Prediction Model For Venous Thromboembolism Research Articles

Establishment of a prediction model for venous thromboembolism in patients with acute exacerbation of chronic obstructive pulmonary disease based on serum homocysteine levels and Wells scores: a retrospective cohort study

BackgroundWe evaluated the diagnostic value of homocysteine (Hcy) levels combined with the Wells score and established a prediction model for venous thromboembolism (VTE) occurrence in patients with acute exacerbations of chronic obstructive pulmonary disease (AECOPD) based on the Hcy level and the Wells score.Patients and methodsClinical information from 914 patients with AECOPD was retrospectively collected in our hospital from June 2020 to October 2023. Receiver operating characteristic curves were plotted to evaluate the diagnostic ability of Hcy concentrations combined with Wells scores and the prediction ability of the model. Univariate and multivariate logistic regressions were used to explore the effects of Hcy levels and the Wells score on VTE occurrence. A nomogram was established for individual risk evaluation.ResultsHcy levels and Wells scores were significantly greater in the VTE group than in the non-VTE group (P < 0.001). The diagnostic ability of Hcy levels combined with the Wells score was greater than that Hcy levels or the Wells score alone. The AUC of the combined parameters was 0.935, with a sensitivity of 0.864 and a specificity of 0.855. Multivariate logistic regression indicated that elevated Hcy levels (OR:5.17, 95%CI: 3.76–7.09, P < 0.001) and Wells score (OR: 5.26, 95%CI: 3.22–8.59, P < 0.001) were independently associated with the risk of developing VTE in AECOPD patients. Decision curve analysis indicated that the net benefit of the nonadherence prediction nomogram was greater than that of the models adjusted for no or all variables, with a threshold of approximately 0.1-1.0.ConclusionsThe established prediction model can be used to evaluate an individual’s risk of developing VTE on the basis of the Hcy level, Wells score, and clinical parameters. AECOPD patients may benefit from the early intervention based on estimated risk probability.

Risk factor analysis and prediction model construction for surgical patients with venous thromboembolism: A prospective study

Abstract Objective: Patients undergoing surgery are at high risk of developing venous thromboembolism (VTE). This study aimed to determine the predictive value of risk factors for VTE in surgical patients and to develop a prediction model by integrating independent predictors. Methods: A total of 1111 patients who underwent surgery at clinical departments in a tertiary general hospital were recruited between May and July 2021. Clinical data, including patient-related, surgery-related, and laboratory parameters, were extracted from the hospital information system and electronic medical records. A VTE prediction model incorporating ten risk variables was constructed using artificial neural networks (ANNs). Results: Ten independent factors (X1: age, X2: alcohol consumption, X3: hypertension, X4: bleeding, X5: blood transfusions, X6: general anesthesia, X7: intrathecal anesthesia, X8: D-dimer, X9: C-reactive protein, and X10: lymphocyte percentage) were identified as associated with an increased risk of VTE. Ten-fold cross-validation results showed that the ANN model was capable of predicting VTE in surgical patients, with an area under the curve (AUC) of 0.89, a Brier score of 0.01, an accuracy of 0.96, and a F1 score of 0.92. The ANN model slightly outperformed the logistic regression model and the Caprini model, but a DeLong test showed that the statistical difference in the AUCs of the ANN and logistic regression models was insignificant (P&gt;0.05). Conclusion: Ten statistical indicators relevant to VTE risk prediction for surgical patients were identified, and ANN and logistic regression both showed promising results as decision-supporting tools for VTE prediction.

Derivation of a Risk Prediction Model for Venous Thromboembolism in Adult Patients with Acute Myeloid Leukemia

