Dataset Information

Development and validation of risk prediction model for venous thromboembolism in postpartum women: multinational cohort study.

ABSTRACT:

Objective

To develop and validate a risk prediction model for venous thromboembolism in the first six weeks after delivery (early postpartum).

Design

Cohort study.

Setting

Records from England based Clinical Practice Research Datalink (CPRD) linked to Hospital Episode Statistics (HES) and data from Sweden based registry.

Participants

All pregnant women registered with CPRD-HES linked data between 1997 and 2014 and Swedish medical birth registry between 2005 and 2011 with postpartum follow-up.

Main outcome measure

Multivariable logistic regression analysis was used to develop a risk prediction model for postpartum venous thromboembolism based on the English data, which was externally validated in the Swedish data.

Results

433?353 deliveries were identified in the English cohort and 662?387 in the Swedish cohort. The absolute rate of venous thromboembolism was 7.2 per 10?000 deliveries in the English cohort and 7.9 per 10?000 in the Swedish cohort. Emergency caesarean delivery, stillbirth, varicose veins, pre-eclampsia/eclampsia, postpartum infection, and comorbidities were the strongest predictors of venous thromboembolism in the final multivariable model. Discrimination of the model was similar in both cohorts, with a C statistic above 0.70, with excellent calibration of observed and predicted risks. The model identified more venous thromboembolism events than the existing national English (sensitivity 68% v 63%) and Swedish guidelines (30% v 21%) at similar thresholds.

Conclusion

A new prediction model that quantifies absolute risk of postpartum venous thromboembolism has been developed and externally validated. It is based on clinical variables that are available in many developed countries at the point of delivery and could serve as the basis for real time decisions on obstetric thromboprophylaxis.

SUBMITTER: Sultan AA

PROVIDER: S-EPMC5137302 | biostudies-literature | 2016 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Development and validation of risk prediction model for venous thromboembolism in postpartum women: multinational cohort study.

Sultan Alyshah Abdul AA West Joe J Grainge Matthew J MJ Riley Richard D RD Tata Laila J LJ Stephansson Olof O Fleming Kate M KM Nelson-Piercy Catherine C Ludvigsson Jonas F JF

BMJ (Clinical research ed.) 20161205

<h4>Objective</h4> To develop and validate a risk prediction model for venous thromboembolism in the first six weeks after delivery (early postpartum).<h4>Design</h4> Cohort study.<h4>Setting</h4> Records from England based Clinical Practice Research Datalink (CPRD) linked to Hospital Episode Statistics (HES) and data from Sweden based registry.<h4>Participants</h4> All pregnant women registered with CPRD-HES linked data between 1997 and 2014 and Swedish medical birth registry between 2005 and 2 ...[more]

PMID: 27919934

Similar Datasets

Project description: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.

Project description:ImportanceThe 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.ObjectiveTo validate the ONKOTEV score as a novel RAM to assess the risk of VTE among outpatients with cancer.Design, setting, and participantsONKOTEV-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.ExposuresThe 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.Main outcomes and measuresThe primary outcome of the study was the incidence of VTE, including deep vein thrombosis and pulmonary embolism.ResultsA 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.Conclusions and relevanceThis 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.

Project description:BackgroundVenous thromboembolism is a common complication of cancer, but the risk of developing venous thromboembolism varies greatly among individuals and depends on numerous factors, including type of cancer. We aimed to develop and externally validate a clinical prediction model for cancer-associated venous thromboembolism.MethodsWe used data from the prospective Vienna Cancer and Thrombosis Study (CATS) cohort (n=1423) to select prognostic variables for inclusion in the model. We then validated the model in the prospective Multinational Cohort Study to Identify Cancer Patients at High Risk of Venous Thromboembolism (MICA) cohort (n=832). We calculated c-indices to show how the predicted incidence of objectively confirmed venous thromboembolism at 6 months compared with the cumulative 6-month incidences observed in both cohorts.FindingsTwo variables were selected for inclusion in the final clinical prediction model: tumour-site risk category (low or intermediate vs high vs very high) and continuous D-dimer concentrations. The multivariable subdistribution hazard ratios were 1·96 (95% CI 1·41-2·72; p=0·0001) for high or very high versus low or intermediate and 1·32 (95% CI 1·12-1·56; p=0·001) per doubling of D-dimer concentration. The cross-validated c-indices of the final model were 0·66 (95% CI 0·63-0·67) in CATS and 0·68 (0·62-0·74) in MICA. The clinical prediction model was adequately calibrated in both cohorts.InterpretationAn externally validated clinical prediction model incorporating only one clinical factor (tumour-site category) and one biomarker (D-dimer) predicted the risk of venous thromboembolism in ambulatory patients with solid cancers. This simple model is a considerable improvement on previous models for predicting cancer-associated venous thromboembolism, and could aid physicians in selection of patients who will likely benefit from thromboprophylaxis.FundingAustrian Science Fund, Austrian National Bank Memorial Fund, and participating hospitals.

Project description:AbstractMost 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.

Project description:BackgroundColorectal cancer (CRC) is a heterogeneous group of malignancies distinguished by distinct clinical features. The association of these features with venous thromboembolism (VTE) is yet to be clarified. Machine learning (ML) models are well suited to improve VTE prediction in CRC due to their ability to receive the characteristics of a large number of features and understand the dataset to obtain implicit correlations.MethodsData were extracted from 4,914 patients with colorectal cancer between August 2019 and August 2022, and 1,191 patients who underwent surgery on the primary tumor site with curative intent were included. The variables analyzed included patient-level factors, cancer-level factors, and laboratory test results. Model training was conducted on 30% of the dataset using a ten-fold cross-validation method and model validation was performed using the total dataset. The primary outcome was VTE occurrence in postoperative 30 days. Six ML algorithms, including logistic regression (LR), random forest (RF), extreme gradient boosting (XGBoost), weighted support vector machine (SVM), a multilayer perception (MLP) network, and a long short-term memory (LSTM) network, were applied for model fitting. The model evaluation was based on six indicators, including receiver operating characteristic curve-area under the curve (ROC-AUC), sensitivity (SEN), specificity (SPE), positive predictive value (PPV), negative predictive value (NPV), and Brier score. Two previous VTE models (Caprini and Khorana) were used as the benchmarks.ResultsThe incidence of postoperative VTE was 10.8%. The top ten significant predictors included lymph node metastasis, C-reactive protein, tumor grade, anemia, primary tumor location, sex, age, D-dimer level, thrombin time, and tumor stage. In our results, the XGBoost model showed the best performance, with a ROC-AUC of 0.990, a SEN of 96.9%, a SPE of 96.1% in training dataset and a ROC-AUC of 0.908, a SEN of 77.5%, a SPE of 93.7% in validation dataset. All ML models outperformed the previously developed models (Caprini and Khorana).ConclusionsThis study developed postoperative VTE predictive models using six ML algorithms. The XGBoost VTE model might supply a complementary tool for clinical VTE prophylaxis decision-making and the proposed risk factors could shed some light on VTE risk stratification in CRC patients.

Dataset Information

Development and validation of risk prediction model for venous thromboembolism in postpartum women: multinational cohort study.

Objective

Design

Setting

Participants

Main outcome measure

Results

Conclusion

Publications

Development and validation of risk prediction model for venous thromboembolism in postpartum women: multinational cohort study.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets