in this study. Data from a cohort of 685 patients was used for model development and validation, while a cohort of 149 patients served for external validation. The prediction performance of random forest (RF), neural network (NN), and extreme gradient boosting (XGBoost) models was compared using comprehensive performance metrics. The Local Interpretable Model-Agnostic Explanations (LIME) methods elucidated the best-performing model. POST incidences across training, validation, and testing cohorts were 41.7%, 38.4%, and 36.2%, respectively. Five predictors were age, sex, endotracheal tube cuff pressure, endotracheal tube insertion depth, and the time interval between extubation and the first drinking of water after extubation. After incorporating these variables, the NN model demonstrated superior generalization capabilities in predicting POST when compared to the XGBoost and RF models in external validation, achieving an area under the receiver operating characteristic curve (AUROC) of 0.81(95% CI 0.74-0.89) and a precision-recall curve (AUPRC) of 0.77 (95% CI 0.66-0.86). The model also showed good calibration and clinical usage values. The NN model outperforms the XGBoost and RF models in predicting POST, with potential applications in the healthcare industry for reducing the incidence of this common postoperative complication.

BACKGROUND:Osteonecrosis of the femoral head (ONFH) is a common clinical disease. Improper treatment can lead to femoral head collapse and hip joint dysfunction. Core decompression is particularly important for early ONFH. However, subtrochanteric fractures after core decompression cause some clinical problems.CASE PRESENTATION:This article describes a 34-year-old male patient with early ONFH. After core decompression, he suffered a subtrochanteric fracture of the femur while bearing weight on the affected limb when going up stairs. He was subsequently treated with open reduction and intramedullary nail fixation.CONCLUSION:When core decompression is used to treat ONFH, the location or size of the drill hole, whether a tantalum rod or bone is inserted, and partial weight-bearing of the affected limb may directly affect whether a fracture occurs after surgery. It is hoped that this case report can provide a reference for clinical orthopedic surgeons in the treatment of early ONFH.

Purpose: Correctly classifying distal femur fractures is essential for surgical treatment planning and patient prognosis. This study assesses the potential of Cinematic Rendering (CR) in classifying these fractures, emphasizing its reported ability to produce more realistic images than Volume Rendering (VR).Methods: Data from 88 consecutive patients with distal femoral fractures collected between July 2013 and July 2020 were included. Two orthopedic surgeons independently evaluated the fractures using CR and VR. The inter-rater and intra-rater agreement was evaluated by using the Cicchetti-Allison weighted Kappa method. Accuracy, precision, recall, and F1 score were also calculated. Diagnostic confidence scores (DCSs) for both imaging methods were compared using chi-square or Fisher’s exact tests.Results: CR reconstruction yielded excellent inter-observer (Kappa = 0.989) and intra-observer (Kappa = 0.992) agreement, outperforming VR (Kappa = 0.941 and 0.905, respectively). While metrics like accuracy, precision, recall, and F1 scores were higher for CR, the difference was not statistically significant (p > 0.05). However, DCAs significantly favored CR (p < 0.05).Conclusion: CR offers a superior visualization of distal femur fractures than VR. It enhances fracture classification accuracy and bolsters diagnostic confidence. The high inter- and intra-observer agreement underscores its reliability, suggesting its potential clinical importance.

Accurate prediction of the length of stay for patients undergoing total knee arthroplasty (TKA) is critical for efficient medical resource allocation. This study aimed to create a user-friendly model to assist this estimation process. A secondary analysis was conducted on 2676 patients who underwent elective primary TKA at a tertiary academic medical center in Singapore from January 2013 to June 2014. The eligible patients (n = 2600) were randomly divided into a training cohort (n = 2081) and a validation cohort (n = 519), at a ratio of 4:1. A prolonged hospital stay was defined as exceeding six days. Multivariable logistic regression was used to develop a prediction model, and an online calculator was created to facilitate its application. The model's discrimination power, goodness-of-fit, and clinical applicability were evaluated. Additionally, models using other statistical methods were developed for performance comparison. The model includes predictors such as age, operation duration, history of cerebrovascular accidents, creatinine levels, procedure site, the American Society of Anesthesiologists Physical status, hemoglobin levels, and primary anesthesia type. The model demonstrated robust discrimination power with a C statistic of 0.70 (95% confidence interval, 0.64 to 0.75), satisfactory goodness-of-fit (Hosmer–Lemeshow test, P=0.286), and was applicable when thresholds were between 0.08 and 0.52, based on decision curve analysis. A predictive model was developed that can be used to identify patients who are likely to require an extended stay following TKA. This could assist in planning bed availability and guiding therapeutic decisions.

