Dataset Information

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

ABSTRACT:

Abstract

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.

SUBMITTER: Lin CC

PROVIDER: S-EPMC8483831 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

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: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: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:Purpose This study aimed to develop and validate a specific risk-stratification nomogram model for the prediction of venous thromboembolism(VTE) in hospitalized patients with lung cancer using readily obtainable demographic, clinical and therapeutic characteristics, thus guiding the individualized decision-making on thromboprophylaxis on the basis of VTE risk levels. Methods We performed a retrospective case–control study among newly diagnosed lung cancer patients hospitalized between January 2016 and December 2021. Included in the cohort were 234 patients who developed PTE and 936 non-VTE patients. The patients were randomly divided into the derivation group (70%, 165 VTE patients and 654 non-VTE patients) and the validation group (30%, 69 VTE patients and 282 non-VTE patients). Cut off values were established using a Youden´s Index. Univariate and multivariate regression analyses were used to determine independent risk factors associated with VTE. Variance Inflation Factor(VIF) was used for collinearity diagnosis of the covariates in the model. The model was validated by the consistency index (C-index), receiver operating characteristic curves(ROC) and the calibration plot with the Hosmer-Lemeshow goodness-of-fit test. The clinical utility of the model was assessed through decision curve analysis(DCA). Further, the comparison of nomogram model with current models(Khorana, Caprini, Padua and COMPASS-CAT) was performed by comparing ROC curves using the DeLong’s test. Results The predictive nomogram modle comprised eleven variables: overweight(24-28) defined by body mass index (BMI): [odds ratio (OR): 1.90, 95% confidence interval (CI): 1.19-3.07], adenocarcinoma(OR:3.00, 95% CI: 1.88-4.87), stageIII-IV(OR:2.75, 95%CI: 1.58-4.96), Central venous catheters(CVCs) (OR:4.64, 95%CI: 2.86-7.62), D-dimer levels≥2.06mg/L(OR:5.58, 95%CI:3.54-8.94), PT levels≥11.45sec(OR:2.15, 95% CI:1.32-3.54), Fbg levels≥3.33 g/L(OR:1.76, 95%CI:1.12-2.78), TG levels≥1.37mmol/L (OR:1.88, 95%CI:1.19-2.99), ROS1 rearrangement(OR:2.87, 95%CI:1.74-4.75), chemotherapy history(OR:1.66, 95%CI:1.01-2.70) and radiotherapy history(OR:1.96, 95%CI:1.17-3.29). Collinearity analysis with demonstrated no collinearity among the variables. The resulting model showed good predictive performance in the derivation group (AUC 0.865, 95% CI: 0.832-0.897) and in the validation group(AUC 0.904,95%CI:0.869-0.939). The calibration curve and DCA showed that the risk-stratification nomogram had good consistency and clinical utility. Futher, the area under the ROC curve for the specific VTE risk-stratification nomogram model (0.904; 95% CI:0.869-0.939) was significantly higher than those of the KRS, Caprini, Padua and COMPASS-CAT models(Z=12.087, 11.851, 9.442, 5.340, all P<0.001, respectively). Conclusion A high-performance nomogram model incorporated available clinical parameters, genetic and therapeutic factors was established, which can accurately predict the risk of VTE in hospitalized patients with lung cancer and to guide individualized decision-making on thromboprophylaxis. Notably, the novel nomogram model was significantly more effective than the existing well-accepted models in routine clinical practice in stratifying the risk of VTE in those patients. Future community-based prospective studies and studies from multiple clinical centers are required for external validation.

Project description:ObjectiveUsing primary care data, develop and validate sex-specific prognostic models that estimate the 10-year risk of people with non-diabetic hyperglycaemia developing type 2 diabetes.DesignRetrospective cohort study.SettingPrimary care.Participants154 705 adult patients with non-diabetic hyperglycaemia.Primary outcomeDevelopment of type 2 diabetes.MethodsThis study used data routinely collected in UK primary care from general practices contributing to the Clinical Practice Research Datalink. Patients were split into development (n=109 077) and validation datasets (n=45 628). Potential predictor variables, including demographic and lifestyle factors, medical and family history, prescribed medications and clinical measures, were included in survival models following the imputation of missing data. Measures of calibration at 10 years and discrimination were determined using the validation dataset.ResultsIn the development dataset, 9332 patients developed type 2 diabetes during 293 238 person-years of follow-up (31.8 (95% CI 31.2 to 32.5) per 1000 person-years). In the validation dataset, 3783 patients developed type 2 diabetes during 115 113 person-years of follow-up (32.9 (95% CI 31.8 to 33.9) per 1000 person-years). The final prognostic models comprised 14 and 16 predictor variables for males and females, respectively. Both models had good calibration and high levels of discrimination. The performance statistics for the male model were: Harrell's C statistic of 0.700 in the development and 0.701 in the validation dataset, with a calibration slope of 0.974 (95% CI 0.905 to 1.042) in the validation dataset. For the female model, Harrell's C statistics were 0.720 and 0.718, respectively, while the calibration slope was 0.994 (95% CI 0.931 to 1.057) in the validation dataset.ConclusionThese models could be used in primary care to identify those with non-diabetic hyperglycaemia most at risk of developing type 2 diabetes for targeted referral to the National Health Service Diabetes Prevention Programme.

Dataset Information

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

Abstract

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets