King's College London

Research portal

Knowledge discovery for Deep Phenotyping serious mental illness from Electronic Mental Health records [version 2; referees: 2 approved]

Research output: Contribution to journalArticle

Standard

Knowledge discovery for Deep Phenotyping serious mental illness from Electronic Mental Health records [version 2; referees : 2 approved]. / Stewart, Robert; Jackson, Richard; Patel, Rashmi; Velupillai, Sumithra; Gkotsis, George; Hoyle, David.

In: F1000Research, Vol. 7, 210, 08.12.2018.

Research output: Contribution to journalArticle

Harvard

Stewart, R, Jackson, R, Patel, R, Velupillai, S, Gkotsis, G & Hoyle, D 2018, 'Knowledge discovery for Deep Phenotyping serious mental illness from Electronic Mental Health records [version 2; referees: 2 approved]', F1000Research, vol. 7, 210. https://doi.org/10.12688/f1000research.13830.2

APA

Stewart, R., Jackson, R., Patel, R., Velupillai, S., Gkotsis, G., & Hoyle, D. (2018). Knowledge discovery for Deep Phenotyping serious mental illness from Electronic Mental Health records [version 2; referees: 2 approved]. F1000Research, 7, [210]. https://doi.org/10.12688/f1000research.13830.2

Vancouver

Stewart R, Jackson R, Patel R, Velupillai S, Gkotsis G, Hoyle D. Knowledge discovery for Deep Phenotyping serious mental illness from Electronic Mental Health records [version 2; referees: 2 approved]. F1000Research. 2018 Dec 8;7. 210. https://doi.org/10.12688/f1000research.13830.2

Author

Stewart, Robert ; Jackson, Richard ; Patel, Rashmi ; Velupillai, Sumithra ; Gkotsis, George ; Hoyle, David. / Knowledge discovery for Deep Phenotyping serious mental illness from Electronic Mental Health records [version 2; referees : 2 approved]. In: F1000Research. 2018 ; Vol. 7.

Bibtex Download

@article{9eb8177eac5948bfafd75d5a6e5b275c,
title = "Knowledge discovery for Deep Phenotyping serious mental illness from Electronic Mental Health records [version 2; referees: 2 approved]",
abstract = "Background: Deep Phenotyping is the precise and comprehensive analysis of phenotypic features in which the individual components of the phenotype are observed and described. In UK mental health clinical practice, most clinically relevant information is recorded as free text in the Electronic Health Record, and offers a granularity of information beyond what is expressed in most medical knowledge bases. The SNOMED CT nomenclature potentially offers the means to model such information at scale, yet given a sufficiently large body of clinical text collected over many years, it is difficult to identify the language that clinicians favour to express concepts. Methods: By utilising a large corpus of healthcare data, we sought to make use of semantic modelling and clustering techniques to represent the relationship between the clinical vocabulary of internationally recognised SMI symptoms and the preferred language used by clinicians within a care setting. We explore how such models can be used for discovering novel vocabulary relevant to the task of phenotyping Serious Mental Illness (SMI) with only a small amount of prior knowledge. Results: 20 403 terms were derived and curated via a two stage methodology. The list was reduced to 557 putative concepts based on eliminating redundant information content. These were then organised into 9 distinct categories pertaining to different aspects of psychiatric assessment. 235 concepts were found to be expressions of putative clinical significance. Of these, 53 were identified having novel synonymy with existing SNOMED CT concepts. 106 had no mapping to SNOMED CT. Conclusions: We demonstrate a scalable approach to discovering new concepts of SMI symptomatology based on real-world clinical observation. Such approaches may offer the opportunity to consider broader manifestations of SMI symptomatology than is typically assessed via current diagnostic frameworks, and create the potential for enhancing nomenclatures such as SNOMED CT based on real-world expressions.",
keywords = "Electronic health records, Natural language processing, Schizophrenia, Serious mental illness, Word2vec",
author = "Robert Stewart and Richard Jackson and Rashmi Patel and Sumithra Velupillai and George Gkotsis and David Hoyle",
year = "2018",
month = "12",
day = "8",
doi = "10.12688/f1000research.13830.2",
language = "English",
volume = "7",
journal = "F1000Research",
issn = "2046-1402",
publisher = "F1000 Research Ltd.",

