English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Linking clinical narratives to standardized vocabularies and coding systemsis a key component of unlocking the information in medical text for analysis.However, many domains of medical concepts lack well-developed terminologiesthat can support effective coding of medical text. We present a framework fordeveloping natural language processing (NLP) technologies for automated codingof under-studied types of medical information, and demonstrate itsapplicability via a case study on physical mobility function. Mobility is acomponent of many health measures, from post-acute care and surgical outcomesto chronic frailty and disability, and is coded in the InternationalClassification of Functioning, Disability, and Health (ICF). However, mobilityand other types of functional activity remain under-studied in medicalinformatics, and neither the ICF nor commonly-used medical terminologiescapture functional status terminology in practice. We investigated twodata-driven paradigms, classification and candidate selection, to linknarrative observations of mobility to standardized ICF codes, using a datasetof clinical narratives from physical therapy encounters. Recent advances inlanguage modeling and word embedding were used as features for establishedmachine learning models and a novel deep learning approach, achieving a macroF-1 score of 84% on linking mobility activity reports to ICF codes. Bothclassification and candidate selection approaches present distinct strengthsfor automated coding in under-studied domains, and we highlight that thecombination of (i) a small annotated data set; (ii) expert definitions of codesof interest; and (iii) a representative text corpus is sufficient to producehigh-performing automated coding systems. This study has implications for theongoing growth of NLP tools for a variety of specialized applications inclinical care and research.

frontiers in digital health

Automated Coding of Under-Studied Medical Concept Domains: Linking  Physical Activity Reports to the International Classification of Functioning,  Disability, and Health