Prediction of Outcome in Acute Lower Gastrointestinal Bleeding Using Gradient Boosting
Open Access
- 14 July 2015
- journal article
- research article
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 10 (7), e0132485
- https://doi.org/10.1371/journal.pone.0132485
Abstract
There are no widely used models in clinical care to predict outcome in acute lower gastro-intestinal bleeding (ALGIB). If available these could help triage patients at presentation to appropriate levels of care/intervention and improve medical resource utilisation. We aimed to apply a state-of-the-art machine learning classifier, gradient boosting (GB), to predict outcome in ALGIB using non-endoscopic measurements as predictors. Non-endoscopic variables from patients with ALGIB attending the emergency departments of two teaching hospitals were analysed retrospectively for training/internal validation (n=170) and external validation (n=130) of the GB model. The performance of the GB algorithm in predicting recurrent bleeding, clinical intervention and severe bleeding was compared to a multiple logic regression (MLR) model and two published MLR-based prediction algorithms (BLEED and Strate prediction rule). The GB algorithm had the best negative predictive values for the chosen outcomes (>88%). On internal validation the accuracy of the GB algorithm for predicting recurrent bleeding, therapeutic intervention and severe bleeding were (88%, 88% and 78% respectively) and superior to the BLEED classification (64%, 68% and 63%), Strate prediction rule (78%, 78%, 67%) and conventional MLR (74%, 74% 62%). On external validation the accuracy was similar to conventional MLR for recurrent bleeding (88% vs. 83%) and therapeutic intervention (91% vs. 87%) but superior for severe bleeding (83% vs. 71%). The gradient boosting algorithm accurately predicts outcome in patients with acute lower gastrointestinal bleeding and outperforms multiple logistic regression based models. These may be useful for risk stratification of patients on presentation to the emergency department.Keywords
This publication has 30 references indexed in Scilit:
- A Gradient Boosting Algorithm for Survival Analysis via Direct Optimization of Concordance IndexComputational and Mathematical Methods in Medicine, 2013
- Regression trees for predicting mortality in patients with cardiovascular disease: What improvement is achieved by using ensemble‐based methods?Biometrical Journal, 2012
- Data mining methods in the prediction of Dementia: A real-data comparison of the accuracy, sensitivity and specificity of linear discriminant analysis, logistic regression, neural networks, support vector machines, classification trees and random forestsBMC Research Notes, 2011
- Impact of upper and lower gastrointestinal blood loss on healthcare utilization and costs: a systematic reviewJournal of Medical Economics, 2011
- Prediction of transfers to tertiary care and hospital mortality: A gradient boosting decision tree approachStatistical Analysis and Data Mining, 2010
- Random forest can predict 30‐day mortality of spontaneous intracerebral hemorrhage with remarkable discriminationEuropean Journal of Neurology, 2010
- Diagnosis and management of lower gastrointestinal bleedingNature Reviews Gastroenterology & Hepatology, 2009
- Risk Factors for Mortality in Lower Intestinal BleedingClinical Gastroenterology and Hepatology, 2008
- SmcHD1, containing a structural-maintenance-of-chromosomes hinge domain, has a critical role in X inactivationNature Genetics, 2008
- Boosting in the presence of noiseJournal of Computer and System Sciences, 2005