Background: Venous thromboembolism (VTE) is a well-established complication of malignancy associated with high morbidity. Many validated scoring systems exist to predict risk of VTE in patients with solid tumors. However, there are no models that can prospectively identify patients at high risk for the development of VTE in acute myeloid leukemia (AML). The purpose of this study was to determine risk factors for the development of VTE in a large cohort of AML patients and to develop a risk stratification model to predict VTE risk in this patient population. Methods: Adult patients presenting to the University of Wisconsin-Madison with newly-diagnosed AML from 1/1/2010 through 12/31/2021 were included in this retrospective cohort study. The primary end point was VTE within one year of diagnosis. Univariate logistic regression models were used to assess the association of each variable with development of VTE. Multivariate analysis was then completed using 16 candidate variables including demographics (sex, race, age at diagnosis), comorbidities (hypertension, diabetes, coronary artery disease, asthma/COPD), body mass index (BMI), Eastern Cooperative Oncology Group performance status (ECOG PS), history of solid organ or hematologic malignancy, smoking status, indwelling venous catheter, history of VTE, and baseline laboratory values (white blood cell count, hemoglobin, platelet count). Non-normally distributed continuous candidates were log10-transformed, then stepwise selection was used on a training set to choose predictive variables to construct a risk score to predict VTE within one year of AML diagnosis. Results: 326 patients with AML were included in the analysis. The median age at diagnosis was 60 years (range 19-92 years), 55% of the study population was male, and 94% were Caucasian race. 59 patients (18%) experienced VTE within one year of diagnosis. Age at diagnosis (OR 0.98, 95% CI, 0.963-0.998, p=0.033), BMI (OR 1.058, 95% CI, 1.02-1.10, p=0.005), hypertension (OR 0.522, 95% CI, 0.29-0.96, p=0.035) and platelets (OR 3.16, 95% CI, 1.44-6.94, p = 0.004) were individually associated with VTE. In a subgroup analysis of 278 patients with next generation sequencing data available, mutations in DNA methylation genes (DNMT3A, DNMT1, IDH1, IDH2, TET2) were associated with an increased risk of VTE (OR 1.911, 95% CI 1.017-3.591, p=0.0442, Table 1). A multivariate logistic regression model identified six independent predictors of VTE including platelet count &amp;gt;150,000 (OR 1.64, 95% CI 0.65-4.14, p=0.2953), BMI &amp;gt;25 (OR 3.10, 95% CI 1.22-7.86, p=0.0173), hypertension (OR 2.17, 95% CI 1.03-4.55, p=0.0410), history of other cancer (OR 1.72, 95% CI, 0.74-4.01, p=0.2109), diabetes (OR 2.05, 95% CI 0.73-5.73, p=0.1718), and ECOG PS (OR 1.33, 95% CI, 0.66-2.65, p=0.4263). Subsequently, a risk score was constructed from the multivariable model (3*platelets&amp;gt;150 + 8*BMI&amp;gt;25 + 5*NoHTN + 3*NoOtherCancer + 4*Diabetes + 1*ECOG0). Patients were categorized into three groups: low (score&amp;lt;9), moderate (9score&amp;lt;12), and high (score) risk of developing VTE (Table 2). Rates of VTE within one year of AML diagnosis were 3.2%, 16.4%, and 23.6% in the low, moderate, and high risk groups respectively. The model had an external AUC=0.704 when applied to our test set. Conclusions: Our study demonstrates a high rate of early VTE in patients with AML at 18%, highlighting the importance of identifying those at higher risk which would allow for early screening, patient education, and consideration of thromboprophylaxis. On multivariable analysis, we found that normal or elevated platelet count &amp;gt;150, BMI 25, and diabetes were associated with an increased risk of early VTE. Surprisingly, higher ECOG PS, history of malignancy, and hypertension were associated with a decreased risk of early VTE in our cohort. A risk prediction model incorporating these findings was able to identify patients with low, moderate, and high risk of VTE. This model may help with clinical decision making, such as the consideration of thromboprophylaxis for patients with a moderate or high risk score. However, prospective validation of this model in a larger cohort of patients is needed. In summary, we propose a risk prediction model for the development of VTE in AML that can now be validated in order to provide optimal supportive care for this patient population.

Prediction of Venous Thromboembolism in Patients with Cancer Using Neural Network

