CREGEX: A Biomedical Text Classifier Based on Automatically Generated Regular Expressions

Abstract

High accuracy text classifiers are used nowadays in organizing large amounts of biomedical information and supporting clinical decision-making processes. In medical informatics, regular expressionbased classifiers have emerged as an alternative to traditional, discriminative classification algorithms due to their ability to model sequential patterns. This article presents CREGEX (Classifier Regular Expression), a biomedical text classifier based on an automatically generated regular-expressions-based feature space. We conceived an algorithm for automatically constructing an informative and discriminative regularexpressions-based feature space, suitable for binary and multiclass discrimination problems. Regular expressions are automatically generated from training texts using a coarse-to-fine text aligning method, which trades off the lexical variants of words, in terms of gender and grammatical number, and the generation of a feature space containing a large number of noisy features. CREGEX carries out feature selection by filtering keywords and also computes a confidence metric to classify test texts. Three de-identified datasets in Spanish, with information on smoking habits, obesity, and obesity types, were used here to assess the performance of CREGEX. For comparison, Support Vector Machine (SVM) and Naïve Bayes (NB) supervised classifiers were also trained with consecutive sequences of tokens (n-grams) as features. Results show that, in all the datasets used for evaluation, CREGEX not only outperformed both the SVM and NB classifiers in terms of accuracy and F-measure (p-value<0.05) but also used a fewer amount of training examples to achieve the same performance. Such a superior performance is attributed to the regular expressions' ability to represent complex text patterns.

A regular expression generator based on CSS selectors for efficient extractionfrom HTML pages

“…Traditional regular expression generators [10][11][12][13][14][15][16][17] focus on trying all variations to obtain the most suitable pattern and ignore time efficiency. Moreover, these generators are suitable for different tasks.…”

“…Locascio et al [14] use an LSTM-based sequence to sequence a neural network for specialized domain knowledge. Flores et al [15] develop an algorithm for automatically generating regular expressions from biomedical texts using a coarse-to-fine text aligning method. Cui et al [16] design an efficient novel regular expression based text classifier.…”

Improving k Nearest Neighbors and Naïve Bayes Classifiers Through Space Transformations and Model Selection

“…In our contribution, we boost the performance of the Naïve Bayes (NB) classifier because, despite its strong assumptions of independence among attributes, the NB classifier is a popular algorithm among practitioners. It is particularly effective in text classification tasks [5], [19], [35], [55] and popular among researchers of some specific domains. For instance, recently, Niazi et al [48] use NB to monitor and maintain photovoltaic modules; Shen et al [60] use it to handle dependencies in medical ontologies.…”

Active Learning for Biomedical Text Classification Based on Automatically Generated Regular Expressions

“…Recently, the AL has attracted the interest of researchers and has been applied to classification algorithms based on DNN [15], [16]. However, to our best knowledge, there are no AL query strategies available for identifying the most informative examples for regular-expressions-based biomedical text classifiers, with only some works related to information extraction tasks but in other usage domains [17]- [21]. Based on the above, in this paper we aim to address the following research questions:…”

“…The conservative AL query strategy assesses the amount of diversity in the examples through the Smith-Waterman (SW) algorithm to provide a level of uncertainty in cases where regular expressions mismatch. Three datasets written in Spanish were used to evaluate whether the AL decision function effectively achieves the same classification performance when used in conjunction with the Classifier Regular Expression (CREGEX) biomedical text discriminant [21]. Such datasets were obtained from the hospital Guillermo Grant Benavente (HGGB) in Concepción, Chile.…”