Development and application of the ocular immune-mediated inflammatory diseases ontology enhanced with synonyms from online patient support forum conversation

Samantha C. Pendleton; Luke T. Slater; Andreas Karwath; Rose M. Gilbert; Nicola Davis; Konrad Pesudovs; Xiaoxuan Liu; Alastair K. Denniston; Georgios V. Gkoutos; Tasanee Braithwaite

doi:10.1016/j.compbiomed.2021.104542

Development and application of the ocular immune-mediated inflammatory diseases ontology enhanced with synonyms from online patient support forum conversation

Samantha C. Pendleton^*, Luke T. Slater, Andreas Karwath, Rose M. Gilbert, Nicola Davis, Konrad Pesudovs, Xiaoxuan Liu, Alastair K. Denniston, Georgios V. Gkoutos, Tasanee Braithwaite

^*Corresponding author for this work

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

55 Downloads (Pure)

Abstract

Background: Unstructured text created by patients represents a rich, but relatively inaccessible resource for advancing patient-centred care. This study aimed to develop an ontology for ocular immune-mediated inflammatory diseases (OcIMIDo), as a tool to facilitate data extraction and analysis, illustrating its application to online patient support forum data.

Methods: We developed OcIMIDo using clinical guidelines, domain expertise, and cross-references to classes from other biomedical ontologies. We developed an approach to add patient-preferred synonyms text-mined from oliviasvision.org online forum, using statistical ranking. We validated the approach with split-sampling and comparison to manual extraction. Using OcIMIDo, we then explored the frequency of OcIMIDo classes and synonyms, and their potential association with natural language sentiment expressed in each online forum post.

Findings: OcIMIDo (version 1.2) includes 661 classes, describing anatomy, clinical phenotype, disease activity status, complications, investigations, interventions and functional impacts. It contains 1661 relationships and axioms, 2851 annotations, including 1131 database cross-references, and 187 patient-preferred synonyms. To illustrate OcIMIDo's potential applications, we explored 9031 forum posts, revealing frequent mention of different clinical phenotypes, treatments, and complications. Language sentiment analysis of each post was generally positive (median 0.12, IQR 0.01–0.24). In multivariable logistic regression, the odds of a post expressing negative sentiment were significantly associated with first posts as compared to replies (OR 3.3, 95% CI 2.8 to 3.9, p < 0.001).

Conclusion: We report the development and validation of a new ontology for inflammatory eye diseases, which includes patient-preferred synonyms, and can be used to explore unstructured patient or physician-reported text data, with many potential applications.

Original language	English
Article number	104542
Number of pages	9
Journal	Computers in Biology and Medicine
Volume	135
Early online date	8 Jun 2021
DOIs	https://doi.org/10.1016/j.compbiomed.2021.104542
Publication status	Published - Aug 2021

Bibliographical note

Funding Information:
GVG acknowledges support from the National Institute for Health Research ( https://www.nihr.ac.uk/ ) Birmingham Experimental Cancer Medicine Centres ( https://www.ecmcnetwork.org.uk/ ), NIHR Birmingham Surgical Reconstruction ( https://www.birminghambrc.nihr.ac.uk/ ) and Microbiology Research Centre ( https://srmrc.nihr.ac.uk/ ), and the NIHR Birmingham Biomedical Research Centre ( https://www.uclh.nhs.uk/Research/BRC/Pages/Home.aspx ).

Funding Information:
AK was supported by the Medical Research Council ( MR/S003991/1 ) ( https://mrc.ukri.org/ ).

Funding Information:
RMG, GVG, and AKD acknowledge support from the Health Data Research UK ( https://www.hdruk.ac.uk/ ), GVG being directly funded (HDRUK/CFC/01).

Funding Information:
SCP and GVG acknowledge support from the Medical Research Council ( MR/S502431/1 ) that directly funded this work ( https://mrc.ukri.org/ ).

Funding Information:
We have reported the development and validation of a novel ontology for inflammatory eye disease, OcIMIDo (version 1.2). OcIMIDo organizes 661 classes into high-level concepts of diagnostic subtype, clinical features, classification (anatomy), disease activity, time course, core investigations, therapeutic interventions (and their efficacy and side effects), complications, and functional impacts, with structured knowledge representation. OcIMIDo joins only a small number of other disease area-specific ontologies currently available in general medicine. Notable examples include the @neurIST ontology of intracranial aneurysms [40], and the ACGT Master Ontology of Cancer [41]. Furthermore, we have reported use of an NLP-guided method to identify patient-preferred terms for inclusion in the ontology under class clinical terms as synonyms from a public patient support forum. This addresses an unmet need to better align computational tools with patient and physician-preferred language [1,20]. LTS and GVG also acknowledge support from Horizon 2020 E-Infrastructures (H2020-EINFRA) (731075) (https://ec.europa.eu/programmes/horizon2020/en) in addition to NanoCommons (H2020-EU) (731032) (https://www.nanocommons.eu/).