Background Venous thromboembolism (VTE) is a frequent complication in patients with cancer and can be provoked by the tumor or treatment.An imbalance between coagulation factors and anticoagulant proteinshas been associated with enhanced VTE risk in these patients. Particularly, elevated fibrinogen, FVIII and von Willebrand factor and decreased antithrombin, increase the risk of cancer-associated VTE. Aim To investigate whether artificial intelligence methodologies based on input of patient characteristics and coagulation parameters can predict VTE in patients with cancer. Methods In the ongoing study, all-type of cancer patients with or without previous VTE are enrolledand thrombotic events were followed up over a period of 2 years or until death. Demographics, cancer type and treatment, medications, and VTE events before and during the study were documented. Coagulation factors, antithrombin, fibrinogen, FVIII and Von Willebrand Factor were determined in all samples. The artificial intelligence method neural networks was used to develop a prediction model for VTE in patients with cancer. Final input parameters were age, sex, prior VTE, use of anticoagulants and statins, fibrinogen, antithrombin, FVIII and von Willebrand factor. Results To date, 118 patients were enrolled in the study, and 28 patients completed the follow-up (24%). A neural network was developed in the sub-cohort of patients that had completed the follow-up period (n=28), of which 7 patients had a VTE during the follow-up period. The top-performing neural network was selected. The developed neural network had an overall accuracy of 98%, a sensitivity of 100% and a specificity of 95%. Furthermore, the negative predictive value was 100% and the positive predictive value was 97% (Figure 1A). The most important variables in the neural network were Von Willebrand Factor, age, anticoagulant therapy and history of VTE, contributing 13% each. Sex, antithrombin and fibrinogen contributed 11%, 10% and 10%, respectively, whereas FVIII (6%) , statin use (5%) and antiplatelet therapy (5%) had a minor contribution (Figure 1B). We validated the neural network in the “on-study” sub-cohort, consisting of patients that did not yet complete the follow-up period. Until now, 2 VTE events were recorded in this group; other patients in the sub-cohort remain potentially at risk for VTE. The neural network was able to accurately discern the patients that experienced a VTE during follow-up, resulting in a sensitivity of 100%, and a negative predictive value of 100%. Moreover, the neural network indicated an increased risk of VTE in 37 subjects out of 88 “on-study” patients. The neural network scores the risk of VTE as a value ranging from 0 (no risk) to 1 (high risk). We stratified the neural network VTE risk estimate according to the Khorana and PROTECHT scores for each patient and found a positive association between both the Khorana and PROTECT scores and the neural network VTE estimate (p&amp;lt;0.05). Conclusions A neural network based on patient characteristics, coagulation parameters, and medication use predicts VTE in our cohort of cancer patients. Although the initial validation of the neural network is promising, further clinically validation is needed.

Development and Validation of a Clinical Prediction Model for Venous Thromboembolism Following Neurosurgery: A 6-Year, Multicenter, Retrospective and Prospective Diagnostic Cohort Study.

Based on the literature and data on its clinical trials, the incidence of venous thromboembolism (VTE) in patients undergoing neurosurgery has been 3.0%~26%. We used advanced machine learning techniques and statistical methods to provide a clinical prediction model for VTE after neurosurgery. All patients (n = 5867) who underwent neurosurgery from the development and retrospective internal validation cohorts were obtained from May 2017 to April 2022 at the Department of Neurosurgery at the Sanbo Brain Hospital. The clinical and biomarker variables were divided into pre-, intra-, and postoperative. A univariate logistic regression (LR) was applied to explore the 67 candidate predictors with VTE. We used a multivariable logistic regression (MLR) to select all significant MLR variables of MLR to build the clinical risk prediction model. We used a random forest to calculate the importance of significant variables of MLR. In addition, we conducted prospective internal (n = 490) and external validation (n = 2301) for the model. Eight variables were selected for inclusion in the final clinical prediction model: D-dimer before surgery, activated partial thromboplastin time before neurosurgery, age, craniopharyngioma, duration of operation, disturbance of consciousness on the second day after surgery and high dose of mannitol, and highest D-dimer within 72 h after surgery. The area under the curve (AUC) values for the development, retrospective internal validation, and prospective internal validation cohorts were 0.78, 0.77, and 0.79, respectively. The external validation set had the highest AUC value of 0.85. This validated clinical prediction model, including eight clinical factors and biomarkers, predicted the risk of VTE following neurosurgery. Looking forward to further research exploring the standardization of clinical decision-making for primary VTE prevention based on this model.

Development and external validation of a prediction model for venous thromboembolism in systemic lupus erythematosus

ObjectivePatients with systemic lupus erythematosus (SLE) have an increased risk of venous thromboembolism (VTE). We conducted this study to develop a risk score algorithm for VTE in patients with SLE...

A New Risk Prediction Model for Venous Thromboembolism and Death in Ambulatory Lung Cancer Patients.

