Injury narrative text classification : a preliminary study

Description of a patient's injuries is recorded in narrative text form by hospital emergency departments. For statistical reporting, this text data needs to be mapped to pre-defined codes. Existing research in this field uses the Naïve Bayes probabilistic method to build classifiers for mapping. In this paper, we focus on providing guidance on the selection of a classification method. We build a number of classifiers belonging to different classification families such as decision tree, probabilistic, neural networks, and instance-based, ensemble-based and kernel-based linear classifiers. An extensive pre-processing is carried out to ensure the quality of data and, in hence, the quality classification outcome. The records with a null entry in injury description are removed. The misspelling correction process is carried out by finding and replacing the misspelt word with a soundlike word. Meaningful phrases have been identified and kept, instead of removing the part of phrase as a stop word. The abbreviations appearing in many forms of entry are manually identified and only one form of abbreviations is used. Clustering is utilised to discriminate between non-frequent and frequent terms. This process reduced the number of text features dramatically from about 28,000 to 5000. The medical narrative text injury dataset, under consideration, is composed of many short documents. The data can be characterized as high-dimensional and sparse, i.e., few features are irrelevant but features are correlated with one another. Therefore, Matrix factorization techniques such as Singular Value Decomposition (SVD) and Non Negative Matrix Factorization (NNMF) have been used to map the processed feature space to a lower-dimensional feature space. Classifiers with these reduced feature space have been built. In experiments, a set of tests are conducted to reflect which classification method is best for the medical text classification. The Non Negative Matrix Factorization with Support Vector Machine method can achieve 93% precision which is higher than all the tested traditional classifiers. We also found that TF/IDF weighting which works well for long text classification is inferior to binary weighting in short document classification. Another finding is that the Top-n terms should be removed in consultation with medical experts, as it affects the classification performance.

Injury narrative text classification using factorization model

Narrative text is a useful way of identifying injury circumstances from the routine emergency department data collections. Automatically classifying narratives based on machine learning techniques is a promising technique, which can consequently reduce the tedious manual classification process. Existing works focus on using Naive Bayes which does not always offer the best performance. This paper proposes the Matrix Factorization approaches along with a learning enhancement process for this task. The results are compared with the performance of various other classification approaches. The impact on the classification results from the parameters setting during the classification of a medical text dataset is discussed. With the selection of right dimension k, Non Negative Matrix Factorization-model method achieves 10 CV accuracy of 0.93.

The use of narrative text for injury surveillance research : a systematic review

Objective: To summarise the extent to which narrative text fields in administrative health data are used to gather information about the event resulting in presentation to a health care provider for treatment of an injury, and to highlight best practise approaches to conducting narrative text interrogation for injury surveillance purposes.----- Design: Systematic review----- Data sources: Electronic databases searched included CINAHL, Google Scholar, Medline, Proquest, PubMed and PubMed Central.. Snowballing strategies were employed by searching the bibliographies of retrieved references to identify relevant associated articles.----- Selection criteria: Papers were selected if the study used a health-related database and if the study objectives were to a) use text field to identify injury cases or use text fields to extract additional information on injury circumstances not available from coded data or b) use text fields to assess accuracy of coded data fields for injury-related cases or c) describe methods/approaches for extracting injury information from text fields.----- Methods: The papers identified through the search were independently screened by two authors for inclusion, resulting in 41 papers selected for review. Due to heterogeneity between studies metaanalysis was not performed.----- Results: The majority of papers reviewed focused on describing injury epidemiology trends using coded data and text fields to supplement coded data (28 papers), with these studies demonstrating the value of text data for providing more specific information beyond what had been coded to enable case selection or provide circumstantial information. Caveats were expressed in terms of the consistency and completeness of recording of text information resulting in underestimates when using these data. Four coding validation papers were reviewed with these studies showing the utility of text data for validating and checking the accuracy of coded data. Seven studies (9 papers) described methods for interrogating injury text fields for systematic extraction of information, with a combination of manual and semi-automated methods used to refine and develop algorithms for extraction and classification of coded data from text. Quality assurance approaches to assessing the robustness of the methods for extracting text data was only discussed in 8 of the epidemiology papers, and 1 of the coding validation papers. All of the text interrogation methodology papers described systematic approaches to ensuring the quality of the approach.----- Conclusions: Manual review and coding approaches, text search methods, and statistical tools have been utilised to extract data from narrative text and translate it into useable, detailed injury event information. These techniques can and have been applied to administrative datasets to identify specific injury types and add value to previously coded injury datasets. Only a few studies thoroughly described the methods which were used for text mining and less than half of the studies which were reviewed used/described quality assurance methods for ensuring the robustness of the approach. New techniques utilising semi-automated computerised approaches and Bayesian/clustering statistical methods offer the potential to further develop and standardise the analysis of narrative text for injury surveillance.

