Academic emergency medicine : official journal of the Society for Academic Emergency Medicine
-
Natural language processing (NLP) tools including recently developed large language models (LLMs) have myriad potential applications in medical care and research, including the efficient labeling and classification of unstructured text such as electronic health record (EHR) notes. This opens the door to large-scale projects that rely on variables that are not typically recorded in a structured form, such as patient signs and symptoms. ⋯ 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.
-
The emergency department (ED) is a demanding and time-pressured environment where doctors must navigate numerous team interactions. Conflicts between health care professionals frequently arise in these settings. We aim to synthesize the individual-, team-, and systemic-level factors that contribute to conflict between clinicians within the ED and explore strategies and opportunities for future research. ⋯ In emergency medicine, conflict is common and occurs at multiple levels, reflecting the complex interface of tasks and relationships within ED.
-
Changes in pain scores that represent clinically significant differences in children with headaches are necessary for study design and interpretation of findings reported in studies. We aimed to determine changes in pain scores associated with a minimum clinically significant difference (MCSD), ideal clinically significant difference (ICSD), and patient-perceived adequate analgesia (PPAA) in this population. ⋯ We identified changes in pain score associated with patient-centered outcomes in children with headaches suitable for designing trials and assigning clinical significance to changes in pain scores reported in studies.