Publisher Copyright:
© 2021 The Author(s)

Keywords

Inflammation
Ontology
Patient voice
Sentiment
Uveitis

ASJC Scopus subject areas

Computer Science Applications
Health Informatics

Access to Document

10.1016/j.compbiomed.2021.104542Licence: Creative Commons: Attribution (CC BY)

1-s2.0-S001048252100336X-mainFinal published version, 2.72 MBLicence: Creative Commons: Attribution (CC BY)

Cite this

Pendleton, S. C., Slater, L. T., Karwath, A., Gilbert, R. M., Davis, N., Pesudovs, K., Liu, X., Denniston, A. K., Gkoutos, G. V., & Braithwaite, T. (2021). Development and application of the ocular immune-mediated inflammatory diseases ontology enhanced with synonyms from online patient support forum conversation. Computers in Biology and Medicine, 135, Article 104542. https://doi.org/10.1016/j.compbiomed.2021.104542

@article{a1112db9b113436eb989224286b0efaa,

title = "Development and application of the ocular immune-mediated inflammatory diseases ontology enhanced with synonyms from online patient support forum conversation",

abstract = "Background: Unstructured text created by patients represents a rich, but relatively inaccessible resource for advancing patient-centred care. This study aimed to develop an ontology for ocular immune-mediated inflammatory diseases (OcIMIDo), as a tool to facilitate data extraction and analysis, illustrating its application to online patient support forum data. Methods: We developed OcIMIDo using clinical guidelines, domain expertise, and cross-references to classes from other biomedical ontologies. We developed an approach to add patient-preferred synonyms text-mined from oliviasvision.org online forum, using statistical ranking. We validated the approach with split-sampling and comparison to manual extraction. Using OcIMIDo, we then explored the frequency of OcIMIDo classes and synonyms, and their potential association with natural language sentiment expressed in each online forum post. Findings: OcIMIDo (version 1.2) includes 661 classes, describing anatomy, clinical phenotype, disease activity status, complications, investigations, interventions and functional impacts. It contains 1661 relationships and axioms, 2851 annotations, including 1131 database cross-references, and 187 patient-preferred synonyms. To illustrate OcIMIDo's potential applications, we explored 9031 forum posts, revealing frequent mention of different clinical phenotypes, treatments, and complications. Language sentiment analysis of each post was generally positive (median 0.12, IQR 0.01–0.24). In multivariable logistic regression, the odds of a post expressing negative sentiment were significantly associated with first posts as compared to replies (OR 3.3, 95% CI 2.8 to 3.9, p < 0.001). Conclusion: We report the development and validation of a new ontology for inflammatory eye diseases, which includes patient-preferred synonyms, and can be used to explore unstructured patient or physician-reported text data, with many potential applications.",

keywords = "Inflammation, Ontology, Patient voice, Sentiment, Uveitis",

author = "Pendleton, {Samantha C.} and Slater, {Luke T.} and Andreas Karwath and Gilbert, {Rose M.} and Nicola Davis and Konrad Pesudovs and Xiaoxuan Liu and Denniston, {Alastair K.} and Gkoutos, {Georgios V.} and Tasanee Braithwaite",