(1) Background: Venous thromboembolism (VTE) is a frequent complication in ambulatory lung cancer patients during chemotherapy and is associated with increased mortality. (2) Methods: We analyzed 568 newly diagnosed metastatic lung cancer patients prospectively enrolled in the HYPERCAN study. Blood samples collected before chemotherapy were tested for thrombin generation (TG) and a panel of hemostatic biomarkers. The Khorana risk score (KRS), new-Vienna CATS, PROTECHT, and CONKO risk assessment models (RAMs) were applied. (3) Results: Within 6 months, the cumulative incidences of VTE and mortality were 12% and 29%, respectively. Patients with VTE showed significantly increased levels of D-dimer, FVIII, prothrombin fragment 1 + 2, and TG. D-dimer and ECOG performance status were identified as independent risk factors for VTE and mortality by multivariable analysis and utilized to generate a risk score that provided a cumulative incidence of VTE of 6% vs. 25%, death of 19% vs. 55%, and in the low- vs. high-risk group, respectively (p < 0.001). While all published RAMs significantly stratified patients for risk of death, only the CATS and CONKO were able to stratify patients for VTE. (4) Conclusions: A new prediction model was generated to stratify lung cancer patients for VTE and mortality risk, where other published RAMs failed.

Validation of the ONKOTEV Risk Prediction Model for Venous Thromboembolism in Outpatients With Cancer

The assessment of the risk of venous thromboembolism (VTE) among outpatients with cancer represents an unsolved topic. Current international guidelines recommend primary prophylaxis for patients at intermediate to high risk of VTE, indicated by a Khorana score of 2 or more. A previous prospective study developed the ONKOTEV score, a 4-variable risk assessment model (RAM) consisting of a Khorana score of more than 2, metastatic disease, vascular or lymphatic compression, and previous VTE event. To validate the ONKOTEV score as a novel RAM to assess the risk of VTE among outpatients with cancer. ONKOTEV-2 is a noninterventional prognostic study conducted in 3 European centers located in Italy, Germany, and the United Kingdom among a prospective cohort of 425 ambulatory patients with a histologically confirmed diagnosis of a solid tumor who were receiving active treatments. The total study duration was 52 months, with an accrual period of 28 months (from May 1, 2015, to September 30, 2017) and an overall follow up-period of 24 months (data were censored September 30, 2019). Statistical analysis was performed in October 2019. The ONKOTEV score was calculated for each patient at baseline by collecting clinical, laboratory, and imaging data from tests performed for routine practice. Each patient was then observed to detect any thromboembolic event throughout the study period. The primary outcome of the study was the incidence of VTE, including deep vein thrombosis and pulmonary embolism. A total of 425 patients (242 women [56.9%]; median age, 61 years [range, 20-92 years]) were included in the validation cohort of the study. The cumulative incidences for the risk of developing VTE at 6 months were 2.6% (95% CI, 0.7%-6.9%), 9.1% (95% CI, 5.8%-13.2%), 32.3% (95% CI, 21.0%-44.1%), and 19.3% (95% CI, 2.5%-48.0%), respectively, among 425 patients with an ONKOTEV score of 0, 1, 2, and greater than 2 (P < .001). The time-dependent area under the curve at 3, 6, and 12 months was 70.1% (95% CI, 62.1%-78.7%), 72.9% (95% CI, 65.6%-79.1%), and 72.2% (95% CI, 65.2%-77.3%), respectively. This study suggests that, because the ONKOTEV score has been validated in this independent study population as a novel predictive RAM for cancer-associated thrombosis, it can be adopted into practice and into clinical interventional trials as a decision-making tool for primary prophylaxis.

Machine learning predicts cancer-associated venous thromboembolism using clinically available variables in gastric cancer patients

Stomach cancer (GC) has one of the highest rates of thrombosis among cancers and can lead to considerable morbidity, mortality, and additional costs. However, to date, there is no suitable venous thromboembolism (VTE) prediction model for gastric cancer patients to predict risk. Therefore, there is an urgent need to establish a clinical prediction model for VTE in gastric cancer patients. We collected data on 3092 patients between January 1, 2018 and December 31, 2021. And after feature selection, 11 variables are reserved as predictors to build the model. Five machine learning (ML) algorithms are used to build different VTE predictive models. The accuracy, sensitivity, specificity, and AUC of these five models were compared with traditional logistic regression (LR) to recommend the best VTE prediction model. RF and XGB models have selected the essential characters in the model: Clinical stage, Blood Transfusion History, D-Dimer, AGE, and FDP. The model has an AUC of 0.825, an accuracy of 0.799, a sensitivity of 0.710, and a specificity of 0.802 in the validation set. The model has good performance and high application value in clinical practice, and can identify high-risk groups of gastric cancer patients and prevent venous thromboembolism.

