Medical Concept Normalization for Online User-Generated Texts

Social media has become an important tool for sharing content in the last decade. People often talk about their experiences and opinions on different health-related issues e.g. they write reviews on medications, describe symptoms and ask informal questions about various health concerns. Due to the colloquial nature of the languages used in the social media, it is often difficult for an automated system to accurately interpret them for appropriate clinical understanding. To address this challenge, this paper proposes a novel approach for medical concept normalization of user-generated texts to map a health condition described in the colloquial language to a medical concept defined in standard clinical terminologies. We use multiple deep learning architectures such as convolutional neural networks (CNN) and recurrent neural networks (RNN) with input word embeddings trained on various clinical domain-specific knowledge sources. Extensive experiments on two benchmark datasets demonstrate that the proposed models can achieve up to 21.28% accuracy improvements over the existing models when we use the combination of all knowledge sources to learn neural embeddings.