Identifying Signs and Symptoms of Urinary Tract Infection from Emergency Department Clinical Notes Using Large Language Models

Objectives Symptom characterization is critical to urinary tract infection (UTI) diagnosis, but identification of symptoms from the electronic health record (EHR) is challenging, limiting large-scale research, public health surveillance, and EHR-based clinical decision support. We therefore developed and compared two natural language processing (NLP) models to identify UTI symptoms from unstructured emergency department (ED) notes. Methods The study population consisted of patients aged ≥ 18 who presented to the (ED) in a north-eastern United States health system between June 2013 and August 2021 and had a urinalysis performed. We annotated a random subset of 1,250 ED clinician notes from these visits for a list of 17 UTI symptoms. We then developed two task-specific large language models (LLMs) to perform the task of named entity recognition (NER): a convolutional neural network (CNN)-based model (SpaCy) and a transformer-based model designed to process longer documents (Longformer). Models were trained on 1,000 notes and tested on a holdout set of 250 notes. We compared model performance (precision, recall, F1 measure) at identifying the presence or absence of UTI symptoms at the note level. Results 8,135 entities were identified in 1,250 notes; 83.6% of notes included at least one entity. Overall F1 measure for note-level symptom identification weighted by entity frequency was 0.84 for the SpaCy model and 0.88 for the Longformer model. F1 measure for identifying presence or absence of any UTI symptom in a clinical note was 0.96 (232/250 correctly classified) for the SpaCy model and 0.98 (240/250 correctly classified) for the Longformer model. Conclusions The study demonstrated the utility of LLMs and transformer-based models in particular for extracting UTI symptoms from unstructured ED clinical notes; models were highly accurate for detecting the presence or absence of any UTI symptom on the note level, with variable performance for individual symptoms.