What's in a Summary? Laying the Groundwork for Advances in Hospital-Course Summarization
This work addresses the problem of summarizing clinical narratives for healthcare professionals, but it is incremental as it focuses on dataset creation and analysis rather than novel methods.
The paper introduces the task of hospital-course summarization, creating a dataset of 109,000 hospitalizations with clinician-authored summaries, and finds that these summaries are highly abstractive, concise, and differ in style from source notes.
Summarization of clinical narratives is a long-standing research problem. Here, we introduce the task of hospital-course summarization. Given the documentation authored throughout a patient's hospitalization, generate a paragraph that tells the story of the patient admission. We construct an English, text-to-text dataset of 109,000 hospitalizations (2M source notes) and their corresponding summary proxy: the clinician-authored "Brief Hospital Course" paragraph written as part of a discharge note. Exploratory analyses reveal that the BHC paragraphs are highly abstractive with some long extracted fragments; are concise yet comprehensive; differ in style and content organization from the source notes; exhibit minimal lexical cohesion; and represent silver-standard references. Our analysis identifies multiple implications for modeling this complex, multi-document summarization task.