Abnormal metaphase cytogenetics predicts venous thromboembolism in myeloma: derivation and validation of the PRISM score

AbstractAlthough venous thromboembolism (VTE) is an important treatment and disease-related complication in myeloma, a validated risk prediction model including disease-specific variables such as cytogenetics or tumor burden is lacking. The aim of this study was to develop a new risk prediction model for VTE in the context of modern antimyeloma therapy. All consecutive patients diagnosed at the Cleveland Clinic between 2008 and 2018 and with available data on baseline candidate risk factors constituted the derivation cohort. The primary outcome was VTE (deep venous thrombosis/pulmonary embolism) within 1 year of treatment initiation. A multivariable model was used, and weights were derived from subdistribution hazard ratios to construct a risk score. The model was validated both by internal bootstrap validation and in an external validation cohort. The derivation cohort consisted of 783 patients. A 5-component risk prediction tool, named the PRISM score, was developed, including the following variables: prior VTE, prior surgery, immunomodulatory drug use, abnormal metaphase cytogenetics, and Black race. The c-statistic of the model was 0.622 (95% confidence interval [CI], 0.567-0.674). The model stratified patients into low, intermediate, and high risk, with 12-month cumulative VTE incidence of 2.7%, 10.8%, and 36.5%, respectively. Risk of VTE increased significantly with increasing score in both the derivation and the external validation data sets, with a subdistribution hazard ratio per 1-point increase of 1.28 (95% CI, 1.19-1.39; P < .001) and 1.23 (95% CI, 1.07-1.41; P = .004) respectively. Although the PRISM score can guide clinicians in identifying patients at a high risk of VTE, additional external validation is necessary for incorporation into routine clinical practice.

Venous thromboembolism in COVID-19 patients and prediction model: a multicenter cohort study

BackgroundPatients with COVID-19 infection are commonly reported to have an increased risk of venous thrombosis. The choice of anti-thrombotic agents and doses are currently being studied in randomized controlled trials and retrospective studies. There exists a need for individualized risk stratification of venous thromboembolism (VTE) to assist clinicians in decision-making on anticoagulation. We sought to identify the risk factors of VTE in COVID-19 patients, which could help physicians in the prevention, early identification, and management of VTE in hospitalized COVID-19 patients and improve clinical outcomes in these patients.MethodThis is a multicenter, retrospective database of four main health systems in Southeast Michigan, United States. We compiled comprehensive data for adult COVID-19 patients who were admitted between 1st March 2020 and 31st December 2020. Four models, including the random forest, multiple logistic regression, multilinear regression, and decision trees, were built on the primary outcome of in-hospital acute deep vein thrombosis (DVT) and pulmonary embolism (PE) and tested for performance. The study also reported hospital length of stay (LOS) and intensive care unit (ICU) LOS in the VTE and the non-VTE patients. Four models were assessed using the area under the receiver operating characteristic curve and confusion matrix.ResultsThe cohort included 3531 admissions, 3526 had discharge diagnoses, and 6.68% of patients developed acute VTE (N = 236). VTE group had a longer hospital and ICU LOS than the non-VTE group (hospital LOS 12.2 days vs. 8.8 days, p < 0.001; ICU LOS 3.8 days vs. 1.9 days, p < 0.001). 9.8% of patients in the VTE group required more advanced oxygen support, compared to 2.7% of patients in the non-VTE group (p < 0.001). Among all four models, the random forest model had the best performance. The model suggested that blood pressure, electrolytes, renal function, hepatic enzymes, and inflammatory markers were predictors for in-hospital VTE in COVID-19 patients.ConclusionsPatients with COVID-19 have a high risk for VTE, and patients who developed VTE had a prolonged hospital and ICU stay. This random forest prediction model for VTE in COVID-19 patients identifies predictors which could aid physicians in making a clinical judgment on empirical dosages of anticoagulation.

Development and Validation of a Risk Prediction Model for Venous Thromboembolism in Lung Cancer Patients Using Machine Learning.

