Knowledge Driven Phenotyping

Honghan Wu; Minhong Wang; Qianyi Zeng; Wenjun Chen; Thomas Nind; Emily Jefferson; Marion Bennie; Corri Black; Jeff Z Pan; Cathie Sudlow; Dave Robertson

doi:10.3233/SHTI200425

Knowledge Driven Phenotyping

Honghan Wu
, Minhong Wang
, Qianyi Zeng
, Wenjun Chen
, Thomas Nind
, Emily Jefferson
, Marion Bennie
, Corri Black
, Jeff Z Pan
, Cathie Sudlow
, Dave Robertson

Research output: Contribution to journal › Article › peer-review

3 Citations (Scopus)

106 Downloads (Pure)

Abstract

Extracting patient phenotypes from routinely collected health data (such as Electronic Health Records) requires translating clinically-sound phenotype definitions into queries/computations executable on the underlying data sources by clinical researchers. This requires significant knowledge and skills to deal with heterogeneous and often imperfect data. Translations are time-consuming, error-prone and, most importantly, hard to share and reproduce across different settings. This paper proposes a knowledge driven framework that (1) decouples the specification of phenotype semantics from underlying data sources; (2) can automatically populate and conduct phenotype computations on heterogeneous data spaces. We report preliminary results of deploying this framework on five Scottish health datasets.

Original language	English
Pages (from-to)	1327-1328
Number of pages	2
Journal	Studies in Health Technology and Informatics
Volume	270
DOIs	https://doi.org/10.3233/SHTI200425
Publication status	Published - 16 Jun 2020

Keywords

Electronic Health Records
Information Storage and Retrieval
Semantics

Access to Document

10.3233/SHTI200425Licence: CC BY-NC

Final Published VersionFinal published version, 111 KBLicence: CC BY-NC

Health Informatics Centre
Health and Clinical Services
Facility/equipment: Facility

Cite this

@article{94624d20aff84bb292e3e4d8c06c69ab,

title = "Knowledge Driven Phenotyping",

abstract = "Extracting patient phenotypes from routinely collected health data (such as Electronic Health Records) requires translating clinically-sound phenotype definitions into queries/computations executable on the underlying data sources by clinical researchers. This requires significant knowledge and skills to deal with heterogeneous and often imperfect data. Translations are time-consuming, error-prone and, most importantly, hard to share and reproduce across different settings. This paper proposes a knowledge driven framework that (1) decouples the specification of phenotype semantics from underlying data sources; (2) can automatically populate and conduct phenotype computations on heterogeneous data spaces. We report preliminary results of deploying this framework on five Scottish health datasets.",

keywords = "Electronic Health Records, Information Storage and Retrieval, Semantics",

author = "Honghan Wu and Minhong Wang and Qianyi Zeng and Wenjun Chen and Thomas Nind and Emily Jefferson and Marion Bennie and Corri Black and Pan, \{Jeff Z\} and Cathie Sudlow and Dave Robertson",

year = "2020",

month = jun,

day = "16",

doi = "10.3233/SHTI200425",

language = "English",

volume = "270",

pages = "1327--1328",

journal = "Studies in Health Technology and Informatics ",

issn = "0926-9630",

publisher = "IOS Press BV",

}

TY - JOUR

T1 - Knowledge Driven Phenotyping

AU - Wu, Honghan

AU - Wang, Minhong

AU - Zeng, Qianyi

AU - Chen, Wenjun

AU - Nind, Thomas

AU - Jefferson, Emily

AU - Bennie, Marion

AU - Black, Corri

AU - Pan, Jeff Z

AU - Sudlow, Cathie

AU - Robertson, Dave

PY - 2020/6/16

Y1 - 2020/6/16

N2 - Extracting patient phenotypes from routinely collected health data (such as Electronic Health Records) requires translating clinically-sound phenotype definitions into queries/computations executable on the underlying data sources by clinical researchers. This requires significant knowledge and skills to deal with heterogeneous and often imperfect data. Translations are time-consuming, error-prone and, most importantly, hard to share and reproduce across different settings. This paper proposes a knowledge driven framework that (1) decouples the specification of phenotype semantics from underlying data sources; (2) can automatically populate and conduct phenotype computations on heterogeneous data spaces. We report preliminary results of deploying this framework on five Scottish health datasets.

AB - Extracting patient phenotypes from routinely collected health data (such as Electronic Health Records) requires translating clinically-sound phenotype definitions into queries/computations executable on the underlying data sources by clinical researchers. This requires significant knowledge and skills to deal with heterogeneous and often imperfect data. Translations are time-consuming, error-prone and, most importantly, hard to share and reproduce across different settings. This paper proposes a knowledge driven framework that (1) decouples the specification of phenotype semantics from underlying data sources; (2) can automatically populate and conduct phenotype computations on heterogeneous data spaces. We report preliminary results of deploying this framework on five Scottish health datasets.

KW - Electronic Health Records

KW - Information Storage and Retrieval

KW - Semantics

U2 - 10.3233/SHTI200425

DO - 10.3233/SHTI200425

M3 - Article

C2 - 32570642

SN - 0926-9630

VL - 270

SP - 1327

EP - 1328

JO - Studies in Health Technology and Informatics

JF - Studies in Health Technology and Informatics

ER -

Knowledge Driven Phenotyping

Abstract

Keywords

Access to Document

Fingerprint

Equipment

Health Informatics Centre

Cite this