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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Social and behavioral determinants of health (SBDoH) have important roles inshaping people's health. In clinical research studies, especially comparativeeffectiveness studies, failure to adjust for SBDoH factors will potentiallycause confounding issues and misclassification errors in either statisticalanalyses and machine learning-based models. However, there are limited studiesto examine SBDoH factors in clinical outcomes due to the lack of structuredSBDoH information in current electronic health record (EHR) systems, while muchof the SBDoH information is documented in clinical narratives. Natural languageprocessing (NLP) is thus the key technology to extract such information fromunstructured clinical text. However, there is not a mature clinical NLP systemfocusing on SBDoH. In this study, we examined two state-of-the-arttransformer-based NLP models, including BERT and RoBERTa, to extract SBDoHconcepts from clinical narratives, applied the best performing model to extractSBDoH concepts on a lung cancer screening patient cohort, and examined thedifference of SBDoH information between NLP extracted results and structuredEHRs (SBDoH information captured in standard vocabularies such as theInternational Classification of Diseases codes). The experimental results showthat the BERT-based NLP model achieved the best strict/lenient F1-score of0.8791 and 0.8999, respectively. The comparison between NLP extracted SBDoHinformation and structured EHRs in the lung cancer patient cohort of 864patients with 161,933 various types of clinical notes showed that much moredetailed information about smoking, education, and employment were onlycaptured in clinical narratives and that it is necessary to use both clinicalnarratives and structured EHRs to construct a more complete picture ofpatients' SBDoH factors.

A Study of Social and Behavioral Determinants of Health in Lung Cancer Patients Using Transformers-based Natural Language Processing Models