Improving ED Emergency Severity Index Acuity Assignment Using Machine Learning and Clinical Natural Language Processing
نویسندگان
چکیده
Effective triage is critical to mitigating the effect of increased volume by accurately determining patient acuity, need for resources, and establishing effective acuity-based prioritization. The purpose this retrospective study was determine whether historical EHR data can be extracted synthesized with clinical natural language processing (C-NLP) latest ML algorithms (KATE) produce highly accurate ESI predictive models. An model process developed using 166,175 encounters from two participating hospitals. then tested against a gold set that derived random sample at sites correct acuity assignments were recorded clinicians Emergency Severity Index (ESI) standard as guide. At sites, KATE predicted 75.9% time, compared nurses (59.8%) average individual (75.3%). accuracy 26.9% higher than nurse (p-value < 0.0001). On boundary between 2 3 assignments, which relates risk decompensation, 93.2% 80% accuracy, 41.4% provides assignment substantially more in sample. operates independently contextual factors, unaffected external pressures cause under may mitigate racial social biases negatively affect assignment. Future research should focus on impact providing feedback real KATEs mortality morbidity, ED throughput, resource optimization, nursing outcomes.
منابع مشابه
Machine Learning in Natural Language Processing
This thesis examines the use of machine learning techniques in various tasks of natural language processing, mainly for the task of information extraction from texts. The objectives are the improvement of adaptability of information extraction systems to new thematic domains (or even languages), and the improvement of their performance using as fewer resources (either linguistic or human) as po...
متن کاملMachine Learning in Natural Language Processing
Machine learning is concerned with acquiring knowledge from an environment in a computational manner, in order to improve the performance. (See Langley [15] for overview of ML.) Many forces over the past couple of decades have seen the blending of ML and NLP become increasingly common. The ever expanding availability of large corpora; more powerful computing resources; and a greater demand for ...
متن کاملMachine Learning in Natural Language Processing
2 Tagging 5 2.1 PoS tagging . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5 2.1.1 Features for PoS Tagging . . . . . . . . . . . . . . . . 6 2.1.2 PoS Tagging Results for Different Languages . . . . . 7 2.2 Named Entity Recognition . . . . . . . . . . . . . . . . . . . . 8 2.2.1 One-step vs Two-step Classification . . . . . . . . . . 8 2.2.2 Features for NER . . . . . . . . . . . . . ...
متن کاملMedical subdomain classification of clinical notes using a machine learning-based natural language processing approach
BACKGROUND The medical subdomain of a clinical note, such as cardiology or neurology, is useful content-derived metadata for developing machine learning downstream applications. To classify the medical subdomain of a note accurately, we have constructed a machine learning-based natural language processing (NLP) pipeline and developed medical subdomain classifiers based on the content of the not...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Journal of Emergency Nursing
سال: 2021
ISSN: ['0099-1767', '1527-2966']
DOI: https://doi.org/10.1016/j.jen.2020.11.001