Dataset Information

Regression trees for predicting mortality in patients with cardiovascular disease: what improvement is achieved by using ensemble-based methods?

ABSTRACT: In biomedical research, the logistic regression model is the most commonly used method for predicting the probability of a binary outcome. While many clinical researchers have expressed an enthusiasm for regression trees, this method may have limited accuracy for predicting health outcomes. We aimed to evaluate the improvement that is achieved by using ensemble-based methods, including bootstrap aggregation (bagging) of regression trees, random forests, and boosted regression trees. We analyzed 30-day mortality in two large cohorts of patients hospitalized with either acute myocardial infarction (N = 16,230) or congestive heart failure (N = 15,848) in two distinct eras (1999-2001 and 2004-2005). We found that both the in-sample and out-of-sample prediction of ensemble methods offered substantial improvement in predicting cardiovascular mortality compared to conventional regression trees. However, conventional logistic regression models that incorporated restricted cubic smoothing splines had even better performance. We conclude that ensemble methods from the data mining and machine learning literature increase the predictive performance of regression trees, but may not lead to clear advantages over conventional logistic regression models for predicting short-term mortality in population-based samples of subjects with cardiovascular disease.

SUBMITTER: Austin PC

PROVIDER: S-EPMC3470596 | biostudies-other | 2012 Sep

REPOSITORIES: biostudies-other

ACCESS DATA

Similar Datasets

Project description:BackgroundPerinatal mortality in Ethiopia is the highest in Africa, with 68 per 1000 pregnancies intrapartum deaths. It is mainly associated with home delivery, which contributes to more than 75% of perinatal deaths. Financial constraints significantly impact timely access to maternal health care. Financial incentives, such as health insurance, may address the demand- and supply-side factors. This study, hence, aims to predict perinatal mortality based on maternal health status and health insurance service using homogeneous ensemble machine learning methods.MethodsThe data was collected from the Ethiopian demographic health survey from 2011 to 2019 G.C. The data were pre-processed to get quality data that are suitable for the homogenous ensemble machine-learning algorithms to develop a model that predicts perinatal mortality. We have applied filter (chi-square and mutual information) and wrapper (sequential forward and sequential backward) feature selection methods. After selecting all the relevant features, we developed a predictive model using cat boost, random forest, and gradient boosting algorithms and evaluated the model using both objective (accuracy, precision, recall, F1_score, ROC) and subjective (domain expert) based evaluation techniques.ResultsPerinatal mortality prediction models were developed using random forest, gradient boosting, and cat boost algorithms with the overall accuracy of 89.95%, 90.24%, and 82%, respectively. Risk factors of perinatal mortality were identified using feature importance analysis and relevant rules were extracted using the best performing model.ConclusionsA prediction model that was developed using gradient boosting algorithms was selected for further use in the risk factor analysis, generating relevant rules, development of artifacts, and model deployment because it has registered better performance with 90.24% accuracy. The most determinant risk factors of perinatal mortality were identified using feature importance and some of them are community-based health insurance, mother's educational level, region and place of residence, age, wealth status, birth interval, preterm, smoking cigarette, anemia level, hemoglobin level, and marital status.

Project description:BackgroundCardiovascular disease is an important driver of the increased mortality associated with chronic kidney disease (CKD). Higher left ventricular mass (LVM) predicts increased risk of adverse cardiovascular outcomes and total mortality, but previous reviews have shown no clear association between intervention-induced LVM change and all-cause or cardiovascular mortality in CKD.MethodsThe primary objective of this meta-analysis was to investigate whether treatment-induced reductions in LVM over periods ≥12 months were associated with all-cause mortality in patients with CKD. Cardiovascular mortality was investigated as a secondary outcome. Measures of association in the form of relative risks (RRs) with associated variability and precision (95% confidence intervals [CIs]) were extracted directly from each study, when reported, or were calculated based on the published data, if possible, and pooled RR estimates were determined.ResultsThe meta-analysis included 42 trials with duration ≥12 months: 6 of erythropoietin stimulating agents treating to higher vs. lower hemoglobin targets, 10 of renin-angiotensin-aldosterone system inhibitors vs. placebo or another blood pressure lowering agent, 14 of modified hemodialysis regimens, and 12 of other types of interventions. All-cause mortality was reported in 121/2584 (4.86%) subjects in intervention groups and 168/2606 (6.45%) subjects in control groups. The pooled RR estimate of the 27 trials ≥12 months with ≥1 event in ≥1 group was 0.72 (95% CI 0.57 to 0.90, p = 0.005), with little heterogeneity across studies. Directionalities of the associations in intervention subgroups were the same. Sensitivity analyses of ≥6 months (34 trials), ≥9 months (29 trials), and >12 months (10 trials), and including studies with no events in either group, demonstrated similar risk reductions to the primary analysis. The point estimate for cardiovascular mortality was similar to all-cause mortality, but not statistically significant: RR 0.67, 95% CI 0.39 to 1.16.ConclusionsThese results suggest that LVM regression may be a useful surrogate marker for benefits of interventions intended to reduce mortality risk in patients with CKD.

Dataset Information

Regression trees for predicting mortality in patients with cardiovascular disease: what improvement is achieved by using ensemble-based methods?

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets