Unstructured Medical Text Classification using Machine Learning and Deep Learning Approaches

On the internet, there is a large volume of unstructured data content that includes useful information. People are having trouble in digesting, reading, and remembering the text content, as it is always changing and developing. Data mining and information extraction techniques are being used to build new automated strategies for processing unstructured text. Natural Language Processing (NLP) is a discipline of linguistics that deals with extracting most significant information from the unstructured data. NLP aids in the resolution of challenges related to text data vulnerability. Text data that is unstructured in nature is commonly available in the public domain. Among these, we have chosen medical text data, which comprises of both text and voice descriptions of the patients. Disease diagnosis, medical research, and automatic construction of disease ontology, as well as obtaining knowledge of clinical data documented in the medical literature, are all impacted by medical text classification. In this paper, we have employed a variety of machine and deep learning models to extract the summary from the text data and identified the diseases. The paper gives the comparison of the accuracy obtained w.r.t different models.