Evaluating the Quality and Safety of Retrieval-Augmented Large Language Models for a Post-Discharge Patient Question Answering System
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Abstract
Evidence on the quality and safety of large language models (LLMs) used to support patient communication remains limited. Recent advances in AI have increased interest in tools that assist patients during transitions of care, such as after hospital discharge. However, many evaluations rely on language similarity metrics or expert judgement without considering patient preferences or safety implications. This thesis develops and evaluates a real-time question–answering (QA) system to support patients following hospital discharge. The QA system used two language models (GPT-4o and QWen) within a retrieval-augmented generation (RAG) framework and could incorporate domain-specific knowledge bases, including MIMIC-IV-Note and a synthetic clinical question–answer dataset. The system was evaluated using 111 patient questions derived from 37 discharge summaries from MIMIC-IV. Three studies examined patient preference, response safety, and language similarity metrics. In study one, patient experts ranked responses from QA system configurations and clinical expert answers based on preference and perceived empathy. AI-generated responses were frequently preferred, particularly when RAG and clinical question datasets were included. In study two, clinical experts assessed the likelihood and severity of safety issues. Unsafe responses were relatively rare and comparable between AI-generated and clinician answers. In study three, language similarity metrics (BLEU, ROUGE, and BERTScore) showed no correlation with patient preference or safety outcomes. These findings suggest that QA systems using discharge information can produce responses acceptable to patients and generally safe under certain configurations. The results highlight limitations of standard language metrics and demonstrate the value of structured safety evaluation. Future systems may benefit from recognising question intent and routing queries to configurations optimised for retrieval, safety, or explanation.
Fields of Study & Subjects
Artificial Intelligence in Healthcare and Education
Machine Learning in Healthcare
Electronic Health Records Systems
Publication details
- Journal / source
- The Sydney eScholarship Repository (The University of Sydney)
- Publication date
- 1 January 2026
- Language
- EN
- Document type
- Thesis