What’s in a Summary? Laying the Groundwork for Advances in Hospital-Course Summarization

Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 4794–4811 June 6–11, 2021. ©2021 Association for Computational Linguistics 4794 What’s in a Summary? Laying the Groundwork for Advances in Hospital-Course Summarization Griffin Adams1, Emily Alsentzer2, Mert Ketenci1, Jason Zucker1, Noémie Elhadad1 1Columbia University, New York, NY 2Harvard-MIT’s Health Science and Technology, Cambridge, MA {griffin.adams, mert.ketenci, noemie.elhadad}@columbia.edu emilya@mit.edu, jz2700@cumc.columbia.edu Abstract Summarization of clinical narratives is a long- standing research problem. Here, we in- troduce the task of hospital-course summa- rization. Given the documentation authored throughout a patient’s hospitalization, gener- ate a paragraph that tells the story of the pa- tient admission. We construct an English, text- to-text dataset of 109,000 hospitalizations (2M source notes) and their corresponding sum- mary proxy: the clinician-authored “Brief Hos- pital Course” paragraph written as part of a discharge note. Exploratory analyses reveal that the BHC paragraphs are highly abstrac- tive with some long extracted fragments; are concise yet comprehensive; differ in style and content organization from the source notes; ex- hibit minimal lexical cohesion; and represent silver-standard references. Our analysis iden- tifies multiple implications for modeling this complex, multi-document summarization task. 1 Introduction The electronic health record (EHR) contains criti- cal information for clinicians to assess a patient’s medical history (e.g., conditions, laboratory tests, procedures, treatments) and healthcare interactions (e.g., primary care and specialist visits, emergency department visits, and hospitalizations). While medications, labs, and diagnoses are documented through structured data elements and flowsheets, clinical notes contain rich narratives describing the patient’s medical condition and interventions. A single hospital visit for a patient with a lengthy hospital stay, or complex illness, can consist of hundreds of notes. At the point of care, clinicians already pressed for time, face a steep challenge of making sense of their patient’s documentation and synthesizing it either for their own decision making process or to ensure coordination of care (Hall and Walton, 2004; Ash et al., 2004). Automatic summarization has been proposed to support clinicians in multiple scenarios, from making sense of a patient’s longitudinal record over long periods of time and multiple interac- tions with the healthcare system, to synthesizing a specific visit’s documentation. Here, we focus on hospital-course summarization: faithfully and concisely summarizing the EHR documentation for a patient’s specific inpatient visit, from admission to discharge. Crucial for continuity of care and pa- tient safety after discharge (Kripalani et al., 2007; Van Walraven et al., 2002), hospital-course summa- rization also represents an incredibly challenging multi-document summarization task with diverse knowledge requirements. To properly synthesize an admission, one must not only identify relevant problems, but link them to symptoms, procedures, medications, and observations while adhering to temporal, problem-specific constraints. Our main contributions are as follows: (1) We in- troduce the task of hospital-course summarization; (2) we collect a dataset of inpatient documenta- tion and corresponding "Brief Hospital Course" paragraphs extracted from discharge notes; and (3) we assess the characteristics of these summary paragraphs as a proxy for target summaries and …

Content truncated to 500 words