Browsing by Author "Yergens, Dean"

Now showing 1 - 2 of 2
  • Thumbnail Image
    ItemOpen Access
    Application of the Weka Machine Learning Library to Hospital Ward Occupancy Problems
    (2008-01-04) Harris, Ian; Denzinger, Joerg; Yergens, Dean
    We explore the potential of applying machine learning techniques to the management of patient ow in hospitals. For this project, we have obtained the Weka machine learning library and three years of historical ward occupancy data from Rockyview Hospital. We use Weka's classifier algorithms and the Rockyview data to build a model of patient ow through each ward. Using Weka, we then attempt to predict ward occupancy problems on any given day using the model and the ward conditions from the previous day. This process is repeated for all eighteen wards. Finally, we obtain rules (sets of ward conditions that warn of an impending occupancy problem) for each ward and present the results.
  • Thumbnail Image
    ItemOpen Access
    National Surgical Quality Improvement Program: A Scoping Review of the Literature and Real-World Application Among Radical Cystectomy Patients
    (2022-05-09) Mardinger, Cynthia; Kortbeek, John; Hyndman, Eric; Brindle, Mary; Yergens, Dean; Hee Lee, Chel; Fraulin, Frankie; Austen, Lea
    Introduction: The National Surgical Quality Improvement Program (NSQIP) is a validated database designed to measure risk-adjusted 30-day surgical outcomes for national and international benchmarking. De-identified, anonymized datasets can be abstracted from submitting NSQIP hospitals. The purpose of this scoping review is to describe the breadth of studies in the NSQIP literature. Methods: A comprehensive electronic literature search was performed using PubMed, MEDLINE, Web of Knowledge and Scopus to capture all NSQIP articles published between January 1, 2000 and December 31, 2020. Two reviewers independently reviewed articles to determine their relevance using predefined inclusion criteria. Articles were included if they were about NSQIP or used NSQIP data. References were imported into a literature review application, Synthesis®, to semi-automate data management. Extracted data included the domain of surgery, study type, and year of publication. Results: Of the 4,661 NSQIP articles included, 77.9% were published within the last 5 years. Outcomes (46.7%) and Association (41.7%) were the most common types of NSQIP-related articles. The most common surgical domains of NSQIP articles were general surgery and orthopedic surgery, representing 35.7% and 24.0% of the articles, respectively. Overall, 52 (1.1%) articles could not be categorized. Conclusion: This scoping review provides an overview of the diversity of articles in the NSQIP literature. Mapping the NSQIP database identified areas where systematic reviews might be feasible or relevant and identified opportunities for future research.