About: A semi-supervised approach for rapidly creating clinical biomarker phenotypes in the UK Biobank using different primary care EHR and clinical terminology systems.

Facets (new session)
Description
Metadata
Settings
- owl:sameAs
- Inference Rule:

About: A semi-supervised approach for rapidly creating clinical biomarker phenotypes in the UK Biobank using different primary care EHR and clinical terminology systems. Goto Sponge NotDistinct Permalink

An Entity of Type : schema:ScholarlyArticle, within Data Space : wasabi.inria.fr associated with source document(s)

Attributes	Values
type	Academic Article research paper schema:ScholarlyArticle
isDefinedBy	Covid-on-the-Web dataset
has title	A semi-supervised approach for rapidly creating clinical biomarker phenotypes in the UK Biobank using different primary care EHR and clinical terminology systems.
Creator	Quint, Jennifer Denaxas, Spiros Hemingway, Harry Shah, Anoop Fatemifar, Ghazaleh Fitzpatrick, Natalie Kuan, Valerie Mateen, Bilal Torralbo, Ana
Source	MedRxiv
abstract	Objectives The UK Biobank (UKB) is making primary care Electronic Health Records (EHR) for 500,000 participants available for COVID-19-related research. Data are extracted from four sources, recorded using five clinical terminologies and stored in different schemas. The aims of our research were to: a) develop a semi-supervised approach for bootstrapping EHR phenotyping algorithms in UKB EHR, and b) to evaluate our approach by implementing and evaluating phenotypes for 31 common biomarkers. Materials and Methods We describe an algorithmic approach to phenotyping biomarkers in primary care EHR involving a) bootstrapping definitions using existing phenotypes, b) excluding generic, rare or semantically distant terms, c) forward-mapping terminology terms, d) expert review, and e) data extraction. We evaluated the phenotypes by assessing the ability to reproduce known epidemiological associations with all-cause mortality using Cox proportional hazards models. Results We created and evaluated phenotyping algorithms for 31 biomarkers many of which are directly related to COVID-19 complications e.g. diabetes, cardiovascular disease, respiratory disease. Our algorithm identified 1651 Read v2 and Clinical Terms Version 3 terms and automatically excluded 1228 terms. Clinical review excluded 103 terms and included 44 terms, resulting in 364 terms for data extraction (sensitivity 0.89, specificity 0.92). We extracted 38,190,682 events and identified 220,978 participants with at least one biomarker measured. Discussion and conclusion Bootstrapping phenotyping algorithms from similar EHR can potentially address pre-existing methodological concerns that undermine the outputs of biomarker discovery pipelines and provide research-quality phenotyping algorithms.
has issue date	2020-05-19(xsd:dateTime)
bibo:doi	10.1101/2020.05.14.20101626
has license	medrxiv
sha1sum (hex)	f7c826701a3968cda59d04fbac320953f4be934c
schema:url	https://doi.org/10.1101/2020.05.14.20101626
resource representing a document's title	A semi-supervised approach for rapidly creating clinical biomarker phenotypes in the UK Biobank using different primary care EHR and clinical terminology systems.
resource representing a document's body	covid:f7c826701a3968cda59d04fbac320953f4be934c#body_text
is schema:about of	named entity 'primary care' named entity 'phenotyping' named entity 'phenotypes' named entity 'clinical terminology' named entity 'USING' named entity 'RELATED' named entity 'BOOTSTRAPPING' named entity 'OUR APPROACH' named entity 'EHR' named entity 'biomarkers' named entity 'bootstrapping' named entity 'evaluating' named entity 'semi-supervised' named entity 'primary care' named entity 'Electronic Health Records' named entity 'phenotypes' named entity 'EHR' named entity 'COVID' named entity 'clinical terminology' named entity 'semi-supervised' named entity 'primary care' named entity 'SQL' named entity 'epidemiological' named entity 'alanine aminotransferase' named entity 'red blood cell' named entity 'EMIS' named entity 'Read codes' named entity 'PHE' named entity 'biomarker' named entity 'NHS' named entity 'Units of Measurement' named entity 'Cox proportional hazards model' named entity 'CTV3' named entity 'peer review' named entity 'metadata' named entity 'phenotyping' named entity 'biomarker' named entity 'EHR' named entity 'England' named entity 'England' named entity 'WBC' named entity 'chronic obstructive pulmonary disease' named entity 'pathologies' named entity 'EHR' named entity 'biomarker' named entity 'general practices' named entity 'blood pressure' named entity 'peer review' named entity 'biomarkers' named entity 'semi-supervised' named entity 'medRxiv' named entity 'biomarker' named entity 'EHR' named entity 'semi-supervised' named entity 'COVID-19' named entity 'blood pressure' named entity 'blood pressure' named entity 'EHR' named entity 'blood pressure' named entity 'health service' named entity 'phenotyping' named entity 'biochemistry' named entity 'proportional hazards regression' named entity 'CTV3' named entity 'phenotypes' named entity 'genetic factors' named entity 'phenotypes' named entity 'CTV3' named entity 'SNOMED-CT' named entity 'White Blood Cell' named entity 'Forced Expiratory Volume' named entity 'UK Biobank' named entity 'phenotype' named entity 'SNOMED-CT' named entity 'Scotland' named entity 'bronchodilation' named entity 'red blood cell'

Faceted Search & Find service v1.13.91 as of Mar 24 2020

Alternative Linked Data Documents: Sponger | ODE Content Formats:

RDF

ODATA

Microdata

About

OpenLink Virtuoso version 07.20.3229 as of Jul 10 2020, on Linux (x86_64-pc-linux-gnu), Single-Server Edition (94 GB total memory)
Data on this page belongs to its respective rights holders.
Virtuoso Faceted Browser Copyright © 2009-2024 OpenLink Software