note = "Funding Information: GVG acknowledges support from the National Institute for Health Research ( https://www.nihr.ac.uk/ ) Birmingham Experimental Cancer Medicine Centres ( https://www.ecmcnetwork.org.uk/ ), NIHR Birmingham Surgical Reconstruction ( https://www.birminghambrc.nihr.ac.uk/ ) and Microbiology Research Centre ( https://srmrc.nihr.ac.uk/ ), and the NIHR Birmingham Biomedical Research Centre ( https://www.uclh.nhs.uk/Research/BRC/Pages/Home.aspx ). Funding Information: AK was supported by the Medical Research Council ( MR/S003991/1 ) ( https://mrc.ukri.org/ ). Funding Information: RMG, GVG, and AKD acknowledge support from the Health Data Research UK ( https://www.hdruk.ac.uk/ ), GVG being directly funded (HDRUK/CFC/01). Funding Information: SCP and GVG acknowledge support from the Medical Research Council ( MR/S502431/1 ) that directly funded this work ( https://mrc.ukri.org/ ). Funding Information: We have reported the development and validation of a novel ontology for inflammatory eye disease, OcIMIDo (version 1.2). OcIMIDo organizes 661 classes into high-level concepts of diagnostic subtype, clinical features, classification (anatomy), disease activity, time course, core investigations, therapeutic interventions (and their efficacy and side effects), complications, and functional impacts, with structured knowledge representation. OcIMIDo joins only a small number of other disease area-specific ontologies currently available in general medicine. Notable examples include the @neurIST ontology of intracranial aneurysms [40], and the ACGT Master Ontology of Cancer [41]. Furthermore, we have reported use of an NLP-guided method to identify patient-preferred terms for inclusion in the ontology under class clinical terms as synonyms from a public patient support forum. This addresses an unmet need to better align computational tools with patient and physician-preferred language [1,20]. LTS and GVG also acknowledge support from Horizon 2020 E-Infrastructures (H2020-EINFRA) (731075) (https://ec.europa.eu/programmes/horizon2020/en) in addition to NanoCommons (H2020-EU) (731032) (https://www.nanocommons.eu/). Publisher Copyright: {\textcopyright} 2021 The Author(s)",

year = "2021",

month = aug,

doi = "10.1016/j.compbiomed.2021.104542",

language = "English",

volume = "135",

journal = "Computers in Biology and Medicine",

issn = "0010-4825",

publisher = "Elsevier",

}

Pendleton, SC, Slater, LT , Karwath, A, Gilbert, RM, Davis, N, Pesudovs, K, Liu, X, Denniston, AK , Gkoutos, GV & Braithwaite, T 2021, 'Development and application of the ocular immune-mediated inflammatory diseases ontology enhanced with synonyms from online patient support forum conversation', Computers in Biology and Medicine, vol. 135, 104542. https://doi.org/10.1016/j.compbiomed.2021.104542

TY - JOUR

T1 - Development and application of the ocular immune-mediated inflammatory diseases ontology enhanced with synonyms from online patient support forum conversation

AU - Pendleton, Samantha C.

AU - Slater, Luke T.

AU - Karwath, Andreas

AU - Gilbert, Rose M.

AU - Davis, Nicola

AU - Pesudovs, Konrad

AU - Liu, Xiaoxuan

AU - Denniston, Alastair K.

AU - Gkoutos, Georgios V.

AU - Braithwaite, Tasanee

N1 - Funding Information: GVG acknowledges support from the National Institute for Health Research ( https://www.nihr.ac.uk/ ) Birmingham Experimental Cancer Medicine Centres ( https://www.ecmcnetwork.org.uk/ ), NIHR Birmingham Surgical Reconstruction ( https://www.birminghambrc.nihr.ac.uk/ ) and Microbiology Research Centre ( https://srmrc.nihr.ac.uk/ ), and the NIHR Birmingham Biomedical Research Centre ( https://www.uclh.nhs.uk/Research/BRC/Pages/Home.aspx ). Funding Information: AK was supported by the Medical Research Council ( MR/S003991/1 ) ( https://mrc.ukri.org/ ). Funding Information: RMG, GVG, and AKD acknowledge support from the Health Data Research UK ( https://www.hdruk.ac.uk/ ), GVG being directly funded (HDRUK/CFC/01). Funding Information: SCP and GVG acknowledge support from the Medical Research Council ( MR/S502431/1 ) that directly funded this work ( https://mrc.ukri.org/ ). Funding Information: We have reported the development and validation of a novel ontology for inflammatory eye disease, OcIMIDo (version 1.2). OcIMIDo organizes 661 classes into high-level concepts of diagnostic subtype, clinical features, classification (anatomy), disease activity, time course, core investigations, therapeutic interventions (and their efficacy and side effects), complications, and functional impacts, with structured knowledge representation. OcIMIDo joins only a small number of other disease area-specific ontologies currently available in general medicine. Notable examples include the @neurIST ontology of intracranial aneurysms [40], and the ACGT Master Ontology of Cancer [41]. Furthermore, we have reported use of an NLP-guided method to identify patient-preferred terms for inclusion in the ontology under class clinical terms as synonyms from a public patient support forum. This addresses an unmet need to better align computational tools with patient and physician-preferred language [1,20]. LTS and GVG also acknowledge support from Horizon 2020 E-Infrastructures (H2020-EINFRA) (731075) (https://ec.europa.eu/programmes/horizon2020/en) in addition to NanoCommons (H2020-EU) (731032) (https://www.nanocommons.eu/). Publisher Copyright: © 2021 The Author(s)