Mismatch between partial imported prostheses and Chinese anatomy affects the clinical outcome of the procedure. The purpose of this study was to measure the anatomical dimensions of Chinese distal femurs to provide guidance for the design of more compatible distal femoral prostheses. A total of 406 healthy distal femurs were reconstructed and measured. Consistency of these measurements and differences in sides, gender, and populations were examined. Parameter correlations were analyzed, and pairs with strong correlations underwent linear regression analysis. The design of distal femoral prostheses was referenced from the results of K-means and hierarchical clustering analysis. Ten parameters were measured, including the trans-epicondylar axis, width of the distal femur (ML), anteroposterior diameter of the distal femur (AP), etc. The intra-class correlation coefficient ranged from 0.795 to 0.999 for intra-observer consistency, and from 0.796 to 0.998 for inter-observer consistency. Males exhibited significantly larger parameters than females, except for the posterior condylar angle (all P values < 0.05). Compared to other populations, substantial differences were observed for most parameters, such as ML, AP, width of lateral femoral condyle, etc. (all P values < 0.05). Clustering analysis suggested that distal femoral prostheses should include at least five sizes to adequately accommodate the sampled population. ML sizes for males were 68, 70, 83, 73, and 89 mm, and for females 64, 65, 71, 67, and 77 mm. AP sizes for males were 56, 60, 60, 64, and 64 mm, and for females 48, 52, 54, 57, and 58 mm. Chinese distal femur morphology, as analyzed using 3D techniques, varies significantly between genders and when compared with international data. For improved patient fit, the creation of five or more distal femur prostheses, diversified by gender and size and informed by the associated morphological parameters, is recommended. IV.

Purpose: Complex distal femoral fractures involve a challenging set of considerations that must be known to provide optimal management. This study aimed to determine the location and frequency of fracture lines and comminution zones in AO/OTA types 33A and 33C distal femoral fractures using three-dimensional computed tomography mapping.Methods: Seventy-four consecutive eligible patients were included. Fracture fragments for each patient were reconstructed, virtually reduced, and adjusted to match the distal femoral template. Then, all fracture lines and comminuted areas were extracted in transparent mode, and corresponding heat maps were constructed. Finally, these maps, along with the quantitative analysis findings of the counts and volumes of each fragment, were used to summarize the characteristics of the fractures.Results: Thirty-four females and 40 males [average age, 58 years (range, 18–92 years)] presented with a distal femoral fracture. There were 53 AO/OTA type 33A fractures, and 21 AO/OTA type 33C fractures. These two patterns differed significantly on fracture fragment count, comminuted zone fracture fragment count, and mean comminuted zone fracture fragment volume (p < 0.05). Most of the fracture line heat zones were in the femoral epiphysis, intercondylar notch of the femur, and patellofemoral joint. The comminuted area heat regions were mostly found on the lateral, anterior, and posterior femoral diaphysis, with less involvement on the medial side.Conclusion: Our findings may serve as a guide for the surgical approach selection of complex distal femur fractures, the placement strategy of the internal fixation, and the optimization of the osteotomy plan for biomechanical studies.

