Limited diagnostic workup for deep vein thrombosis after major joint surgery: findings from a prospective, multicentre, cohort study

Comparison of different machine learning classification models for predicting deep vein thrombosis in lower extremity fractures

Deep vein thrombosis (DVT) is a common complication in patients with lower extremity fractures. Once it occurs, it will seriously affect the quality of life and postoperative recovery of patients. Therefore, early prediction and prevention of DVT can effectively improve the prognosis of patients. This study constructed different machine learning models to explore their effectiveness in predicting DVT. Five prediction models were applied to the study, including Extreme Gradient Boosting (XGBoost) model, Logistic Regression (LR) model, RandomForest (RF) model, Multilayer Perceptron (MLP) model, and Support Vector Machine (SVM) model. Afterwards, the performance of the obtained prediction models was evaluated by area under the curve (AUC), accuracy, sensitivity, specificity, F1 score, and Kappa. The prediction performances of the models based on machine learning are as follows: XGBoost model (AUC = 0.979, accuracy = 0.931), LR model (AUC = 0.821, accuracy = 0.758), RF model (AUC = 0.970, accuracy = 0.921), MLP model (AUC = 0.830, accuracy = 0.756), SVM model (AUC = 0.713, accuracy = 0.661). On our data set, the XGBoost model has the best performance. However, the model still needs external verification research before clinical application.

Nomogram for Predicting Deep Venous Thrombosis in Lower Extremity Fractures

Deep venous thrombosis (DVT) is a common complication in patients with lower extremity fractures, causing delays in recovery short-term and possible impacts on quality of life long-term. Early prediction and prevention of thrombosis can effectively reduce patient pain while improving outcomes. Although research on the risk factors for thrombosis is prevalent, there is a stark lack of clinical predictive models for DVT occurrence specifically in patients with lower limb fractures. In this study, we aim to propose a new thrombus prediction model for lower extremity fracture patients. Data from 3300 patients with lower limb fractures were collected from Wuhan Union Hospital and Hebei Third Hospital, China. Patients who met our inclusion criteria were divided into a thrombosis and a nonthrombosis group. A multivariate logistic regression analysis was carried out to identify predictors with obvious effects, and the corresponding formulas were used to establish the model. Model performance was evaluated using a discrimination and correction curve. 2662 patients were included in the regression analysis, with 1666 in the thrombosis group and 996 in the nonthrombosis group. Predictive factors included age, Body Mass Index (BMI), fracture-fixation types, energy of impact at the time of injury, blood transfusion during hospitalization, and use of anticoagulant drugs. The discriminative ability of the model was verified using the C-statistic (0.676). For the convenience of clinical use, a score table and nomogram were compiled. Data from two centers were used to establish a novel thrombus prediction model specific for patients with lower limb fractures, with verified predictive ability.

Cost-effectiveness impact of rivaroxaban versus new and existing prophylaxis for the prevention of venous thromboembolism after total hip or knee replacement surgery in France, Italy and Spain

Venous thromboembolism (VTE) has a significant impact on healthcare costs but is largely preventable with anticoagulant prophylaxis using low-molecular-weight heparins (LMWHs), such as enoxaparin or dalteparin. Rivaroxaban and dabigatran etexilate are two new oral anticoagulants (NOACs) both compared with enoxaparin in separate trials. A decision analytic model with a healthcare and national payer perspective over a five-year time horizon was used to evaluate the cost-effectiveness of the NOACs for VTE prophylaxis after total hip replacement (THR) or total knee replacement (TKR) in France, Italy and Spain. Efficacy and safety data were obtained from randomised controlled trials of rivaroxaban vs enoxaparin and an indirect statistical comparison for rivaroxaban vs dabigatran. Rivaroxaban demonstrated dominance across all comparisons, indications and countries. In THR, total per-patient costs were reduced by up to €160 in the enoxaparin comparison and €115 in the dabigatran comparison, respectively. In addition, quality-adjusted life-years (QALYs) were increased by up to 0.0011 and 0.0012 in each comparison, respectively. Similarly, total costs were reduced in TKR by up to €137 and €28 in the enoxaparin and dabigatran comparisons, respectively. The total number of QALYs was increased by up to 0.0014 in the enoxaparin comparison and 0.0005 in the dabigatran comparison. The results were driven by costs since the incremental benefits were minimal. Rivaroxaban use could result in substantial healthcare cost savings and improved quality of life. The results are applicable across three European countries with differing healthcare systems so, potentially, could be generalised to a much wider population.

Symptomatic venous thromboembolism in elderly patients following major orthopedic surgery of the lower limb is associated with elevated vitamin B12 serum levels

BACKGROUND

Elevated vitamin B12 serum levels are associated with systemic inflammation and mortality. Since venous thromboembolism (VTE) is associated with systemic inflammation and mortality as well, we have hypothesized that it is also associated with elevated vitamin B12 serum levels in elderly patients following major orthopedic surgery of the lower limb.

