121 A retrospective study of diagnoses and next steps for the development of clinical informatics tools. (15th December 2021)

• Record Type: Journal Article
• Authors: Spear, Joshua; Booth, John; Briggs, Lydia; Bryant, William A; Key, Daniel; Shah, Mohsin; Spiridou, Anastassia; Bowyer, Stuart A; Sebire, Neil J
• Is Part Of: Archives of disease in childhood. Volume 106(2021)Supplement 3
• Page Start: A45
• Page End: A45
• Publication Date: 2021-12-15
• Subjects: Children -- Diseases -- Periodicals; Infants -- Diseases -- Periodicals; 618.920005
• DOI: 10.1136/archdischild-2021-gosh.121
• Languages: English
• ISSNs: 0003-9888

Abstract

Abstract : Background: With the introduction of EPIC at GOSH, more data than ever are being collected pertaining to patients and their interactions with the hospital. This data can be effectively leveraged to enrich clinicians' understanding of conditions and provide data driven medical care, which is the core focus of the DRIVE group at GOSH. One example of this is providing clinicians with a holistic understanding of diagnoses made at GOSH, and their characteristics. This information could be used to pre-empt potential comorbidities as well as assess the heterogeneity of a patient diagnoses against the wider GOSH population. Method: We performed a retrospective study of GOSH patients aged between 0 and 18, with diagnoses recorded at the hospital from 01/06/2019 to 01/06/2021. Firstly, we examined the prevalence of diagnoses via clustering methods. Secondly, we examined the most prevalent 200 diagnoses, to understand when these diagnoses most likely occur, and general trends at different ages. Results: The data we used corresponded to 83705 unique patients, 5316 unique diagnoses and on average 6 unique diagnoses per patient. We identified clear patterns of diagnosis changes and general trends in diagnosis groups and progression. Whilst the clinical application of the analysis presented here is useful in and of itself, it also acts as a proof of concept for the kind of automated analysis that could be embedded into clinical informatics tools, which we believe can become commonplace throughout the hospital.