Adaptive ensemble learning with confidence bounds for personalized diagnosis

Date
2016
Advisor
Supervisor
Co-Advisor
Co-Supervisor
Instructor
Source Title
Proceedings of the 30th AAAI Conference on Artificial Intelligence, 2016
Print ISSN
Electronic ISSN
Publisher
AAAI Press
Volume
WS-16-08
Issue
Pages
462 - 468
Language
English
Type
Conference Paper
Journal Title
Journal ISSN
Volume Title
Series
Abstract

With the advances in the field of medical informatics, automated clinical decision support systems are becoming the de facto standard in personalized diagnosis. In order to establish high accuracy and confidence in personalized diagnosis, massive amounts of distributed, heterogeneous, correlated and high-dimensional patient data from different sources such as wearable sensors, mobile applications, Electronic Health Record (EHR) databases etc. need to be processed. This requires learning both locally and globally due to privacy constraints and/or distributed nature of the multimodal medical data. In the last decade, a large number of meta-learning techniques have been proposed in which local learners make online predictions based on their locally-collected data instances, and feed these predictions to an ensemble learner, which fuses them and issues a global prediction. However, most of these works do not provide performance guarantees or, when they do, these guarantees are asymptotic. None of these existing works provide confidence estimates about the issued predictions or rate of learning guarantees for the ensemble learner. In this paper, we provide a systematic ensemble learning method called Hedged Bandits, which comes with both long run (asymptotic) and short run (rate of learning) performance guarantees. Moreover, we show that our proposed method outperforms all existing ensemble learning techniques, even in the presence of concept drift.

Course
Other identifiers
Book Title
Keywords
Artificial intelligence, Big data, Cognitive systems, Computer games, Computer programming, Computer systems programming, Data mining, Decision support systems, Machine learning, Ensemble learning, Online learning, Hospital data processing, Hybrid systems, Learning algorithms, Learning systems, Population statistics, Clinical decision support systems, Electronic health record, Global predictions, Medical informatics, Meta-learning techniques, Mobile applications, Performance guarantees, Privacy constraints, Confidence bounds
Citation
Published Version (Please cite this version)