LCDS: A Logic-Controlled Discharge Summary Generation System Supporting Source Attribution and Expert Review
Preprint
Abstract
Despite the remarkable performance of Large Language Models (LLMs) in automated discharge summary generation, they still suffer from hallucination issues, such as generating inaccurate content or fabricating information without valid sources. In addition, electronic medical records (EMRs) typically consist of long-form data, making it challenging for LLMs to attribute the generated content to the sources. To address these challenges, we propose LCDS, a Logic-Controlled Discharge Summary generation system. LCDS constructs a source mapping table by calculating textual similarity between EMRs and discharge summaries to constrain the scope of summarized content. Moreover, LCDS incorporates a comprehensive set of logical rules, enabling it to generate more reliable silver discharge summaries tailored to different clinical fields. Furthermore, LCDS supports source attribution for generated content, allowing experts to efficiently review, provide feedback, and rectify errors. The resulting golden discharge summaries are subsequently recorded for incremental fine-tuning of LLMs. Our project and demo video are in the GitHub repository https://github.com/ycycyc02/LCDS.Keywords
All Related Versions
This publication has 19 references indexed in Scilit:
- A survey on LLM-as-a-judgeThe Innovation, 2026
- Adapted large language models can outperform medical experts in clinical text summarizationNature Medicine, 2024
- Attribute First, then Generate: Locally-attributable Grounded Text Generation2024
- A method to automate the discharge summary hospital course for neurology patientsJournal of the American Medical Informatics Association, 2023
- Survey of Hallucination in Natural Language GenerationACM Computing Surveys, 2023
- On Faithfulness and Factuality in Abstractive Summarization2020
- Timeliness in discharge summary dissemination is associated with patients' clinical outcomesJournal of Evaluation in Clinical Practice, 2011
- The Probabilistic Relevance Framework: BM25 and BeyondFoundations and Trends® in Information Retrieval, 2009
- Promoting effective transitions of care at hospital discharge: A review of key issues for hospitalistsJournal of Hospital Medicine, 2007
- Effect of discharge summary availability during post-discharge visits on hospital readmissionJournal of General Internal Medicine, 2002