Background Rapid identification of high-risk polytrauma patients is crucial for early intervention and improved outcomes. This study aimed to develop and validate machine learning models for predicting 72 h mortality in adult polytrauma patients using readily available clinical parameters. Methods A retrospective analysis was conducted on polytrauma patients from the Dryad database and our institution. Missing values pertinent to eligible individuals within the Dryad database were compensated for through the k-nearest neighbor algorithm, subsequently randomizing them into training and internal validation factions on a 7:3 ratio. The patients of our institution functioned as external validation cohorts. The predictive efficacy of random forest (RF), neural network, and XGBoost models was assessed through an exhaustive suite of performance indicators. The SHapley Additive exPlanations (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME) methods were engaged to explain the supreme-performing model. Conclusively, restricted cubic spline analysis and multivariate logistic regression were employed as sensitivity analyses to verify the robustness of the findings. Results Parameters including age, body mass index, Glasgow Coma Scale, Injury Severity Score, pH, base excess, and lactate emerged as pivotal predictors of 72 h mortality. The RF model exhibited unparalleled performance, boasting an area under the receiver operating characteristic curve (AUROC) of 0.87 (95% confidence interval [CI] 0.84–0.89), an area under the precision-recall curve (AUPRC) of 0.67 (95% CI 0.61–0.73), and an accuracy of 0.83 (95% CI 0.81–0.86) in the internal validation cohort, paralleled by an AUROC of 0.98 (95% CI 0.97–0.99), an AUPRC of 0.88 (95% CI 0.83–0.93), and an accuracy of 0.97 (95% CI 0.96–0.98) in the external validation cohort. It provided the highest net benefit in the decision curve analysis in relation to the other models. The outcomes of the sensitivity examinations were congruent with those inferred from SHAP and LIME. Conclusions The RF model exhibited the best performance in predicting 72 h mortality in adult polytrauma patients and has the potential to aid clinicians in identifying high-risk patients and guiding clinical decision-making.

Background Early and accessible screening of patients with polytrauma at a high risk of hospital death is essential. The purpose of this research was to seek an accurate and convenient solution to predict deaths occurring within 72 h after admission of these patients. Methods A secondary analysis was conducted on 3,075 patients with polytrauma from the Dryad database. We imputed missing values in eligible individuals with the k-nearest neighbor algorithm and then randomly stratified them into the training group (n = 2,461) and the validation group (n = 614) based on a proportion of 8:2. The restricted cubic spline, univariate, backward stepwise, and multivariate logistic regression methods were employed to determine the suitable predictors. Calibration and receiver operating characteristic (ROC) curves were applied to assess the calibration and discrimination of the obtained model. The decision curve analysis was then chosen as the measure to examine the clinical usage. Results Age, the Glasgow Coma Scale score, the Injury Severity Score, base excess, and the initial lactate level were inferred as independent prognostic factors related to mortality. These factors were then integrated and applied to construct a model. The performance of calibration plots, ROC curves, and decision curve analysis indicated that the model had satisfactory predictive power for 72-h mortality after admission of patients with polytrauma. Moreover, we developed a nomogram for visualization and a web-based calculator for convenient application (https://songandwen.shinyapps.io/DynNomapp/). Conclusions A convenient web-based calculator was constructed to robustly estimate the risk of death in patients with polytrauma within 72 h after admission, which may aid in further rationalization of clinical decision-making and accurate individual treatment.