BackgroundThere is currently a lack of model for predicting the occurrence of venous thromboembolism (VTE) in patients with lung cancer. Machine learning (ML) techniques are being increasingly adapted for use in the medical field because of their capabilities of intelligent analysis and scalability. This study aimed to develop and validate ML models to predict the incidence of VTE among lung cancer patients.MethodsData of lung cancer patients from a Grade 3A cancer hospital in China with and without VTE were included. Patient characteristics and clinical predictors related to VTE were collected. The primary endpoint was the diagnosis of VTE during index hospitalization. We calculated and compared the area under the receiver operating characteristic curve (AUROC) using the selected best-performed model (Random Forest model) through multiple model comparison, as well as investigated feature contributions during the training process with both permutation importance scores and the impurity-based feature importance scores in random forest model.ResultsIn total, 3,398 patients were included in our study, 125 of whom experienced VTE during their hospital stay. The ROC curve and precision–recall curve (PRC) for Random Forest Model showed an AUROC of 0.91 (95% CI: 0.893–0.926) and an AUPRC of 0.43 (95% CI: 0.363–0.500). For the simplified model, five most relevant features were selected: Karnofsky Performance Status (KPS), a history of VTE, recombinant human endostatin, EGFR-TKI, and platelet count. We re-trained a random forest classifier with results of the AUROC of 0.87 (95% CI: 0.802–0.917) and AUPRC of 0.30 (95% CI: 0.265–0.358), respectively.ConclusionAccording to the study results, there was no conspicuous decrease in the model’s performance when use fewer features to predict, we concluded that our simplified model would be more applicable in real-life clinical settings. The developed model using ML algorithms in our study has the potential to improve the early detection and prediction of the incidence of VTE in patients with lung cancer.

Development and Validation of Clinical Prediction Model for Venous Thromboembolism Following Neurosurgery: A Single-Center, Retrospective, and Cohort Study

Development and Validation of Clinical Prediction Model for Venous Thromboembolism Following Neurosurgery: A Single-Center, Retrospective, and Cohort Study

Evaluation of the Khorana score for prediction of venous thromboembolism in patients with multiple myeloma

BackgroundGuidelines recommend thromboprophylaxis for patients with multiple myeloma (MM) at high risk for venous thromboembolism (VTE). However, the optimal risk prediction model for VTE in MM remains unclear. Khorana et al developed a VTE risk score (Khorana score) in ambulatory cancer patients receiving chemotherapy. We aimed to evaluate the predictive ability of the Khorana score in patients with MM. MethodsWe identified patients with MM within the Veterans Affairs health care system between 2006 and 2013. The Khorana score was calculated before treatment initiation. Using logistic regression, the relationship between risk group and VTE was assessed at 3 and 6 months. We tested model discrimination using the concordance statistic. ResultsIn the cohort of 2870 patients with MM, there were 1328 at low risk (0 points), 1521 at intermediate risk (1‐2 points), and 21 at high risk (≥3 points) for VTE by the Khorana score. The 6‐month cumulative incidence of VTE was 5.1% (95% confidence interval [CI], 4.0%‐6.4%) in low risk, 3.9% (95% CI, 3.0%‐5.0%) in intermediate risk, 4.8% (95% CI, 0.3%‐20.2%) in high risk. The Khorana score did not strongly discriminate between patients who did and did not develop VTEs at 3 or 6 months (concordance statistic, 0.58; 95% CI, 0.54‐0.63; and 0.53, 95% CI, 0.50‐0.57, respectively. ConclusionsIn conclusion, in this cohort of 2870 patients with MM, the Khorana score did not predict VTE. Our study supports the need to use myeloma‐specific risk models to predict VTE risk in patients with MM.

Derivation and validation of a clinical prediction model for risks of venous thromboembolism in diabetic and general populations.

Most studies on the prediction of venous thromboembolism (VTE) focused on hospitalized, surgery, and cancer patients or women receiving hormonal contraceptives or menopausal hormone therapy. No study considered diabetic and general populations to establish a VTE prediction model, especially in Asia. We developed a predictive model for VTE among type 2 diabetic patients and the general population.This study considered 2 nationwide retrospective cohort studies consisting of 52,427 diabetic participants and 508,664 participants from the general population aged 30 to 85 years during 2001 to 2004 in Taiwan. All participants were followed up until VTE event, death, or December 2011. The outcome event was VTE, including deep venous thrombosis and pulmonary embolism. Candidate predictors consisted of socio-demographic factors, diabetes-related factors and biomarkers, comorbidities, and medicine use. Our study followed the procedures proposed by the Framingham Heart Study to develop prediction models by using a Cox regression model. The predictive accuracy and performance characteristics were assessed using the area under curve of receiver operating characteristics curve and calibration of a risk score were performed by Hosmer–Lemeshow goodness-of-fit test.The common factors for persons with type 2 diabetes and general population included age, hospitalization status 1 year before the baseline, hypertension, chronic kidney disease, chronic obstructive pulmonary disease, and anti-diabetes medications; the specific factors for persons with type 2 diabetes consisted of body mass index, glycosylated hemoglobin A1C, and creatinine; and the factors for general population included gender, peripheral vascular disease, cancer, hypertension medication, cardiovascular medication, and non-steroidal anti-inflammatory drug. The area under curve of 3-, 5-, and 8-year VTE prediction models were 0.74, 0.71, and 0.69 in the diabetic population and 0.77, 0.76, and 0.75 in the general population, respectively.The new clinical prediction models can help identify a high risk of VTE and provide medical intervention in diabetic and general populations.