METHODS

This is a retrospective study. Medical charts of consecutive elderly (≥65 years) patients admitted for rehabilitation following major orthopedic surgery of the lower limb during 2007-2009 were reviewed. The study group included symptomatic VTE patients. The control group included patients in whom VTE was excluded. Demographics, co-morbidities, VTE risk factors, vitamin B12 serum levels, and 1-year mortality were studied.

RESULTS

The cohort included 197 elderly patients (median age: 82 years): 140 (71.1%) women and 57 (28.9%) men. Overall, 20 (10.2%) patients had VTE (study group) and in 177 (89.8%) patients VTE was excluded (control group). Vitamin B12 serum levels were higher in the study group compared with the control group (median: 634 vs. 409 pg/dL, p=0.024). The incidence of elevated vitamin B12 serum levels (≥500 pg/dL) was higher in the study group compared with the control group (odds ratio 3.1, p=0.031). Elevated vitamin B12 serum levels were associated with VTE (odds ratio 5.3, p=0.011) and with 1-year mortality (odds ratio 6.6, p=0.015) independent of demographics, co-morbidities, and VTE risk factors.

CONCLUSIONS

Symptomatic VTE is associated with elevated vitamin B12 serum levels in elderly patients following major orthopedic surgery of the lower limb.

[Primary hip replacement: first year results and predictive factors of poor outcome]

OBJECTIVE

To evaluate the results of total hip arthroplasty in patients with osteoarthritis and to identify predictors of poor functional outcome.

MATERIAL AND METHODS

A prospective observational study in patients operated on in 2006 with total hip arthroplasty in 4 hospitals in Guipúzcoa, followed up for 1 year.

OUTCOME VARIABLES

pain, physical function, complications, mortality, quality of life by WOMAC and SF-12 (at 0, 3, 6 and 12 months) and «Poor functional outcome» at one year (last quartile of the WOMAC in function area). Logistic regression was performed to examine predictors of poor functional outcome.

RESULTS

A total of 166 patients were followed up. The incidence of systemic and local complications was 6.3% and 14.5%, respectively, 4.3% readmissions and no deaths related to surgery. Close to 40 points improvement in pain, stiffness and WOMAC functional limitation, mainly in the first 3 months after surgery. A similar trend was seen, but lower in the physical and mental component of the SF12 (12 and 8 points, respectively). The previous score on the WOMAC function area and the physical component of SF-12, and the existence of any complications, are predictors of poor functional recovery.

DISCUSSION

The improvement experienced after the surgery is already very important before the third month. The functional and physical status before surgery and possible complications of surgery are significant determinants of the results.

Venous thromboembolism and bleeding after total knee and hip arthroplasty. Findings from the Spanish National Discharge Database

The impact of venous thromboembolism (VTE) and bleeding in patients undergoing major joint surgery has not been thoroughly studied. The Spanish National Discharge Database during the years 2005-2006 was used to assess the frequency and clinical impact of VTE and bleeding after elective total knee (TKA) or hip (THA) arthroplasty. Of 58,037 patients undergoing TKA, 0.18% (95% confidence interval [CI]: 0.15-0.22) were diagnosed with pulmonary embolism (PE), 0.57% (95% CI: 0.51-0.63) with deep-vein thrombosis (DVT), 1.20% (95% CI: 1.12-1.30) had bleeding complications, and 0.09% (95% CI: 0.07-0.12) died. Of 54 patients who died, 20.4% (95% CI: 10.7-35.4) had been diagnosed with PE, 3.70% (95% CI: 0.63-11.7) with DVT, and 13.0% (95% CI: 5.67-25.6) had bled. Of 31,769 patients undergoing elective THA, 0.23% (95% CI: 0.18-0.29) were diagnosed with PE, 0.44% (95% CI: 0.37-0.52) with DVT, 1.21% (95% CI: 1.10-1.34) bled, and 0.16% (95% CI: 0.12-0.21) died. Of 52 patients who died, 13.5% (95% CI: 6.08-24.8) had been diagnosed with PE, and 9.61% (95% CI: 3.52-21.3) had bled. On multivariable analysis, PE (odds ratio [OR]: 157; 95% CI: 75-328), DVT (OR: 6.3; 95% CI: 1.5-27) and bleeding (OR: 8.5; 95% CI: 3.6-20) were independent predictors for death after TKA. After THA, only PE (OR: 65; 95% CI: 26-160) and bleeding (OR: 6.4; 95% CI: 2.3-17) predicted the risk for death. Bleeding, DVT, and PE, arising after TKA were all independent predictors for death. Their increase in risk was, however, substantially higher for PE. After THA, only PE and bleeding independently predicted death.