Objective To evaluate the computational biomechanical analysis of intra‐articular calcaneal fractures with different fixation status of the sustentaculum plate screw, when the finite element modeling of calcaneal fractures were fixed by the lateral locking plate. Methods The normal right foot of a male (age: 36 years; height: 174 cm; body weight: 65 kg) was scanned by the CT scanner. As the computational biomechanical study, the three‐dimensional finite element model of the simplified Sanders type‐II calcaneal fracture was built. Fixation with the lateral calcaneal locking plate and screws was simulated using a finite element software package according to clinical operation. According to the different placement of the sustentaculum plate screw, the models were categorized as the accurate fixation group, marginal fixation group, and non‐fixation group. The loading of 650 N with the vertical axial compression was applied to simulate the standing phase with single foot. The Von Mises stress distribution, maximal displacement, and contact area of the subtalar joint were analyzed among three groups. Results The pressure distribution of the subtalar joint facet was inhomogeneous. The stress concentration of the calcaneus was located at the medial zone of the posterior subtalar joint facet. The peak Von Mises stress distribution in three groups was similar at the subtalar joint facet of 4.9 MPa, 5.1 MPa, and 5.4 MPa. In the accurate fixation group, the contact area on the posterior articular facet was 277.1 mm2; the maximal displacement was 0.18 mm. The contact area of the marginal fixation group was 265.3 mm2 on the posterior facet, where the maximal displacement was 0.23 mm. In the non‐fixation group, the contact area was 253.8 mm2; the maximal displacement was 0.25 mm. There was a slight change in the contact area of the subtalar joint and no prominent displacement of the calcaneus could be detected among the three groups. Conclusions The biomechanical results, including the peak stress distribution, contact area, and maximal displacement of subtalar joint, were similar whether the screw is placed exactly within the sustentaculum tali or not, when the calcaneal fractures were fixed by the lateral locking plate. The sustentaculum plate screw had less effect on the biomechanical performance of the calcaneus.

The aim of this study was to compare the values of six methods in measuring the involvement of posterior malleolus and to demonstrate the reliability and reproducibility of each method. Three independent orthopaedic surgeons, retrospectively, measured 106 cases. The difference between the six methods was analyzed using Bonferroni-corrected paired t-tests after one-way ANOVA. The agreement between the six methods was analyzed using Bland–Altman analysis. The intraclass correlation coefficient (ICC) was used to assess intraobserver reproducibility and interobserver reliability. Significant differences were observed between values of any two of the six measurement methods (P < 0.0033), except between any two of the plane radiograph linear, axial CT linear, sagittal CT linear, and 3D CT linear. The Bland–Altman plots demonstrated poor agreement between values of any two of the six methods. The lowest intraobserver reproducibility was 0.46 (moderate) for resident surgeon using plain radiographs. The intraobserver reproducibility for three surgeons using two-dimensional (2D) and 3D images was almost perfect (ICC, 0.82–0.96). The lowest interobserver reliability was 0.41 (moderate) between chief and attending surgeon using plain radiographs, and it improved to almost perfect (ICC, 0.81–0.95) with the use of 3D CT images. The standard error of measurement showed almost the same results as ICC values. The existing operative indications which were determined based on plain radiography are neither reliable nor suitable for other measurement methods. Both 3D linear and 3D surface measurement methods are reliable and reproducible in measuring posterior fragment involvement, and experience is not so crucial. Operative indications for posterior malleolar fractures need to be redefined based on the 3D measurement method.

BACKGROUND:The application of computer-assisted virtual surgical technology in preoperative planning for distal femoral fractures has been rarely presented. This study aimed to evaluate the intra-operative realization of this technology and the clinical outcomes based on it for distal femoral fractures. METHODS:Between February 2014 and May 2017, 32 patients with distal femoral fractures treated by open reduction and internal fixation were included and divided into 2 groups on the basis of preoperative planning methods: conventional (N = 17) and virtual surgical (N = 15). The time required for virtual segmentation, reduction, and fixation of the fracture fragments in virtual surgical group were analyzed. Operation time, intra-operative blood loss, times of fluoroscopy during operation and days of hospital stay in two groups were compared. Postoperative functional outcomes were assessed using the Knee Society Score (KSS), Short Form-36 (SF-36) scoring systems, and visual analogue scale (VAS) for pain. RESULTS:Mean total planning time for 33-A, 33-B, and 33-C fractures in virtual surgical group were 43.0 ± 1.7, 23.0 ± 1.3, and 51.4 ± 3.7 min, respectively. Compared with the conventional group, Patients in virtual surgical group had lower blood loss, fewer fluoroscopic images, less operative time, and shorter days of hospital stay (P < 0.05). No significant difference could detected in the KSS, SF-36, or VAS scores between the two groups at the final follow-up (P > 0.05). CONCLUSIONS:Computer-assisted virtual surgical technology could rapidly complete surgical treatment protocol, improve operative efficiency, and provide satisfying clinical and radiographic outcomes for distal femoral fractures.

