Revolutionizing Clinical Documentation: An Overview of Automation Possibilities with Open Data Sets

  • Background:

     

    Several studies have been conducted around the possible uses of clinical documentation (e.g., nursing and physician notes) to develop tools that support physicians and nurses in their work. These include using natural language processing (NLP) to identify important mortality predictors, to enable the prediction of intensive care unit (ICU) readmission, or to enable the prediction of cardiac episodes. However, research on the automation of clinical documentation (e.g., discharge summaries) based on the already available data on a patient has only received little attention. An overview of this research body is necessary in order to understand the current state of the art in clinical documentation automation and identify areas that require further attention to enable or improve clinical documentation automation. Moreover, this research is highly relevant for practice as it provides an overview of what is possible in clinical documentation automation. It thereby builds the foundation for further research that can help to alleviate the time-consuming documentation burden for physicians and nurses.


    Objective(s):

     

    • Create an overview of open data sets of clinical documentation
    • Create an overview of how open data sets of clinical documentation have been used to automate clinical documentation (e.g., discharge summaries)
    • Identify areas in which automation of clinical documentation can be used


    Note: This is an umbrella topic. The overall goal, context, and direction of the thesis are defined in the first kickoff meeting.


    Research Method:


    Literature Review


    Literature:

     

    • Callen, J., McIntosh, J., & Li, J. (2010). Accuracy of medication documentation in hospital discharge summaries: A retrospective analysis of medication transcription errors in manual and electronic discharge summaries. International Journal of Medical Informatics, 79(1), 58–64. https://doi.org/10.1016/j.ijmedinf.2009.09.002
    • Johnson, A. E. W., Pollard, T. J., Shen, L., Lehman, L. H., Feng, M., Ghassemi, M., Moody, B., Szolovits, P., Anthony Celi, L., & Mark, R. G. (2016). MIMIC-III, a freely accessible critical care database. Scientific Data, 3(1), Art. 1. https://doi.org/10.1038/sdata.2016.35
    • Syed, M., Syed, S., Sexton, K., Syeda, H. B., Garza, M., Zozus, M., Syed, F., Begum, S., Syed, A. U., Sanford, J., & Prior, F. (2021). Application of Machine Learning in Intensive Care Unit (ICU) Settings Using MIMIC Dataset: Systematic Review. Informatics, 8(1), Art. 1. https://doi.org/10.3390/informatics8010016
    • Starlinger, J., Kittner, M., Blankenstein, O., & Leser, U. (2017). How to improve information extraction from German medical records. Information Technology, 59(4), 171–179. https://doi.org/10.1515/itit-2016-0027