Mining a data reasoning model for personalized text classification

It is a big challenge to acquire correct user profiles for personalized text classification since users may be unsure in providing their interests. Traditional approaches to user profiling adopt machine learning (ML) to automatically discover classification knowledge from explicit user feedback in describing personal interests. However, the accuracy of ML-based methods cannot be significantly improved in many cases due to the term independence assumption and uncertainties associated with them. This paper presents a novel relevance feedback approach for personalized text classification. It basically applies data mining to discover knowledge from relevant and non-relevant text and constraints specific knowledge by reasoning rules to eliminate some conflicting information. We also developed a Dempster-Shafer (DS) approach as the means to utilise the specific knowledge to build high-quality data models for classification. The experimental results conducted on Reuters Corpus Volume 1 and TREC topics support that the proposed technique achieves encouraging performance in comparing with the state-of-the-art relevance feedback models.

Unsupervised multi-label text classification using a world knowledge ontology

The development of text classification techniques has been largely promoted in the past decade due to the increasing availability and widespread use of digital documents. Usually, the performance of text classification relies on the quality of categories and the accuracy of classifiers learned from samples. When training samples are unavailable or categories are unqualified, text classification performance would be degraded. In this paper, we propose an unsupervised multi-label text classification method to classify documents using a large set of categories stored in a world ontology. The approach has been promisingly evaluated by compared with typical text classification methods, using a real-world document collection and based on the ground truth encoded by human experts.

Rough set based approach to text classification

Textual document set has become an important and rapidly growing information source in the web. Text classification is one of the crucial technologies for information organisation and management. Text classification has become more and more important and attracted wide attention of researchers from different research fields. In this paper, many feature selection methods, the implement algorithms and applications of text classification are introduced firstly. However, because there are much noise in the knowledge extracted by current data-mining techniques for text classification, it leads to much uncertainty in the process of text classification which is produced from both the knowledge extraction and knowledge usage, therefore, more innovative techniques and methods are needed to improve the performance of text classification. It has been a critical step with great challenge to further improve the process of knowledge extraction and effectively utilization of the extracted knowledge. Rough Set decision making approach is proposed to use Rough Set decision techniques to more precisely classify the textual documents which are difficult to separate by the classic text classification methods. The purpose of this paper is to give an overview of existing text classification technologies, to demonstrate the Rough Set concepts and the decision making approach based on Rough Set theory for building more reliable and effective text classification framework with higher precision, to set up an innovative evaluation metric named CEI which is very effective for the performance assessment of the similar research, and to propose a promising research direction for addressing the challenging problems in text classification, text mining and other relative fields.

Decision boundary setting and classifier combination for text classification

This thesis presents a promising boundary setting method for solving challenging issues in text classification to produce an effective text classifier. A classifier must identify boundary between classes optimally. However, after the features are selected, the boundary is still unclear with regard to mixed positive and negative documents. A classifier combination method to boost effectiveness of the classification model is also presented. The experiments carried out in the study demonstrate that the proposed classifier is promising.

