Attention-based Clinical Note Summarization

The trend of deploying digital systems in numerous industries has induced a hike in recording digital information. The health sector has observed an extensive adoption of digital devices and systems that generate large volumes of personal medical records. Electronic health records contain valuable information for retrospective and prospective analysis that is often not entirely exploited because of the dense information storage. The crude purpose of condensing health records is to select the information that holds most characteristics of the original documents based on reported disease. These summaries may boost diagnosis and extend a doctor's time with the patient during a high workload situation like the COVID-19 pandemic. In this paper, we propose applying a multi-head attention-based mechanism to perform extractive summarization of meaningful phrases in clinical notes. This method finds major sentences for a summary by correlating tokens, segments, and positional embeddings. The model outputs attention scores that are statistically transformed to extract key phrases and can be used to projection on the heat-mapping tool for visual and human use.