Medical documents classification using topic modeling

Abstract

The number of digital medical documents is increasing continuously; several medical websites share a lot of unclassified articles. These articles have very long texts that should be read to determine the topic of each document. The classification of these documents is important so researchers can use these documents easily and the effort and time in reading and searching for a specific topic will be reduced. Therefore, an automatic way to extract latent topics from these text documents is needed. Topic modeling is one of the techniques used to deal with this problem. In this paper, a medical collection of documents is used; this collection contains documents from three types of widespread diseases (Heart Diseases, Blood Pressure and Cholesterol). LDA topic modeling technique is applied to classify these documents into the previous mentioned topics. An evaluation of the algorithm’s results is done and the LDA shows a good level of classification accuracy.

Topic prediction modelling on social media content using machine learning

“…Ahn et al [11] implemented topic modelling using LDA to find similar and different topics between certain organisations regarding Ridgecrest earthquake tweets to predict public engagement and encourage more effective communication during natural disasters. Other than that, in this study, LDA got a resulting accuracy rate of 71.4% for documents correctly classified, which involves developing topic modeling for medical documents with constructing a document term matrix to capture word occurrences in each document [12].…”

Automated hierarchical classification of scanned documents using convolutional neural network and regular expression

“…To date, most of the text classification methods generally used to assign multiple topics to documents [6], grouping of documents into a fixed number of predefined classes [7], sentiment analysis to determine the viewpoint/polarity of a writer with respect to some topic [8], spam filtering of emails [9], automatic hate speech detection [10]. In the era of big data, the increasing number of complex documents makes traditional machine learning methods difficult to implement because conventional learning processes are not designed for big data and will not work properly with high data volumes.…”