A passage extractor for classification of disease aspect information

Abstract

Retrieval of disease information is often based on several key aspects such as etiology, diagnosis, treatment, prevention, and symptoms of diseases. Automatic identification of disease aspect information is thus essential. In this article, I model the aspect identification problem as a text classification (TC) problem in which a disease aspect corresponds to a category. The disease aspect classification problem poses two challenges to classifiers: (a) a medical text often contains information about multiple aspects of a disease and hence produces noise for the classifiers and (b) text classifiers often cannot extract the textual parts (i.e., passages) about the categories of interest. I thus develop a technique, PETC (Passage Extractor for Text Classification), that extracts passages (from medical texts) for the underlying text classifiers to classify. Case studies on thousands of Chinese and English medical texts show that PETC enhances a support vector machine (SVM) classifier in classifying disease aspect information. PETC also performs better than three state‐of‐the‐art classifier enhancement techniques, including two passage extraction techniques for text classifiers and a technique that employs term proximity information to enhance text classifiers. The contribution is of significance to evidence‐based medicine, health education, and healthcare decision support. PETC can be used in those application domains in which a text to be classified may have several parts about different categories.

Characterizing the dissemination of misinformation on social media in health emergencies: An empirical study based on COVID-19

“…During health emergencies, a large amount of misinformation emerged on social media. Although previous studies have attempted to classify health-related information into various categories, such as health education ( Liu, 2013 ) and prevention and treatment information ( Liu et al., 2020b ), few studies have paid attention to classifying the types of misinformation in health emergencies. Accordingly, this study measures misinformation support from a more precise approach.…”

Identification of highly related references about gene-disease association

“…Therefore, more intelligent identification of the concluding paragraph of a reference is an interesting research problem. Previous techniques that extracted and classified passages (e.g., [ 37 ]) may be applicable to the problem. Integration of CRFref and the previous techniques should be helpful in improving CRFref.…”

A two-phase sentiment analysis approach for judgement prediction

“…As illustrated in Figure 2, the proposed method contains two stages: relevant article retrieval through multilabel classification and judgement category forecast based on sentiment analysis using the classifier. SVM was chosen as the classification algorithm because of its strong performance in many previous text classification studies [50–52].…”