Objective evaluate the efficacy of a single medial locking plate and lag screws based on computer-assisted pre-operation plan (CAPP) for the treatment of pilon fractures.Methods Between 2013 and 2016,data of 27 patients with pilon fractures who were treated using a single medial locking and lag screws based on CAPP were retrospectively analyzed.All the cases were AO/OTA 43-C type pilon fractures.According to the Rüedi-Allg(o)wer classification,there were 5 cases of type Ⅱ and 22 cases of type Ⅲ.Among 27 patients,19 patients had fibula fracture.CAPP was performed for all fractures,including simulated reduction,virtual surgery,and implantation of internal fixation.The time of CAPP,intraoperative realization of preoperative plan,operation time,intraoperative blood loss,and pre-and post-operative range of motion of ankle were recorded.Functional outcomes at final follow up were assessed using American Orthopedic Foot and Ankle Society (AOFAS) ankle hindfoot scale,visual analogue scale (VAS).Results The mean time of CAPP was 25.8 minutes (range,14-30 minutes).The average operating time was 138.5 minutes.The average intraoperative blood loss was 225.9 ml.All the twenty-seven patients were followed up for an average period of 18.6 months.The average AOFAS score,VAS score at the final follow-up was 82.9,2.7 points respectively,which was significandy improved compared with those before operation (t=-19.358,7.720;all P＜ 0.001).Conclusion CAPP system is convenient and efficient,which can facilitate the treatment of type C pilon fractures with a single medial locking plate and lag screws.In addition,satisfactory clinical outcomes can be obtained.

No computer-assisted pre-operative design for calcaneal fracture malunions has been presented. The aim of the study is to evaluate the intra-operative realization of computer-assisted pre-operative planning (CAPP) and the clinical outcomes based on computer-assisted virtual surgical technology for calcaneal malunions.

Background: The purpose of this study was to measure the three-dimensional range of motion of adjacent, unfused joint or joints after different arthrodesis of hindfoot. Methods: Sixteen fresh frozen cadaver feet were immobilized in the non-weight bearing position. The threedimensional coordinates of markers in tarsal were measured in six directions (involving dorsiflexion-plantarflexion, eversion-inversion, and adduction-abduction) before and after single (involving subtalar joint, talonavicular joint, and calcaneocuboid joint) and double (talonavicular and calcaneocuboid joints) arthrodesis with a three-dimensional coordinate instrument. The range of motion of the joint was calculated with the least square method and matrix transformation. Findings: We found that the range of motion of joints in all direction was reduced significantly after any combination of selective arthrodesis (all p < 0.001). After arthrodesis of the subtalar joint, the motion of talonavicular joint was reduced by 72%, and that of calcaneocuboid joint by 36%. After arthrodesis of talonavicular joint, the motion of subtalar joint was diminished by 36%, and that of calcaneocuboid joint by 51%. After arthrodesis of calcaneocuboid joint, the motion of subtalar joint was decreased by 21%, and that of talonavicular joint by 42%. After double arthrodesis, the motion of subtalar joint was reduced by 62%. Interpretation: In single arthrodesis, subtalar arthrodesis had the greatest effect on the motion of unfused joints, and the least was the calcaneocuboid arthrodesis. The motion of the subtalar joint was eliminated more than half after double arthrodesis. The data provide a biomechanical rationale to ascertain the clinical implication of the arthrodesis.

