Browsing by Subject "Medical informatics"

Now showing 1 - 3 of 3

Open Access
Adaptive ensemble learning with confidence bounds
(Institute of Electrical and Electronics Engineers Inc., 2017) Tekin, C.; Yoon, J.; Schaar, M. V. D.
Extracting actionable intelligence from distributed, heterogeneous, correlated, and high-dimensional data sources requires run-time processing and learning both locally and globally. 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, our approach yields performance guarantees with respect to the optimal local prediction strategy, and is also able to adapt its predictions in a data-driven manner. We illustrate the performance of Hedged Bandits in the context of medical informatics and show that it outperforms numerous online and offline ensemble learning methods.
Open Access
Adaptive ensemble learning with confidence bounds for personalized diagnosis
(AAAI Press, 2016) Tekin, Cem; Yoon, J.; Van Der Schaar, M.
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.
Open Access
Two learning approaches for protein name extraction
(Academic Press, 2009) Tatar, S.; Cicekli, I.
Protein name extraction, one of the basic tasks in automatic extraction of information from biological texts, remains challenging. In this paper, we explore the use of two different machine learning techniques and present the results of the conducted experiments. In the first method, Bigram language model is used to extract protein names. In the latter, we use an automatic rule learning method that can identify protein names located in the biological texts. In both cases, we generalize protein names by using hierarchically categorized syntactic token types. We conducted our experiments on two different datasets. Our first method based on Bigram language model achieved an F-score of 67.7% on the YAPEX dataset and 66.8% on the GENIA corpus. The developed rule learning method obtained 61.8% F-score value on the YAPEX dataset and 61.0% on the GENIA corpus. The results of the comparative experiments demonstrate that both techniques are applicable to the task of automatic protein name extraction, a prerequisite for the large-scale processing of biomedical literature. © 2009 Elsevier Inc. All rights reserved.