Search Articles

View query in Help articles search
e.g. mhealth

Search Results (1 to 3 of 3 Results)

Download search results: CSV END BibTex RIS

Using Synthetic Health Care Data to Leverage Large Language Models for Named Entity Recognition: Development and Validation Study

Using Synthetic Health Care Data to Leverage Large Language Models for Named Entity Recognition: Development and Validation Study

Named entity recognition (NER) stands as a cornerstone in the realm of natural language processing, playing a pivotal role in the automated extraction of named entities, such as diseases, medications, symptoms, and medical procedures, from unstructured text [1]. NER facilitates the transformation of text data into structured information, enabling health care professionals and researchers to carry out statistical analyses on the data.

Hendrik Šuvalov, Mihkel Lepson, Veronika Kukk, Maria Malk, Neeme Ilves, Hele-Andra Kuulmets, Raivo Kolde

J Med Internet Res 2025;27:e66279

Download Citation: END BibTex RIS

Download PDF Download XML

Performance Improvement of a Natural Language Processing Tool for Extracting Patient Narratives Related to Medical States From Japanese Pharmaceutical Care Records by Increasing the Amount of Training Data: Natural Language Processing Analysis and Validation Study

Performance Improvement of a Natural Language Processing Tool for Extracting Patient Narratives Related to Medical States From Japanese Pharmaceutical Care Records by Increasing the Amount of Training Data: Natural Language Processing Analysis and Validation Study

For example, named entity recognition (NER) technology can be used to extract disease and symptom names from natural language text and determine whether the extracted terms are positively or negatively expressed (positive-negative classification). NER is expected to be useful for analyzing symptoms, as in adverse event monitoring.

Yukiko Ohno, Tohru Aomori, Tomohiro Nishiyama, Riri Kato, Reina Fujiki, Haruki Ishikawa, Keisuke Kiyomiya, Minae Isawa, Mayumi Mochizuki, Eiji Aramaki, Hisakazu Ohtani

JMIR Med Inform 2025;13:e68863

Download Citation: END BibTex RIS

Download PDF Download XML
Article has an altmetric score of 2

Developing an ICD-10 Coding Assistant: Pilot Study Using RoBERTa and GPT-4 for Term Extraction and Description-Based Code Selection

Developing an ICD-10 Coding Assistant: Pilot Study Using RoBERTa and GPT-4 for Term Extraction and Description-Based Code Selection

For each diagnosis and procedure that needs an ICD code, the initial step is to identify the lead term, which is comparable to the named entity recognition (NER) task in NLP. NER involves extracting specific categories like names, locations, medications, and diseases from unstructured text. Only a few studies proposing lead term-based approaches for ICD coding have been published [5], possibly due to the absence of public datasets annotated with lead terms.

Sander Puts, Catharina M L Zegers, Andre Dekker, Iñigo Bermejo

JMIR Form Res 2025;9:e60095

Download Citation: END BibTex RIS

Download PDF Download XML
Article has an altmetric score of 1