Background: This study aimed to determine the difference between computer-assisted virtual surgical technology and 3-dimensional (3D) printing technology in preoperative planning for proximal humeral fractures. Methods: Between February 2009 and October 2015, 131 patients with 3 and 4-part proximal humeral fractures were divided into 3 groups on the basis of the preoperative planning method: conventional (n = 53), virtual surgical (n = 46), and 3D printing (n = 32). Fracture characteristics and intraoperative realization of preoperative planning (reduction shape and implant choices) were evaluated. Postoperative functional outcomes were assessed using the American Shoulder and Elbow Surgeons, Constant-Murley, and Short Form-36 (SF-36) scoring systems and shoulder range of motion; postoperative radiographic outcomes were assessed with respect to the loss of the neck-shaft angle (NSA) and loss of humeral head height (HHH). Results: Excellent sensitivity, specificity, and accuracy for fracture characteristics were seen in all 3 groups. The correlations for NSA (p = 0.033) and HHH (p = 0.035) were higher in the virtual surgical group than in the 3D printing group. The lengths of the medial support screws in the actual choices were shorter than those in the preoperative plan for the 3D printing group, but a similar pattern was not seen in the virtual surgical group. Compared with the conventional method, the virtual surgical and 3D printing methods of preoperative planning resulted in shorter operative time, less blood loss, and fewer fluoroscopic images. The functional outcomes in both the 3D printing and virtual surgical groups were better than those in the conventional group. The virtual surgical method was faster than the 3D printing method, as suggested by a shorter time to surgery (2.5 compared with 4.6 days; p < 0.001), a shorter time for preoperative planning (30.4 compared with 262.4 minutes; p < 0.001), and a decreased duration of hospital stay (10.9 compared with 14.6 days; p < 0.001). Conclusions: The clinical outcomes in both the virtual surgical and 3D printing groups were better than those in the conventional group. However, computer-assisted virtual surgical technology is more convenient and efficient, considering the shorter time for preoperative planning. In addition, it has improved correlation with preoperative planning. Level of Evidence: Therapeutic Level III. See Instructions for Authors for a complete description of levels of evidence.

Objective To discuss the curative effect of computer assisted pre-operation plan (CAPP) in treating the geriatric intertrochanteric femoral fracture.Methods The data of intertrochanteric fractures treated with PFNA-Ⅱ between March 2012 and June 2015 were retrospectively analyzed.They were divided into two groups by preoperative design.One group was the CAPP group consisting of 53 patients with a mean age of 75.3 years (range,60-92 years).According to the Evans Classification,there were 12 Evans type Ⅰb,9 Evans type Ⅰc,15 Evans type Ⅰd and 17 Evans type Ⅱ fractures.The other group was the non-CAPP group consisting of 74 patients with a mean age of 76.6 years (range,62-95 years).There were 18 Evans type Ⅰb,15 Evans type Ⅰc,20 Evans type Ⅰd and 21 Evans type Ⅱ fractures.Operation time,intraoperative blood loss,times of fluoroscopy during operation and days of hospital stay were compared.The hip joint function was evaluated by Harris score at the final follow-up.Results The CAPP meanly cost 24.7 min.The consistency of the surgery and CAPP was up to 100％.In the CAPP group,the average operation time was 46.8±6.5 min;the average times of fluoroscopy during operation were 12.0±2.3 times;and the average blood loss was 154.4±27.6 ml.In the non-CAPP group,the average operation time was 57.8±10.3 min;the average times of fluoroscopy during operation was 20.9±3.2;and the average blood loss was 235.0±65.8 ml.All above data in the CAPP group were significantly lower than those in the non-CAPP group.The mean days of hospital stay were 13.9±1.3 days in the CAPP group and 14.3±1.4 days in non-CAPP group.The days of hospital stay had no significant difference between the two groups.Forty-five patients with an average follow-up period of 18.3 months were reviewed in the CAPP group.Fifty patients were followed up with an average period of 19.2 months in the non-CAPP group.At the final follow-up,the average Harris score was 88.6±2.8 points (range,84-96 points) in the CAPP group and 87.5±3.2 points (range,80-95 points) in the non-CAPP group.Conclusion CAPP system is convenient and efficient.It can facilitate the treatment of intertrochanteric fracture effectively.