Use of Pharmacologic Prophylaxis Against Venous Thromboembolism in Hospitalized Injured Children.

Despite a practice management guideline and risk prediction model for venous thromboembolism (VTE), pediatric-specific evidence on pharmacologic prophylaxis is lacking. In a retrospective study, we characterized receipt of prophylaxis and explored its effectiveness in hospitalized injured patients below 18 years old using data from the Trauma Quality Improvement Program. Concordance of receipt of prophylaxis with guideline and predicted risk of VTE was estimated using κ statistic. Effectiveness was explored using cohorts matched based on the risk prediction model. A total of 11,165 (6.2%) of 180,932 patients received prophylaxis. Those who received prophylaxis were more commonly post-pubertal and more severely injured. Receipt of prophylaxis was fairly concordant with the guideline (κ=0.32) and predicted risk of VTE (κ=0.29). Receipt of prophylaxis was associated with higher rates of VTE likely due to confounding by indication. Low molecular weight heparin seemed more effective against VTE than unfractionated heparin (incidence rate ratio: 0.52; 95% confidence interval: 0.36, 0.75), but less effective when received ≥72 hours after admission to the hospital. We showed that hospitalized injured children did not commonly receive prophylaxis. We also showed that prophylaxis may be effective in hospitalized injured children, but it needs to be proven definitively in a randomized clinical trial.

Predicting the Incidence of Venous Thromboembolism Using the Khorana Score: A Literature Review

Venous thromboembolism (VTE) is the second most common cause of cancer-related deaths globally. The Khorana score, a VTE prediction model, is calculated using the site of cancer, white blood cell count, hemoglobin level, platelet count, and body mass index. This study aimed to investigate the usefulness of the Khorana score, using data available in the literature. On July 28, 2020, we collected papers using the following keywords: "cancer", "venous thromboembolism", "deep vein thrombosis", "pulmonary embolism", and "Khorana score" on PubMed. Papers published after 2016 were eligible. The selection criteria were as follows: "English or Japanese", "original paper", "abstract and full text", and "comply with the clinical question". There were 131 papers that matched the keywords, and 15 of them complied with the selection criteria. In 15 papers, Khorana score was calculated in 8047 patients. In the low- and intermediate-risk groups, 532 of 6812 patients developed VTE [7.8%, 95%confidence intervals (CI) 7.2-8.5], whereas in the high-risk group, 127 of 1235 patients developed VTE (10.3%, 95% CI 8.7-12.1) [odds ratio (OR) 1.3, 95% CI 1.0-1.6] (I2=0%, τ2=0, p=0.50). Venous thromboembolism prediction using the Khorana score might be useful. However, most of the number of VTE patients are in the low- and intermediate-risk groups. Therefore, a comprehensive evaluation according to clinical conditions is required, regardless of the risk classification using the Khorana score.

Derivation and Validation of a Prediction Model for Venous Thromboembolism in Primary Care.

Most episodes of venous thromboembolism (VTE) occurred in primary care. To date, no score potentially able to identify those patients who may deserve an antithrombotic prophylaxis has been developed. The objective of this study is to develop and validate a prediction model for VTE in primary care. Using the Health Search Database, we identified a cohort of 1,359,880 adult patients between 2002 and 2013. The date of the first General Practitioner's (GP) visit was the cohort entry date. All VTE cases (index date) observed up to December 2014 were identified. The cohort was randomly divided in a development and a validation cohort. According to nested case-cohort analysis, up to five controls were matched to their respective cases on month and year of cohort entry and duration of follow-up.The score was evaluated according to explained variance (pseudo R2) as a performance measure, ratio of predicted to observed cases as model calibration and area under the curve (AUC) as discrimination measure. The score was able to explain 27.9% of the variation for VTE occurrence. The calibration measure revealed a margin of error lower than 10% in 70% of the population. In terms of discrimination, AUC was 0.82 (95% confidence interval: 0.82-0.83). Results of sensitivity analyses substantially confirmed these findings. The present score demonstrated a very good accuracy in predicting the risk of VTE in primary care. This score may be therefore implemented in clinical practice so aiding GPs in making decision on patients potentially at risk of VTE.

