Deep Learning based Transcribing and Summarizing Clinical Conversations

Doctor-Patient interaction plays a very vital role in patient care. The essence of the interaction is lost when a lot of time is consumed in writing or typing the required patient details. These administrative tasks happen at the expense of patient care. With Artificial Intelligence and Natural Language Processing, this research work creates different ways to reduce the time spent on such onerous, trivial administrative tasks at healthcare facilities and concentrate on serving the patients in a better way. This paper proposes an automation mechanism of noise suppression to eliminate environmental disturbance, transcription and sum- summarization of the recorded conversation taking place between the doctor and the patient(s) to focus only on the essential information, since abridging the entire conversation as a whole may be counterproductive. The tabular summary obtained at the end of the process can be used by the doctors and patients alike, to understand the patient history, prognoses and/or diagnoses. A supervised deep learning technique is used for noise suppression by using a convolutional network, the Google Speech- to-Text API for transcription of the conversation and a basic SVM module which categorizes text based on the given tags and relative frequency of occurrence of a word to create the tabular summary of the said doctor-patient verbal exchange.