Generating Faithful and Complete Hospital-Course Summaries from the Electronic Health Record

TL;DR

This paper develops and evaluates automated methods to generate accurate, comprehensive hospital admission summaries from electronic health records, aiming to reduce clinician workload and improve documentation quality.

Contribution

It introduces a large dataset, explores modeling techniques for faithfulness, and proposes entity-guided summarization to enhance accuracy and coverage in hospital summaries.

Findings

Fine-grained error analysis reveals key challenges in domain adaptation.

Entity-guided summarization improves coverage and reduces hallucinations.

Fine-tuned LLMs are prone to entity hallucinations without planning.

Abstract

The rapid adoption of Electronic Health Records (EHRs) has been instrumental in streamlining administrative tasks, increasing transparency, and enabling continuity of care across providers. An unintended consequence of the increased documentation burden, however, has been reduced face-time with patients and, concomitantly, a dramatic rise in clinician burnout. In this thesis, we pinpoint a particularly time-intensive, yet critical, documentation task: generating a summary of a patient's hospital admissions, and propose and evaluate automated solutions. In Chapter 2, we construct a dataset based on 109,000 hospitalizations (2M source notes) and perform exploratory analyses to motivate future work on modeling and evaluation [NAACL 2021]. In Chapter 3, we address faithfulness from a modeling perspective by revising noisy references [EMNLP 2022] and, to reduce the reliance on references, directly calibrating model outputs to metrics [ACL 2023]. These works relied heavily on automatic metrics as human annotations were limited. To fill this gap, in Chapter 4, we conduct a fine-grained expert annotation of system errors in order to meta-evaluate existing metrics and better understand task-specific issues of domain adaptation and source-summary alignments. To learn a metric less correlated to extractiveness (copy-and-paste), we derive noisy faithfulness labels from an ensemble of existing metrics and train a faithfulness classifier on these pseudo labels [MLHC 2023]. Finally, in Chapter 5, we demonstrate that fine-tuned LLMs (Mistral and Zephyr) are highly prone to entity hallucinations and cover fewer salient entities. We improve both coverage and faithfulness by performing sentence-level entity planning based on a set of pre-computed salient entities from the source text, which extends our work on entity-guided news summarization [ACL, 2023], [EMNLP, 2023].