MaLei at MultiClinSUM: Summarisation of Clinical Documents using Perspective-Aware Iterative Self-Prompting with LLMs

2025/09/09 by Libo Ren, Ren, Libo, Yee Man Ng +3 · 1 citation
Biochemistry, Genetics and Molecular Biology · Computer Science · #Biomedical Text Mining and Ontologies #Computation and Language (cs.CL) #FOS: Computer and information sciences #Machine Learning in Healthcare #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2509.07622

openalex publication_date 2025/09/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Efficient communication between patients and clinicians plays an important role in shared decision-making. However, clinical reports are often lengthy and filled with clinical jargon, making it difficult for domain experts to identify important aspects in the document efficiently. This paper presents the methodology we applied in the MultiClinSUM shared task for summarising clinical case documents. We used an Iterative Self-Prompting technique on large language models (LLMs) by asking LLMs to generate task-specific prompts and refine them via example-based few-shot learning. Furthermore, we used lexical and embedding space metrics, ROUGE and BERT-score, to guide the model fine-tuning with epochs. Our submission using perspective-aware ISP on GPT-4 and GPT-4o achieved ROUGE scores (46.53, 24.68, 30.77) and BERTscores (87.84, 83.25, 85.46) for (P, R, F1) from the official evaluation on 3,396 clinical case reports from various specialties extracted from open journals. The high BERTscore indicates that the model produced semantically equivalent output summaries compared to the references, even though the overlap at the exact lexicon level is lower, as reflected in the lower ROUGE scores. This work sheds some light on how perspective-aware ISP (PA-ISP) can be deployed for clinical report summarisation and support better communication between patients and clinicians.

Citations

• Overview of BioASQ 2025: The Thirteenth BioASQ Challenge on Large-Scale Biomedical Semantic Indexing and Question Answering
• MaLei at the PLABA Track of TREC 2024: RoBERTa for Term Replacement -- LLaMA3.1 and GPT-4o for Complete Abstract Adaptation
• Synthetic4Health: Generating Annotated Synthetic Clinical Letters
• Neural Machine Translation of Clinical Text: An Empirical Investigation into Multilingual Pre-Trained Language Models and Transfer-Learning
• Extraction of Medication and Temporal Relation from Clinical Text using Neural Language Models
• Investigating Large Language Models and Control Mechanisms to Improve Text Readability of Biomedical Abstracts
• Exploring the Value of Pre-trained Language Models for Clinical Named Entity Recognition
• Shared decision making: Concepts, evidence, and practice
• DeIDClinic: A Multi-Layered Framework for De-identification of Clinical Free-text Data

Cited by

• Dutch Metaphor Extraction from Cancer Patients' Interviews and Forum Data using LLMs and Human in the Loop
• ReviewGraph: A Knowledge Graph Embedding Based Framework for Review Rating Prediction with Sentiment Features

Related

• CLINICSUM: Utilizing Language Models for Generating Clinical Summaries from Patient-Doctor Conversations
• Adapted large language models can outperform medical experts in clinical text summarization
• Patient-Centered Summarization Framework for AI Clinical Summarization: A Mixed-Methods Design
• A Comparative Study of Recent Large Language Models on Generating Hospital Discharge Summaries for Lung Cancer Patients
• Towards Adapting Open-Source Large Language Models for Expert-Level Clinical Note Generation