Modern machine learning techniques play a very crucial role in dealing with very complex unstructured data that is available in the medical domain. The wide range of applications in this area is capable of changing the available data to valuable information that could be used for recommendation of appropriate treatment and drugs by analysing the symptoms and other information regarding the patient. In this work, the data available in the form of plain text in the form of electronic health records were used to give appropriate recommendations regarding the medication that could be given to the patient. Thus it acts as a clinical decision support system that can assist the doctor in taking suitable decisions regarding the treatment plan of the patient. The model used techniques from Natural Language Processing and Deep Learning to process that raw data and build a learning model for recommendation. The model was able to give an accuracy of 77 percent with raw text as input.
Keywords
Clinical Decision Support System , Electronic Health Record(EHR), Long Short Term Memory(LSTM), Machine Learning , Natural Language Processing, , Recurrent Neural Networks (RNN).
