Biomedical Text Mining for Diagnosing Diseases - A Review

Diagnosis of diseases is a difficult work that has to do in accurate manner. Text mining deals a great job in this field. A huge mass of data is available in biomedical field, using this data we can diagnosis many diseases by text mining techniques in efficient manner. Text mining methods are used to retrieve useful knowledge from large data. Objective: The aim of this paper is to review several text mining methods used in biomedical field. This survey is helpful to select a best text mining method for biomedical data. Methods/Analysis: In this paper, classification method is used to study the biomedical text mining for diagnosing diseases. In the field of biomedical, classification can be done on the basis of patient disease pattern to separate the patients into high risk or low risk The classification techniques have two methods they are Binary contains two classes and multilevel contains more than two classes. Classification method is widely used in biomedical text mining. In this paper different classification techniques can be applied to categorize the text they are SVM (Support Vector Machine) NN (Neural Network), K-NN (K-Nearest Neighbor), Bayesian Method and DT (Decision Tree). Findings: In this paper, different classification techniques were surveyed and their merits and limitations have been discussed. The various classification techniques were applied in medical data where useful patterns and knowledge were extracted. The important task is that to select the suitable data and classification method for disease diagnosis. The objective of this survey is that how the classification methods are applied in biomedical application and to select which method is suitable and efficient for diagnosis of a particular disease. Novelty/Improvement: The main advantage of the survey is that it can be applied to any kind of dataset, it is a description dataset or not. For future improvement, we will implement our proposed methodology on using some major chest diseases datasets and measured performance in terms of training time and accurate diagnosis.