Automated Medical Assistance: Attention Based Consultation System

Raj Ratn Pranesh, Ambesh Shekhar, Sumit Kumar

Abstract:

With so many possibilities of disease and disorders, there had been a surge in demand for medical assistance. Although there are a number of well-practised physicians and doctors, the inability to reach has always been a concern to many diseased ones. To fill this gap, we propose a model based on deep learning methods, a conversational dialogue system that is able to provide better medication during the need of such and is able to answer any queries related to one’s health. We utilized the human-generated medical assistance dataset collected from online platform containing professional assistance via a conversation system. We designed three transformers based encoder-decoder model, namely, BERT, GPT2, and BART and trained them on large the dialogue dataset for text generation. We performed a comparative study of the models and in our analysis, we found that the BART
model generates a doctor-like response and contains clinically informative data. The overall generated results were very promising and show that through transfer learning pre-trained transformers are reliable for developing automated medical assistance system and doctor-like-treatments.