PY - 2021/8

Y1 - 2021/8

N2 - Background: Unstructured text created by patients represents a rich, but relatively inaccessible resource for advancing patient-centred care. This study aimed to develop an ontology for ocular immune-mediated inflammatory diseases (OcIMIDo), as a tool to facilitate data extraction and analysis, illustrating its application to online patient support forum data. Methods: We developed OcIMIDo using clinical guidelines, domain expertise, and cross-references to classes from other biomedical ontologies. We developed an approach to add patient-preferred synonyms text-mined from oliviasvision.org online forum, using statistical ranking. We validated the approach with split-sampling and comparison to manual extraction. Using OcIMIDo, we then explored the frequency of OcIMIDo classes and synonyms, and their potential association with natural language sentiment expressed in each online forum post. Findings: OcIMIDo (version 1.2) includes 661 classes, describing anatomy, clinical phenotype, disease activity status, complications, investigations, interventions and functional impacts. It contains 1661 relationships and axioms, 2851 annotations, including 1131 database cross-references, and 187 patient-preferred synonyms. To illustrate OcIMIDo's potential applications, we explored 9031 forum posts, revealing frequent mention of different clinical phenotypes, treatments, and complications. Language sentiment analysis of each post was generally positive (median 0.12, IQR 0.01–0.24). In multivariable logistic regression, the odds of a post expressing negative sentiment were significantly associated with first posts as compared to replies (OR 3.3, 95% CI 2.8 to 3.9, p < 0.001). Conclusion: We report the development and validation of a new ontology for inflammatory eye diseases, which includes patient-preferred synonyms, and can be used to explore unstructured patient or physician-reported text data, with many potential applications.

AB - Background: Unstructured text created by patients represents a rich, but relatively inaccessible resource for advancing patient-centred care. This study aimed to develop an ontology for ocular immune-mediated inflammatory diseases (OcIMIDo), as a tool to facilitate data extraction and analysis, illustrating its application to online patient support forum data. Methods: We developed OcIMIDo using clinical guidelines, domain expertise, and cross-references to classes from other biomedical ontologies. We developed an approach to add patient-preferred synonyms text-mined from oliviasvision.org online forum, using statistical ranking. We validated the approach with split-sampling and comparison to manual extraction. Using OcIMIDo, we then explored the frequency of OcIMIDo classes and synonyms, and their potential association with natural language sentiment expressed in each online forum post. Findings: OcIMIDo (version 1.2) includes 661 classes, describing anatomy, clinical phenotype, disease activity status, complications, investigations, interventions and functional impacts. It contains 1661 relationships and axioms, 2851 annotations, including 1131 database cross-references, and 187 patient-preferred synonyms. To illustrate OcIMIDo's potential applications, we explored 9031 forum posts, revealing frequent mention of different clinical phenotypes, treatments, and complications. Language sentiment analysis of each post was generally positive (median 0.12, IQR 0.01–0.24). In multivariable logistic regression, the odds of a post expressing negative sentiment were significantly associated with first posts as compared to replies (OR 3.3, 95% CI 2.8 to 3.9, p < 0.001). Conclusion: We report the development and validation of a new ontology for inflammatory eye diseases, which includes patient-preferred synonyms, and can be used to explore unstructured patient or physician-reported text data, with many potential applications.

KW - Inflammation

KW - Ontology

KW - Patient voice

KW - Sentiment

KW - Uveitis

UR - http://www.scopus.com/inward/record.url?scp=85107944630&partnerID=8YFLogxK

U2 - 10.1016/j.compbiomed.2021.104542

DO - 10.1016/j.compbiomed.2021.104542

M3 - Article

C2 - 34139439

AN - SCOPUS:85107944630

SN - 0010-4825

VL - 135

JO - Computers in Biology and Medicine

JF - Computers in Biology and Medicine

M1 - 104542

ER -

Development and application of the ocular immune-mediated inflammatory diseases ontology enhanced with synonyms from online patient support forum conversation

Abstract

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this