Prediction of recurrent venous thrombosis in all patients with a first venous thrombotic event: The Leiden Thrombosis Recurrence Risk Prediction model (L-TRRiP).

BackgroundRecurrent venous thromboembolism (VTE) is common. Current guidelines suggest that patients with unprovoked VTE should continue anticoagulants unless they have a high bleeding risk, whereas all others can stop. Prediction models may refine this dichotomous distinction, but existing models apply only to patients with unprovoked first thrombosis. We aimed to develop a prediction model for all patients with first VTE, either provoked or unprovoked.Methods and findingsData were used from two population-based cohorts of patients with first VTE from the Netherlands (Multiple Environment and Genetic Assessment of Risk Factors for Venous Thrombosis [MEGA] follow-up study, performed from 1994 to 2009; model derivation; n = 3,750) and from Norway (Tromsø study, performed from 1999 to 2016; model validation; n = 663). Four versions of a VTE prediction model were developed: model A (clinical, laboratory, and genetic variables), model B (clinical variables and fewer laboratory markers), model C (clinical and genetic factors), and model D (clinical variables only). The outcome measure was recurrent VTE. To determine the discriminatory power, Harrell’s C-statistic was calculated. A prognostic score was assessed for each patient. Kaplan-Meier plots for the observed recurrence risks were created in quintiles of the prognostic scores. For each patient, the 2-year predicted recurrence risk was calculated. Models C and D were validated in the Tromsø study.During 19,201 person-years of follow-up (median duration 5.7 years) in the MEGA study, 507 recurrences occurred. Model A had the highest predictive capability, with a C-statistic of 0.73 (95% CI 0.71–0.76). The discriminative performance was somewhat lower in the other models, with C-statistics of 0.72 for model B, 0.70 for model C, and 0.69 for model D. Internal validation showed a minimal degree of optimism bias. Models C and D were externally validated, with C-statistics of 0.64 (95% CI 0.62–0.66) and 0.65 (95% CI 0.63–0.66), respectively. According to model C, in 2,592 patients with provoked first events, 367 (15%) patients had a predicted 2-year risk of >10%, whereas in 1,082 patients whose first event was unprovoked, 484 (45%) had a predicted 2-year risk of <10%. A limitation of both cohorts is that laboratory measurements were missing in a substantial proportion of patients, which therefore were imputed.ConclusionsThe prediction model we propose applies to patients with provoked or unprovoked first VTE—except for patients with (a history of) cancer—allows refined risk stratification, and is easily usable. For optimal individualized treatment, a management study in which bleeding risks are also taken into account is necessary.

Quick risk assessment profile (qRAP) is a prediction model for post-traumatic venous thromboembolism

ObjectiveThe Risk Assessment Profile (RAP) score is used as a tool of risk prediction in post-traumatic venous thromboembolism (VTE), but this scoring system is complicated to use in clinical settings due to its many variables. The objective of this study was to validate the utility of the RAP model and to develop a simpler risk prediction model for post-traumatic VTE. MethodsWe conducted an observational study at two emergency and critical care centres in Japan between 2013 and 2016. Consecutive adult trauma patients who survived for 24 h or more after admission to the hospital were enroled. One prediction model (quick RAP model) was created with 6 variables based on clinical utility, experience, and thrombogenic mechanism from 17 variables in the conventional RAP model. We calculated diagnostic performance with 95% confidence interval (95% CI) by exact method. ResultsWe identified and analysed 859 patients. Twenty-six patients (3.0%) had VTE (17 with deep venous thrombosis alone, 2 with pulmonary embolism alone, and 7 with both). In the external validation, the RAP model had a sensitivity of 100% (95% CI, 86.8–100%) and specificity of 37.9% (95% CI, 34.6–41.3%). In contrast, the qRAP model had a sensitivity of 96.2% (95% CI, 80.4–99.9%) and specificity of 56.2% (95% CI, 52.7–59.6%). In the internal validation, receiver-operating characteristic curve analysis showed that the two models had similar area under the curve values that were not significantly different (0.832 and 0.800, respectively; RAP vs qRAP, p = 0.477). ConclusionsWe developed a practical, modified predictive model for VTE, the qRAP model, which appeared only slightly less accurate than the conventional RAP model and had the advantage of being simpler to use to predict VTE. In our dataset, the conventional RAP model was also evaluated as useful for the prediction of post-traumatic VTE.