}

RIS (suitable for import to EndNote) Download

TY - JOUR

T1 - Knowledge discovery for Deep Phenotyping serious mental illness from Electronic Mental Health records [version 2; referees

T2 - 2 approved]

AU - Stewart, Robert

AU - Jackson, Richard

AU - Patel, Rashmi

AU - Velupillai, Sumithra

AU - Gkotsis, George

AU - Hoyle, David

PY - 2018/12/8

Y1 - 2018/12/8

N2 - Background: Deep Phenotyping is the precise and comprehensive analysis of phenotypic features in which the individual components of the phenotype are observed and described. In UK mental health clinical practice, most clinically relevant information is recorded as free text in the Electronic Health Record, and offers a granularity of information beyond what is expressed in most medical knowledge bases. The SNOMED CT nomenclature potentially offers the means to model such information at scale, yet given a sufficiently large body of clinical text collected over many years, it is difficult to identify the language that clinicians favour to express concepts. Methods: By utilising a large corpus of healthcare data, we sought to make use of semantic modelling and clustering techniques to represent the relationship between the clinical vocabulary of internationally recognised SMI symptoms and the preferred language used by clinicians within a care setting. We explore how such models can be used for discovering novel vocabulary relevant to the task of phenotyping Serious Mental Illness (SMI) with only a small amount of prior knowledge. Results: 20 403 terms were derived and curated via a two stage methodology. The list was reduced to 557 putative concepts based on eliminating redundant information content. These were then organised into 9 distinct categories pertaining to different aspects of psychiatric assessment. 235 concepts were found to be expressions of putative clinical significance. Of these, 53 were identified having novel synonymy with existing SNOMED CT concepts. 106 had no mapping to SNOMED CT. Conclusions: We demonstrate a scalable approach to discovering new concepts of SMI symptomatology based on real-world clinical observation. Such approaches may offer the opportunity to consider broader manifestations of SMI symptomatology than is typically assessed via current diagnostic frameworks, and create the potential for enhancing nomenclatures such as SNOMED CT based on real-world expressions.

AB - Background: Deep Phenotyping is the precise and comprehensive analysis of phenotypic features in which the individual components of the phenotype are observed and described. In UK mental health clinical practice, most clinically relevant information is recorded as free text in the Electronic Health Record, and offers a granularity of information beyond what is expressed in most medical knowledge bases. The SNOMED CT nomenclature potentially offers the means to model such information at scale, yet given a sufficiently large body of clinical text collected over many years, it is difficult to identify the language that clinicians favour to express concepts. Methods: By utilising a large corpus of healthcare data, we sought to make use of semantic modelling and clustering techniques to represent the relationship between the clinical vocabulary of internationally recognised SMI symptoms and the preferred language used by clinicians within a care setting. We explore how such models can be used for discovering novel vocabulary relevant to the task of phenotyping Serious Mental Illness (SMI) with only a small amount of prior knowledge. Results: 20 403 terms were derived and curated via a two stage methodology. The list was reduced to 557 putative concepts based on eliminating redundant information content. These were then organised into 9 distinct categories pertaining to different aspects of psychiatric assessment. 235 concepts were found to be expressions of putative clinical significance. Of these, 53 were identified having novel synonymy with existing SNOMED CT concepts. 106 had no mapping to SNOMED CT. Conclusions: We demonstrate a scalable approach to discovering new concepts of SMI symptomatology based on real-world clinical observation. Such approaches may offer the opportunity to consider broader manifestations of SMI symptomatology than is typically assessed via current diagnostic frameworks, and create the potential for enhancing nomenclatures such as SNOMED CT based on real-world expressions.

KW - Electronic health records

KW - Natural language processing

KW - Schizophrenia

KW - Serious mental illness

KW - Word2vec

UR - http://www.scopus.com/inward/record.url?scp=85047790722&partnerID=8YFLogxK

U2 - 10.12688/f1000research.13830.2

DO - 10.12688/f1000research.13830.2

M3 - Article

AN - SCOPUS:85047790722

VL - 7

JO - F1000Research

JF - F1000Research

SN - 2046-1402

M1 - 210

ER -

View graph of relations

© 2018 King's College London | Strand | London WC2R 2LS | England | United Kingdom | Tel +44 (0)20 7836 5454