38 Web apps for delivering predictive analytics at the bedside. (22nd November 2019)

• Record Type: Journal Article
• Authors: Issitt, Richard; Margetts, Ben
• Is Part Of: Archives of disease in childhood. Volume 104:(2019)Supplement 4
• Page Start: A16
• Page End: A16
• Publication Date: 2019-11-22
• Subjects: Children -- Diseases -- Periodicals; Infants -- Diseases -- Periodicals; 618.920005
• DOI: 10.1136/archdischild-2019-gosh.38
• Languages: English
• ISSNs: 0003-9888

Abstract

Abstract : The end point of clinical research is often considered to be the publication of peer reviewed data and results. Although an effective method for communication with a technical audience, publications can often appear impenetrable for non-technical audiences and are typically unable to deliver a clear method for implementation of the research output. Web applications provide a potential solution for data-driven research and are able to deliver accessible, interactive interfaces for wide audiences. When considering the wealth of data collected in clinical systems such as Epic, the potential for delivering web-based hospital tools derived from GOSH research output is substantial. EPR data were sourced from legacy hospital systems and integrated with patient-level outcome data, including risk of death, and renal failure outcome measurements in the GOSH Digital Research Environment (DRE). These data were then modelled using logistic regression models written in the open source Bayesian modelling platform, Stan, to predict patient outcome. Finally, the project's analysis workflow, written in the R language, was ported to a dashboard-style R Shiny web app using the Shiny Dashboard package. The resulting modular web app was capable of delivering each element of the project in an accessible manner, without sacrificing the detail or transparency required for clinical research. Each tab of the web app represented a separate step, presenting a high-level project overview, interactive data visualisations, modelling teaching tools, an interactive, dynamic, and interpretable model estimation module, a patient outcome prediction module, customization options, and a tab that renders the app's source code, encouraging reproducibility. The app was written to be fully compatible with research data provisioned through the DRE and modular enough to be ported to prospective research projects. This work demonstrates a proof-of-concept open source Shiny web app framework for delivering interactive and predictive analytics from clinical research projects.