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 | |
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