We present our system for the PsyDefDetect shared task, which focuses on detecting and classifying psychological defense mechanisms in peer emotional support conversations. Our core contribution is a hierarchical classification framework that structures prediction as a coarse-to-fine pipeline over a clinically validated label hierarchy, grounded in the Defense Mechanism Rating Scales (DMRS). Through systematic experimentation with flat fine-tuning, few-shot prompting, and hierarchical classification, we demonstrate that explicitly modelling the structured relationships among defense levels offers a more effective alternative to flat classification, achieving a macro F1 of 0.23 on the official test set.

dbt mimic omop is a free, open-source resource that converts the MIMIC-IV dataset to the Observational Medical Outcomes Partnership (OMOP) common data model (CDM) format on consumer level hardware. CDM approaches are increasingly adopted in both industry and academia due to the need for interoperability and reproducibility, including in clinical NLP tasks such as cohort selection, information extraction, and retrieval-augmented generation. The MIMIC-IV database is among the most widely used critical care research datasets, yet existing pipelines to transform it to OMOP depend on enterprise database infrastructure and complex orchestration, limiting accessibility for practitioners and resource-constrained researchers. We further integrate free-text clinical notes (195.6M clinical annotations) and chest radiographs into the OMOP note nlp and imaging extension tables, making all MIMIC-IV modalities (structured data, free-text, and imaging) accessible through a common data model. This resource generates a more comprehensive dataset than existing alternatives and is intended to be used to aid in system development, testing, and evaluation.

Retrieval-augmented generation (RAG) holds promise for clinical question answering over electronic health records (EHRs), but existing systems treat retrieval as an opaque subroutine, limiting auditability and reliability in patient care workflows. We introduce a deterministic multi-stage retrieval pipeline for longitudinal EHR question answering that decomposes retrieval into four distinct, ablated stages where each stage is instrumented with diagnostic metrics, making the flow of clinical evidence measurable and auditable at every step. Evaluated on a broad LLM-annotated cohort and an expert-annotated cardiovascular benchmark developed alongside clinicians from real ICU records, the full pipeline achieves 22-23% relative recall gain over a strong dense retrieval baseline across both cohorts, with consistent improvements in downstream answer quality. The pipeline’s deterministic and transparent design addresses a critical gap in clinical NLP: retrieval systems that clinicians and researchers can not only rely on, but inspect, audit, and build upon for real-world deployment.

MedCAT is an open-source framework for clinical named entity recognition and linking (NER+L) widely used in research and healthcare settings. We present MedCAT v2, a re-engineered version designed to improve modularity, extensibility, and maintainability while preserving the core functionality and performance of previous releases. The new architecture introduces a registry-based component system and a flexible pipeline that enables easy substitution of components, integration of alternative methods, and future expansion, including support for pre-trained components across the full NER+L and contextualisation workflow. This enables systematic exploration of clinical NER+L design trade-offs by evaluating different components in the pipeline. Evaluation across multiple public datasets shows equivalent or improved performance compared to earlier versions, with reduced integration overhead and improved runtime flexibility. The framework also supports optional extensions such as meta-annotation, relation extraction, providing a unified and reproducible environment for clinical NLP in real-world settings.

Transformer-based Large Language Models (LLMs) have achieved remarkable success across various domains, including clinical language processing, where they enable state-of-the-art performance in numerous tasks. Like all deep learning models, LLMs are susceptible to inference attacks that exploit sensitive attributes seen during training. AnonCAT, a RoBERTa-based masked language model, has been fine-tuned to de-identify sensitive clinical textual data. The community has a responsibility to explore the privacy risks of these models. This work proposes an attack method to infer sensitive named entities used in the training of AnonCAT models. We perform three experiments; the privacy implications of generating multiple names, the impact of white-box and black-box on attack inference performance, and the privacy-enhancing effects of Differential Privacy (DP) when applied to AnonCAT. By providing real textual predictions and privacy leakage metrics, this research contributes to understanding and mitigating the potential risks associated with exposing LLMs in sensitive domains like healthcare.

We present our system for the ArchEHR shared task, which focuses on answering clinical and patient-facing questions grounded in real-world EHR data. Our core contribution is a 2-Stage prompting pipeline that separates evidence selection from answer generation while employing in-context learning strategies. Our experimentation leveraged the open-weight Gemma-v3 family of models, with our best submission using the Gemma-12B model securing 5th place overall on the unseen test set. Through systematic experimentation, we demonstrate the effectiveness of task decomposition in improving both factual accuracy and answer relevance in grounded clinical question answering.

Electronic Health Records contain vast amounts of valuable clinical data, much of which is stored as unstructured text. Extracting meaningful clinical events (e.g., disorders, symptoms, findings, medications, and procedures etc.) in context within real-world healthcare settings is crucial for enabling downstream applications such as disease prediction, clinical coding for billing and decision support.After Named Entity Recognition and Linking (NER+L) methodology, the identified concepts need to be further classified (i.e. contextualized) for distinct properties such as their relevance to the patient, their temporal and negated status for meaningful clinical use. We present a solution that, using an existing NER+L approach - MedCAT, classifies and contextualizes medical entities at scale. We evaluate the NLP approaches through 14 distinct real-world clinical text classification projects, testing our suite of models tailored to different clinical NLP needs. For tasks requiring high minority class recall, BERT proves the most effective when coupled with class imbalance mitigation techniques, outperforming Bi-LSTM with up to 28%. For majority class focused tasks, Bi-LSTM offers a lightweight alternative with, on average, 32% faster training time and lower computational cost. Importantly, these tools are integrated into an openly available library, enabling users to select the best model for their specific downstream applications.

Text classification tasks which aim at harvesting and/or organizing information from electronic health records are pivotal to support clinical and translational research. However these present specific challenges compared to other classification tasks, notably due to the particular nature of the medical lexicon and language used in clinical records. Recent advances in embedding methods have shown promising results for several clinical tasks, yet there is no exhaustive comparison of such approaches with other commonly used word representations and classification models. In this work, we analyse the impact of various word representations, text pre-processing and classification algorithms on the performance of four different text classification tasks. The results show that traditional approaches, when tailored to the specific language and structure of the text inherent to the classification task, can achieve or exceed the performance of more recent ones based on contextual embeddings such as BERT.

Clinical coding is currently a labour-intensive, error-prone, but a critical administrative process whereby hospital patient episodes are manually assigned codes by qualified staff from large, standardised taxonomic hierarchies of codes. Automating clinical coding has a long history in NLP research and has recently seen novel developments setting new benchmark results. A popular dataset used in this task is MIMIC-III, a large database of clinical free text notes and their associated codes amongst other data. We argue for the reconsideration of the validity MIMIC-III’s assigned codes, as MIMIC-III has not undergone secondary validation. This work presents an open-source, reproducible experimental methodology for assessing the validity of EHR discharge summaries. We exemplify the methodology with MIMIC-III discharge summaries and show the most frequently assigned codes in MIMIC-III are undercoded up to 35%.

An interface for building, improving and customising a given Named Entity Recognition and Linking (NER+L) model for biomedical domain text, and the efficient collation of accurate research use case specific training data and subsequent model training. Screencast demo available here: https://www.youtube.com/watch?v=lM914DQjvSo