H.3.8. Natural Language Processing
A. Akkasi; E. Varoglu
Abstract
Chemical Named Entity Recognition (NER) is the basic step for consequent information extraction tasks such as named entity resolution, drug-drug interaction discovery, extraction of the names of the molecules and their properties. Improvement in the performance of such systems may affects the quality ...
Read More
Chemical Named Entity Recognition (NER) is the basic step for consequent information extraction tasks such as named entity resolution, drug-drug interaction discovery, extraction of the names of the molecules and their properties. Improvement in the performance of such systems may affects the quality of the subsequent tasks. Chemical text from which data for named entity recognition is extracted is naturally imbalanced since chemical entities are fewer compared to other segments in text. In this paper, the class imbalance problem in the context of chemical named entity recognition has been studied and adopted version of random undersampling for NER data, has been leveraged to generate a pool of classifiers. In order to keep the classes’ distribution balanced within each sentence, the well-known random undersampling method is modified to a sentence based version where the random removal of samples takes place within each sentence instead of considering the dataset as a whole. Furthermore, to take the advantages of combination of a set of diverse predictors, an ensemble of classifiers trained with the set of different training data resulted by sentence-based undersampling, is created. The proposed approach is developed and tested using the ChemDNER corpus released by BioCreative IV. Results show that the proposed method improves the classification performance of the baseline classifiers mainly as a result of an increase in recall. Furthermore, the combination of high performing classifiers trained using undersampled train data surpasses the performance of all single best classifiers and the combination of classifiers using full data.
F.4.17. Survival analysis
S. Miri Rostami; M. Ahmadzadeh
Abstract
Application of data mining methods as a decision support system has a great benefit to predict survival of new patients. It also has a great potential for health researchers to investigate the relationship between risk factors and cancer survival. But due to the imbalanced nature of datasets associated ...
Read More
Application of data mining methods as a decision support system has a great benefit to predict survival of new patients. It also has a great potential for health researchers to investigate the relationship between risk factors and cancer survival. But due to the imbalanced nature of datasets associated with breast cancer survival, the accuracy of survival prognosis models is a challenging issue for researchers. This study aims to develop a predictive model for 5-year survivability of breast cancer patients and discover relationships between certain predictive variables and survival. The dataset was obtained from SEER database. First, the effectiveness of two synthetic oversampling methods Borderline SMOTE and Density based Synthetic Oversampling method (DSO) is investigated to solve the class imbalance problem. Then a combination of particle swarm optimization (PSO) and Correlation-based feature selection (CFS) is used to identify most important predictive variables. Finally, in order to build a predictive model three classifiers decision tree (C4.5), Bayesian Network, and Logistic Regression are applied to the cleaned dataset. Some assessment metrics such as accuracy, sensitivity, specificity, and G-mean are used to evaluate the performance of the proposed hybrid approach. Also, the area under ROC curve (AUC) is used to evaluate performance of feature selection method. Results show that among all combinations, DSO + PSO_CFS + C4.5 presents the best efficiency in criteria of accuracy, sensitivity, G-mean and AUC with values of 94.33%, 0.930, 0.939 and 0.939, respectively.