Centroid training to achieve effective text classification

Traditional text classification technology based on machine learning and data mining techniques has made a big progress. However, it is still a big problem on how to draw an exact decision boundary between relevant and irrelevant objects in binary classification due to much uncertainty produced in the process of the traditional algorithms. The proposed model CTTC (Centroid Training for Text Classification) aims to build an uncertainty boundary to absorb as many indeterminate objects as possible so as to elevate the certainty of the relevant and irrelevant groups through the centroid clustering and training process. The clustering starts from the two training subsets labelled as relevant or irrelevant respectively to create two principal centroid vectors by which all the training samples are further separated into three groups: POS, NEG and BND, with all the indeterminate objects absorbed into the uncertain decision boundary BND. Two pairs of centroid vectors are proposed to be trained and optimized through the subsequent iterative multi-learning process, all of which are proposed to collaboratively help predict the polarities of the incoming objects thereafter. For the assessment of the proposed model, F1 and Accuracy have been chosen as the key evaluation measures. We stress the F1 measure because it can display the overall performance improvement of the final classifier better than Accuracy. A large number of experiments have been completed using the proposed model on the Reuters Corpus Volume 1 (RCV1) which is important standard dataset in the field. The experiment results show that the proposed model has significantly improved the binary text classification performance in both F1 and Accuracy compared with three other influential baseline models.

A regularized linear classifier for effective text classification

In document community support vector machines and naïve bayes classifier are known for their simplistic yet excellent performance. Normally the feature subsets used by these two approaches complement each other, however a little has been done to combine them. The essence of this paper is a linear classifier, very similar to these two. We propose a novel way of combining these two approaches, which synthesizes best of them into a hybrid model. We evaluate the proposed approach using 20ng dataset, and compare it with its counterparts. The efficacy of our results strongly corroborate the effectiveness of our approach.

Extension of TSVM to multi-class and hierarchical text classification problems With general losses

Transductive SVM (TSVM) is a well known semi-supervised large margin learning method for binary text classification. In this paper we extend this method to multi-class and hierarchical classification problems. We point out that the determination of labels of unlabeled examples with fixed classifier weights is a linear programming problem. We devise an efficient technique for solving it. The method is applicable to general loss functions. We demonstrate the value of the new method using large margin loss on a number of multi-class and hierarchical classification datasets. For maxent loss we show empirically that our method is better than expectation regularization/constraint and posterior regularization methods, and competitive with the version of entropy regularization method which uses label constraints.

Improving Multi-class Text Classification with Naive Bayes

There are numerous text documents available in electronic form. More and more are becoming available every day. Such documents represent a massive amount of information that is easily accessible. Seeking value in this huge collection requires organization; much of the work of organizing documents can be automated through text classification. The accuracy and our understanding of such systems greatly influences their usefulness. In this paper, we seek 1) to advance the understanding of commonly used text classification techniques, and 2) through that understanding, improve the tools that are available for text classification. We begin by clarifying the assumptions made in the derivation of Naive Bayes, noting basic properties and proposing ways for its extension and improvement. Next, we investigate the quality of Naive Bayes parameter estimates and their impact on classification. Our analysis leads to a theorem which gives an explanation for the improvements that can be found in multiclass classification with Naive Bayes using Error-Correcting Output Codes. We use experimental evidence on two commonly-used data sets to exhibit an application of the theorem. Finally, we show fundamental flaws in a commonly-used feature selection algorithm and develop a statistics-based framework for text feature selection. Greater understanding of Naive Bayes and the properties of text allows us to make better use of it in text classification.

Improving Multiclass Text Classification with the Support Vector Machine

We compare Naive Bayes and Support Vector Machines on the task of multiclass text classification. Using a variety of approaches to combine the underlying binary classifiers, we find that SVMs substantially outperform Naive Bayes. We present full multiclass results on two well-known text data sets, including the lowest error to date on both data sets. We develop a new indicator of binary performance to show that the SVM's lower multiclass error is a result of its improved binary performance. Furthermore, we demonstrate and explore the surprising result that one-vs-all classification performs favorably compared to other approaches even though it has no error-correcting properties.

Identifying problematic classes in text classification

Real-world text classification tasks often suffer from poor class structure with many overlapping classes and blurred boundaries. Training data pooled from multiple sources tend to be inconsistent and contain erroneous labelling, leading to poor performance of standard text classifiers. The classification of health service products to specialized procurement classes is used to examine and quantify the extent of these problems. A novel method is presented to analyze the labelled data by selectively merging classes where there is not enough information for the classifier to distinguish them. Initial results show the method can identify the most problematic classes, which can be used either as a focus to improve the training data or to merge classes to increase confidence in the predicted results of the classifier.