Machine Learning
From data mining to knowledge discovery: an overview
Advances in knowledge discovery and data mining
The Random Subspace Method for Constructing Decision Forests
IEEE Transactions on Pattern Analysis and Machine Intelligence
Past, present, and future of decision support technology
Decision Support Systems - Special issue: Decision support systems: Directions for the next decade
A decision-theoretic generalization of on-line learning and an application to boosting
EuroCOLT '95 Proceedings of the Second European Conference on Computational Learning Theory
Combining Pattern Classifiers: Methods and Algorithms
Combining Pattern Classifiers: Methods and Algorithms
Decision station: situating decision support systems
Decision Support Systems
Rule Based Expert Systems: The Mycin Experiments of the Stanford Heuristic Programming Project (The Addison-Wesley series in artificial intelligence)
The use of receiver operating characteristic curves in biomedical informatics
Journal of Biomedical Informatics - Special issue: Clinical machine learning
Adaptive Business Intelligence
Adaptive Business Intelligence
Mortality assessment in intensive care units via adverse events using artificial neural networks
Artificial Intelligence in Medicine
Information architecture for intelligent decision support in intensive medicine
WSEAS Transactions on Computers
Closed loop knowledge discovery for decision support in intensive care medicine
ICCOMP'09 Proceedings of the WSEAES 13th international conference on Computers
Nursing information architecture for situated decision support in intensive care units
AIC'09 Proceedings of the 9th WSEAS international conference on Applied informatics and communications
Adaptive knowledge discovery for decision support in intensive care units
WSEAS Transactions on Computers
Hi-index | 0.00 |
The condition of patients admitted to an Intensive Care Unit is complex to the point that it is often very difficult for physicians to accurately determine the most adequate course of action. However, an ICU is a data rich environment where patients are continuously connected to sensors that allow data collection. Datasets containing such data may hide invaluable information regarding the patients' prognosis. Previous work on intensive care data, produced prediction models that were integrated into a decision support system called INTCare. Although presenting interesting results, INTCare uses static models that are expected to become less accurate over time. As an alternative, this paper presents the results of a set of experiments using an ensemble approach to the prediction of the final outcome of ICU patients, given the data collected during the first 24 hours after ICU admission. Results for both the static and dynamic ensembles (where model weights are updated after each prediction) are presented.