87 Clinician to informatician – transitioning from blood flow to data flow. (22nd November 2019)

• Record Type: Journal Article
• Authors: Margetts, Ben; Issitt, Richard
• Is Part Of: Archives of disease in childhood. Volume 104:Supplement 4(2019)
• Page Start: A34
• Page End: A34
• Publication Date: 2019-11-22
• Subjects: Infants -- Diseases -- Periodicals; Newborn infants -- Diseases -- Periodicals; Fetus -- Diseases -- Periodicals; 618.920105
• DOI: 10.1136/archdischild-2019-gosh.87
• Languages: English
• ISSNs: 1359-2998

Abstract

Abstract : Given the emphasis placed on technology by the Department of Health and the recent high profile Topol review, the role of healthcare data is set to become highly prevalent in the coming years. To bridge the gap between the traditional clinical-academic and statistician roles in translational research, the skillsets of interdisciplinary 'clinical informaticians' are required. This new role requires staff to be conversant in high level programming languages, such as R, python and SQL (the lingua franca of data science), whilst retaining their domain-specific knowledge and an active academic presence within their clinical specialty. To assess the feasibility of upskilling clinical staff into clinical informatician roles, we present case studies of clinicians with little-to-no formal experience of programming, statistics, and data science, who undertook this transition with the Digital Research Environment (DRE). In particular, this transition required a grounding in database extraction, data manipulation, and statistical modelling, replicating the workflow expected in a data-rich research setting. Each case study suggested that online content (tutorials, articles, open source code) provided a solid background in basic data science and functional programming. The benefits of pursuing open-source languages were most keenly observed in question and answer forums, tutorials, and open sessions, with full-text articles and books freely available. Furthermore, paid online courses were abundant, providing high-quality methodological workflows for all aspects of data science and analysis, including advanced topics such as machine learning and deep learning. We found that within 18 months, the staff were able to integrate typical data science workflows within their research programmes. The combination of clinical knowledge and data science will allow the maximum possible value to be extracted from future clinical studies and databases that host increasingly rich EPR datasets, thus further supporting evidence-based improvements to the standard of care in paediatrics.