Exploring Optimal Granularity for Extractive Summarization of Unstructured Health Records: Analysis of the Largest Multi-Institutional Archive of Health Records in Japan

  title={Exploring Optimal Granularity for Extractive Summarization of Unstructured Health Records: Analysis of the Largest Multi-Institutional Archive of Health Records in Japan},
  author={Kenichiro Ando and Takashi Okumura and Mamoru Komachi and Hiromasa Horiguchi and Yuji Matsumoto},
Automated summarization of clinical texts can reduce the burden of medical professionals. “Discharge summaries” are one promising application of the summarization, because they can be generated from daily inpatient records. Our preliminary experiment suggests that 20–31% of the descriptions in discharge summaries overlap with the content of the inpatient records. However, it remains unclear how the summaries should be generated from the unstructured source. To decompose the physician’s… 
1 Citations

Figures and Tables from this paper

Is artificial intelligence capable of generating hospital discharge summaries from inpatient records?

The analysis of discharge summaries revealed that end-to-end summarization using machine learning is considered infeasible, and machine summarization with an assisted post-editing process is the best fit for this problem domain.



A Novel System for Extractive Clinical Note Summarization using EHR Data

This paper presents their clinical note processing pipeline, which extends beyond basic medical natural language processing (NLP) with concept recognition and relation detection to also include components specific to EHR data, such as structured data associated with the encounter, sentence-level clinical aspects, and structures of the clinical notes.

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

This work constructs an English, text-to-text dataset of 109,000 hospitalizations and their corresponding summary proxy: the clinician-authored “Brief Hospital Course” paragraph written as part of a discharge note, and identifies multiple implications for modeling this complex, multi-document summarization task.

Extractive Summarization of EHR Discharge Notes

An upper bound on extractive summarization of discharge notes is provided and an LSTM model to sequentially label topics of history of present illness notes is developed.

Ontology-Aware Clinical Abstractive Summarization

A sequence-to-sequence abstractive summarization model augmented with domain-specific ontological information to enhance content selection and summary generation is proposed and significantly outperforms the current state-of-the-art on this task in terms of rouge scores.

Towards Clinical Encounter Summarization: Learning to Compose Discharge Summaries from Prior Notes

Two new measures, faithfulness and hallucination rate, are introduced for evaluation in this task, which complement existing measures for fluency and informativeness.

Unsupervised Pseudo-Labeling for Extractive Summarization on Electronic Health Records

This work studied how to utilize the intrinsic correlation between multiple EHRs to generate pseudo-labels and train a supervised model with no external annotation that is effective in summarizing crucial disease-specific information for patients.