WisPerMed at ArchEHR-QA 2025: A Modular, Relevance-First Approach for Grounded Question Answering on Eletronic Health Records

Abstract

Automatically answering patient questions based on electronic health records (EHRs) requires systems that both identify relevant evidence and generate accurate, grounded responses. We present a three-part pipeline developed by WisPerMed for the ArchEHR-QA 2025 shared task. First, a fine-tuned BioClinicalBERT model classifies note sentences by their relevance using synonym-based and paraphrased data augmentation. Second, a constrained generation step uses DistilBART-MedSummary to produce faithful answers strictly limited to top-ranked evidence. Third, we align each answer sentence to its supporting evidence via BiomedBERT embeddings and ROUGE-based similarity scoring to ensure citation transparency. Our system achieved a 35.0{%} overall score on the hidden test set, outperforming the organizer{’}s baseline by 4.3 percentage points. Gains in BERTScore (+44{%}) and SARI (+119{%}) highlight substantial improvements in semantic accuracy and relevance. This modular approach demonstrates that enforcing evidence-awareness and citation grounding enhances both answer quality and trustworthiness in clinical QA systems.

Jan-Henning Büns

Researcher in the second cohort

My research interests include Deep Learning, Computer Vision and Multimodal Techniques

Hendrik Damm

Researcher in the second cohort

My research interests include Deep Learning, Natural Language Processing, and Information Retrieval.

Tabea Pakull

Researcher in the second cohort

My research interests include Deep Learning, Natural Language Processing, Lay Summarization and Explainable AI.

Felix Nensa

Speaker

My research interests include medical digitalization, computer vision and radiology.

Elisabeth Livingstone

Principal Investigator

My research interests include Medical Research, Dermatology, and Digitalization.