首页|Hospital General Universitario Gregorio Maranon Reports Findings in Venous Throm boembolism (Prediction model for major bleeding in anticoagulated patients with cancer-associated venous thromboembolism using machine learning and natural lang uage ...)
Hospital General Universitario Gregorio Maranon Reports Findings in Venous Throm boembolism (Prediction model for major bleeding in anticoagulated patients with cancer-associated venous thromboembolism using machine learning and natural lang uage ...)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-New research on Cardiovascular Disease s and Conditions - Venous Thromboembolism is the subject of a report. According to news reporting out of Madrid, Spain, by NewsRx editors, research stated, "We developed a predictive model to assess the risk of major bleeding (MB) within 6 months of primary venous thromboembolism (VTE) in cancer patients receiving anti coagulant treatment. We also sought to describe the prevalence and incidence of VTE in cancer patients, and to describe clinical characteristics at baseline and bleeding events during follow-up in patients receiving anticoagulants." Financial support for this research came from BMS-Pfizer Alliance. Our news journalists obtained a quote from the research from Hospital General Un iversitario Gregorio Maranon, "This observational, retrospective, and multicente r study used natural language processing and machine learning (ML), to analyze u nstructured clinical data from electronic health records from nine Spanish hospi tals between 2014 and 2018. All adult cancer patients with VTE receiving anticoa gulants were included. Both clinicAlly- and ML-driven feature selection was perf ormed to identify MB predictors. Logistic regression (LR), decision tree (DT), a nd random forest (RF) algorithms were used to train predictive models, which wer e validated in a hold-out dataset and compared to the previously developed CAT-B LEED score. Of the 2,893,108 cancer patients screened, in-hospital VTE prevalenc e was 5.8% and the annual incidence ranged from 2.7 to 3.9% . We identified 21,227 patients with active cancer and VTE receiving anticoagula nts (53.9% men, median age of 70 years). MB events after VTE diagn osis occurred in 10.9% of patients within the first six months. MB predictors included: hemoglobin, metastasis, age, platelets, leukocytes, and se rum creatinine. The LR, DT, and RF models had AUC-ROC (95% confide nce interval) values of 0.60 (0.55, 0.65), 0.60 (0.55, 0.65), and 0.61 (0.56, 0. 66), respectively. These models outperformed the CAT-BLEED score with values of 0.53 (0.48, 0.59)."
MadridSpainEuropeCancerCardiovas cular Diseases and ConditionsCyborgsDrugs and TherapiesEmbolism and Thromb osisEmerging TechnologiesHealth and MedicineHematologyMachine LearningNatural Language ProcessingOncologyThromboembolismVascular Diseases and Co nditionsVenous Thromboembolism
NETL
NSTL
