Extractive Summarization of EHR Discharge Notes

TL;DR

This paper establishes an upper bound for extractive summarization of discharge notes and develops an LSTM model to identify key topics, aiding automated summarization and clinical decision-making.

Contribution

It introduces a new dataset and an LSTM-based approach for topic labeling in discharge notes, advancing extractive summarization techniques.

Findings

Achieved an F1 score of 0.876 for topic labeling.

Provided an upper bound for extractive summarization performance.

Demonstrated the potential for automated summarization in clinical settings.

Abstract

Patient summarization is essential for clinicians to provide coordinated care and practice effective communication. Automated summarization has the potential to save time, standardize notes, aid clinical decision making, and reduce medical errors. Here we provide an upper bound on extractive summarization of discharge notes and develop an LSTM model to sequentially label topics of history of present illness notes. We achieve an F1 score of 0.876, which indicates that this model can be employed to create a dataset for evaluation of extractive summarization methods.