King's College London

Research portal

Detection of Suicidality in Adolescents with Autism Spectrum Disorders: Developing a Natural Language Processing Approach for Use in Electronic Health Records

Research output: Contribution to journalArticle

Standard

Detection of Suicidality in Adolescents with Autism Spectrum Disorders : Developing a Natural Language Processing Approach for Use in Electronic Health Records. / Downs, Johnny; Velupillai, Sumithra; Gkotsis, Georgios; Holden, Rachel ; Kikoler, Maxim ; Dean, Harry; Fernandes, Andrea; Dutta, Rina.

In: Proceedings / AMIA, Vol. 2017, No. eCollection 2017, 16.04.2018, p. 641-649.

Research output: Contribution to journalArticle

Harvard

Downs, J, Velupillai, S, Gkotsis, G, Holden, R, Kikoler, M, Dean, H, Fernandes, A & Dutta, R 2018, 'Detection of Suicidality in Adolescents with Autism Spectrum Disorders: Developing a Natural Language Processing Approach for Use in Electronic Health Records', Proceedings / AMIA, vol. 2017, no. eCollection 2017, pp. 641-649. <https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5977628/>

APA

Downs, J., Velupillai, S., Gkotsis, G., Holden, R., Kikoler, M., Dean, H., Fernandes, A., & Dutta, R. (2018). Detection of Suicidality in Adolescents with Autism Spectrum Disorders: Developing a Natural Language Processing Approach for Use in Electronic Health Records. Proceedings / AMIA, 2017(eCollection 2017), 641-649. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5977628/

Vancouver

Downs J, Velupillai S, Gkotsis G, Holden R, Kikoler M, Dean H et al. Detection of Suicidality in Adolescents with Autism Spectrum Disorders: Developing a Natural Language Processing Approach for Use in Electronic Health Records. Proceedings / AMIA. 2018 Apr 16;2017(eCollection 2017):641-649.

Author

Downs, Johnny ; Velupillai, Sumithra ; Gkotsis, Georgios ; Holden, Rachel ; Kikoler, Maxim ; Dean, Harry ; Fernandes, Andrea ; Dutta, Rina. / Detection of Suicidality in Adolescents with Autism Spectrum Disorders : Developing a Natural Language Processing Approach for Use in Electronic Health Records. In: Proceedings / AMIA. 2018 ; Vol. 2017, No. eCollection 2017. pp. 641-649.

Bibtex Download

@article{2e703fc12f87448eabfc14e36036c471,
title = "Detection of Suicidality in Adolescents with Autism Spectrum Disorders: Developing a Natural Language Processing Approach for Use in Electronic Health Records",
abstract = "Over 15% of young people with autism spectrum disorders (ASD) will contemplate or attempt suicide during adolescence. Yet, there is limited evidence concerning risk factors for suicidality in childhood ASD. Electronic health records (EHRs) can be used to create retrospective clinical cohort data for large samples of children with ASD. However systems to accurately extract suicidality-related concepts need to be developed so that putative models of suicide risk in ASD can be explored. We present a systematic approach to 1) adapt Natural Language Processing (NLP) solutions to screen with high sensitivity for reference to suicidal constructs in a large clinical ASD EHR corpus (230,465 documents), and 2) evaluate within a screened subset of 500 patients, the performance of an NLP classification tool for positive and negated suicidal mentions within clinical text. When evaluated, the NLP classification tool showed high system performance for positive suicidality with precision, recall, and F1 scores all > 0.85 at a document and patient level. The application therefore provides accurate output for epidemiological research into the factors contributing to the onset and recurrence of suicidality, and potential utility within clinical settings as an automated surveillance or risk prediction tool for specialist ASD services. ",
author = "Johnny Downs and Sumithra Velupillai and Georgios Gkotsis and Rachel Holden and Maxim Kikoler and Harry Dean and Andrea Fernandes and Rina Dutta",
year = "2018",
month = apr,
day = "16",
language = "English",
volume = "2017",
pages = "641--649",
journal = "Proceedings / AMIA",
issn = "1559-4076",
number = "eCollection 2017",

}

RIS (suitable for import to EndNote) Download

TY - JOUR

T1 - Detection of Suicidality in Adolescents with Autism Spectrum Disorders

T2 - Developing a Natural Language Processing Approach for Use in Electronic Health Records

AU - Downs, Johnny

AU - Velupillai, Sumithra

AU - Gkotsis, Georgios

AU - Holden, Rachel

AU - Kikoler, Maxim

AU - Dean, Harry

AU - Fernandes, Andrea

AU - Dutta, Rina

PY - 2018/4/16

Y1 - 2018/4/16

N2 - Over 15% of young people with autism spectrum disorders (ASD) will contemplate or attempt suicide during adolescence. Yet, there is limited evidence concerning risk factors for suicidality in childhood ASD. Electronic health records (EHRs) can be used to create retrospective clinical cohort data for large samples of children with ASD. However systems to accurately extract suicidality-related concepts need to be developed so that putative models of suicide risk in ASD can be explored. We present a systematic approach to 1) adapt Natural Language Processing (NLP) solutions to screen with high sensitivity for reference to suicidal constructs in a large clinical ASD EHR corpus (230,465 documents), and 2) evaluate within a screened subset of 500 patients, the performance of an NLP classification tool for positive and negated suicidal mentions within clinical text. When evaluated, the NLP classification tool showed high system performance for positive suicidality with precision, recall, and F1 scores all > 0.85 at a document and patient level. The application therefore provides accurate output for epidemiological research into the factors contributing to the onset and recurrence of suicidality, and potential utility within clinical settings as an automated surveillance or risk prediction tool for specialist ASD services.

AB - Over 15% of young people with autism spectrum disorders (ASD) will contemplate or attempt suicide during adolescence. Yet, there is limited evidence concerning risk factors for suicidality in childhood ASD. Electronic health records (EHRs) can be used to create retrospective clinical cohort data for large samples of children with ASD. However systems to accurately extract suicidality-related concepts need to be developed so that putative models of suicide risk in ASD can be explored. We present a systematic approach to 1) adapt Natural Language Processing (NLP) solutions to screen with high sensitivity for reference to suicidal constructs in a large clinical ASD EHR corpus (230,465 documents), and 2) evaluate within a screened subset of 500 patients, the performance of an NLP classification tool for positive and negated suicidal mentions within clinical text. When evaluated, the NLP classification tool showed high system performance for positive suicidality with precision, recall, and F1 scores all > 0.85 at a document and patient level. The application therefore provides accurate output for epidemiological research into the factors contributing to the onset and recurrence of suicidality, and potential utility within clinical settings as an automated surveillance or risk prediction tool for specialist ASD services.

UR - https://www.ncbi.nlm.nih.gov/pubmed/29854129

M3 - Article

C2 - 29854129

VL - 2017

SP - 641

EP - 649

JO - Proceedings / AMIA

JF - Proceedings / AMIA

SN - 1559-4076

IS - eCollection 2017

ER -

View graph of relations

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