Guardado en:
Detalles Bibliográficos
Autores principales: Munzir, Syed I., Hier, Daniel B., Oommen, Chelsea, Carrithers, Michael D.
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2406.14757
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866909228765020160
author Munzir, Syed I.
Hier, Daniel B.
Oommen, Chelsea
Carrithers, Michael D.
author_facet Munzir, Syed I.
Hier, Daniel B.
Oommen, Chelsea
Carrithers, Michael D.
contents High-throughput phenotyping, the automated mapping of patient signs and symptoms to standardized ontology concepts, is essential to gaining value from electronic health records (EHR) in the support of precision medicine. Despite technological advances, high-throughput phenotyping remains a challenge. This study compares three computational approaches to high-throughput phenotyping: a Large Language Model (LLM) incorporating generative AI, a Natural Language Processing (NLP) approach utilizing deep learning for span categorization, and a hybrid approach combining word vectors with machine learning. The approach that implemented GPT-4 (a Large Language Model) demonstrated superior performance, suggesting that Large Language Models are poised to be the preferred method for high-throughput phenotyping of physician notes.
format Preprint
id arxiv_https___arxiv_org_abs_2406_14757
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Large Language Model Outperforms Other Computational Approaches to the High-Throughput Phenotyping of Physician Notes
Munzir, Syed I.
Hier, Daniel B.
Oommen, Chelsea
Carrithers, Michael D.
Artificial Intelligence
92-05
I.2
High-throughput phenotyping, the automated mapping of patient signs and symptoms to standardized ontology concepts, is essential to gaining value from electronic health records (EHR) in the support of precision medicine. Despite technological advances, high-throughput phenotyping remains a challenge. This study compares three computational approaches to high-throughput phenotyping: a Large Language Model (LLM) incorporating generative AI, a Natural Language Processing (NLP) approach utilizing deep learning for span categorization, and a hybrid approach combining word vectors with machine learning. The approach that implemented GPT-4 (a Large Language Model) demonstrated superior performance, suggesting that Large Language Models are poised to be the preferred method for high-throughput phenotyping of physician notes.
title A Large Language Model Outperforms Other Computational Approaches to the High-Throughput Phenotyping of Physician Notes
topic Artificial Intelligence
92-05
I.2
url https://arxiv.org/abs/2406.14757