arXiv subjects

Paul M. Middleton

Publications and source records attributed to Paul M. Middleton.

3 recordsLinked to original sources

arXiv2026

Beyond the Basics: Leveraging Large Language Model for Fine-Grained Medical Entity Recognition

Extracting clinically relevant information from unstructured medical narratives such as admission notes, discharge summaries, and emergency case histories remains a challenge in clinical natural language processing (NLP). Medical Entity Recognition (MER) identifies meaningful concepts embedded in these records. Recent advancements in large language models (LLMs) have shown competitive MER performance; however, evaluations often focus on general entity types, offering limited utility for real-world clinical needs requiring finer-grained extraction. To address this gap, we rigorously evaluated the open-source LLaMA3 model for fine-grained medical entity recognition across 18 clinically detailed categories. To optimize performance, we employed three learning paradigms: zero-shot, few-shot, and fine-tuning with Low-Rank Adaptation (LoRA). To further enhance few-shot learning, we introduced two example selection methods based on token- and sentence-level embedding similarity, utilizing a pre-trained BioBERT model. Unlike prior work assessing zero-shot and few-shot performance on proprietary models (e.g., GPT-4) or fine-tuning different architectures, we ensured methodological consistency by applying all strategies to a unified LLaMA3 backbone, enabling fair comparison across learning settings. Our results showed that fine-tuned LLaMA3 surpasses zero-shot and few-shot approaches by 63.11% and 35.63%, respectivel respectively, achieving an F1 score of 81.24% in granular medical entity extraction.

cs.AI↗

arXiv2025

OMOP ETL Framework for Semi-Structured Health Data

Healthcare data are generated in many different formats, which makes it difficult to integrate and reuse across institutions and studies. Standardisation is required to enable consistent large-scale analysis. The OMOP-CDM, developed by the OHDSI community, provides one widely adopted standard. Our framework achieves schema-agnostic transformation by extending upon existing literature in using human-readable YAML specification to support both relational (Microsoft SQL Server (MSSQL)) and document-based (MongoDB) data sources. It also incorporates critical production readiness features: provenance-aware mapping and support for incremental updates. We validated the pipeline using 2.7 million patient records and 27 million encounters across six hospitals spanning two decades of records. The resulting OMOP-CDM dataset demonstrated an acceptable level of data quality with a 97% overall passing rate based on the OHDSI Data Quality Dashboard check. Our work provides a reusable blueprint for large-scale data harmonisation, directly supporting real-world medical data research.

q-bio.QM↗

arXiv2025

Classification of kinetic-related injury in hospital triage data using NLP

Triage notes, created at the start of a patient's hospital visit, contain a wealth of information that can help medical staff and researchers understand Emergency Department patient epidemiology and the degree of time-dependent illness or injury. Unfortunately, applying modern Natural Language Processing and Machine Learning techniques to analyse triage data faces some challenges: Firstly, hospital data contains highly sensitive information that is subject to privacy regulation thus need to be analysed on site; Secondly, most hospitals and medical facilities lack the necessary hardware to fine-tune a Large Language Model (LLM), much less training one from scratch; Lastly, to identify the records of interest, expert inputs are needed to manually label the datasets, which can be time-consuming and costly. We present in this paper a pipeline that enables the classification of triage data using LLM and limited compute resources. We first fine-tuned a pre-trained LLM with a classifier using a small (2k) open sourced dataset on a GPU; and then further fine-tuned the model with a hospital specific dataset of 1000 samples on a CPU. We demonstrated that by carefully curating the datasets and leveraging existing models and open sourced data, we can successfully classify triage data with limited compute resources.

cs.CL↗