scholarly journals Risk Assessment of Pulmonary Metastasis for Cervical Cancer Patients by Ensemble Learning Models: A Large Population Based Real-World Study

2021 ◽  
Vol Volume 14 ◽  
pp. 8713-8723
Author(s):  
Menglin Zhu ◽  
Bo Wang ◽  
Tiejun Wang ◽  
Yilin Chen ◽  
Du He
Keyword(s):  
Risk Assessment ◽  
Cervical Cancer ◽  
Cancer Patients ◽  
Ensemble Learning ◽  
Pulmonary Metastasis ◽  
Real World ◽  
Large Population ◽  
Population Based ◽  
Learning Models

scholarly journals Risk Assessment of Bone Metastasis for Cervical Cancer Patients by Multiple Models: A Large Population Based Real-World Study

2021 ◽  
Vol 8 ◽  
Author(s):  
Yun Han ◽  
Bo Wang ◽  
Jinjin Zhang ◽  
Su Zhou ◽  
Jun Dai ◽  
...  
Keyword(s):  
Machine Learning ◽  
Risk Assessment ◽  
Cervical Cancer ◽  
Bone Metastasis ◽  
Predictive Model ◽  
Cancer Patients ◽  
Roc Curve ◽  
Predictive Models ◽  
Population Based ◽  
Machine Learning Algorithms

Background: Population-based data on the risk assessment of newly diagnosed cervical cancer patients' bone metastasis (CCBM) are lacking. This study aimed to develop various predictive models to assess the risk of bone metastasis via machine learning algorithms.Materials and Methods: We retrospectively reviewed the CCBM patients from the Surveillance, Epidemiology, and End Results (SEER) database of the National Cancer Institute to risk factors of the presence of bone metastasis. Clinical usefulness was assessed by Akaike information criteria (AIC) and multiple machine learning algorithms based predictive models. Concordance index (C-index) and receiver operating characteristic (ROC) curve were used to define the predictive and discriminatory capacity of predictive models.Results: A total of 16 candidate variables were included to develop predictive models for bone metastasis by machine learning. The areas under the ROC curve (AUCs) of the random forest model (RF), generalized linear model (GL), support vector machine (SVM), eXtreme Gradient Boosting (XGBoost), artificial neutral network (ANN), decision tree (DT), and naive bayesian model (NBM) ranged from 0.85 to 0.93. The RF model with 10 variables was developed as the optimal predictive model. The weight of variables indicated the top seven factors were organ-site metastasis (liver, brain, and lung), TNM stage and age.Conclusions: Multiple machine learning based predictive models were developed to identify risk of bone metastasis in cervical cancer patients. By incorporating clinical characteristics and other candidate variables showed robust risk stratification for CCBM patients, and the RF predictive model performed best among these predictive models.

scholarly journals Nomogram Models for Predicting Risk and Prognosis of Newly Diagnosed Ovarian Cancer Patients with Liver Metastases - A Large Population-Based Real-World Study

2021 ◽  
Vol 12 (24) ◽  
pp. 7255-7265
Author(s):  
Gui-Min Hou ◽  
Chuang Jiang ◽  
Jin-peng Du ◽  
Chang Liu ◽  
Xiang-zheng Chen ◽  
...  
Keyword(s):  
Ovarian Cancer ◽  
Liver Metastases ◽  
Cancer Patients ◽  
Real World ◽  
Large Population ◽  
Population Based ◽  
Newly Diagnosed

Abstract P005: Comparative Effectiveness of Rivaroxaban versus Warfarin for the Treatment of Patients with Non-valvular Atrial Fibrillation

Circulation ◽  
2016 ◽  
Vol 133 (suppl_1) ◽  
Author(s):  
Faye L Norby ◽  
Lindsay G Bengtson ◽  
Lin Y Chen ◽  
Richard F MacLehose ◽  
Pamela L Lutsey ◽  
...  
Keyword(s):  
Atrial Fibrillation ◽  
Ischemic Stroke ◽  
Real World ◽  
Proportional Hazards ◽  
Large Population ◽  
Population Based ◽  
Cox Proportional Hazards ◽  
Gi Bleeding ◽  
Cox Proportional Hazards Models ◽  
The Us

Background: Rivaroxaban is a novel oral anticoagulant approved in the US in 2011 for prevention of stroke and systemic embolism in patients with non-valvular atrial fibrillation (NVAF). Information on risks and benefits among rivaroxaban users in real-world populations is limited. Methods: We used data from the US MarketScan Commercial and Medicare Supplemental databases between 2010 and 2013. We selected patients with a history of NVAF and initiating rivaroxaban or warfarin. Rivaroxaban users were matched with up to 5 warfarin users by age, sex, database enrollment date and drug initiation date. Ischemic stroke, intracranial bleeding (ICB), myocardial infarction (MI), and gastrointestinal (GI) bleeding outcomes were defined by ICD-9-CM codes in an inpatient claim after drug initiation date. Cox proportional hazards models were used to assess the association between rivaroxaban vs. warfarin use and outcomes adjusting for age, sex, and CHA2DS2-VASc score. Separate models were used to compare a) new rivaroxaban users with new warfarin users, and b) switchers from warfarin to rivaroxaban to continuous warfarin users. Results: Our analysis included 34,998 rivaroxaban users matched to 102,480 warfarin users with NVAF (39% female, mean age 71), in which 487 ischemic strokes, 179 ICB, 647 MI, and 1353 GI bleeds were identified during a mean follow-up of 9 months. Associations of rivaroxaban vs warfarin were similar in new users and switchers; therefore we pooled both analyses. Rivaroxaban users had lower rates of ICB (hazard ratio (HR) (95% confidence interval (CI)) = 0.72 (0.46, 1.12))) and ischemic stroke (HR (95% CI) = 0.88 (0.68, 1.13)), but higher rates of GI bleeding (HR (95% CI) = 1.15 (1.01, 1.33)) when compared to warfarin users (table). Conclusion: In this large population-based study of NVAF patients, rivaroxaban users had a non-significant lower risk of ICB and ischemic stroke than warfarin users, but a higher risk of GI bleeding. These real-world findings are comparable to results reported in published clinical trials.

Sign in / Sign up

Export Citation Format

Share Document