How is the weather? Forecasting inpatient glycemic control. (11th September 2017)

• Record Type: Journal Article
• Authors: Saulnier, George E; Castro, Janna C; Cook, Curtiss B; Thompson, Bithika M
• Is Part Of: Future science OA. Volume 3:Number 4(2017)
• Publication Date: 2017-09-11
• Subjects: forecasting -- hyperglycemia -- inpatient -- operational research; Medicine -- Periodicals; Biotechnology -- Periodicals; 610
• DOI: 10.4155/fsoa-2017-0066
• Languages: English
• ISSNs: 2056-5623

Abstract

Aim: Apply methods of damped trend analysis to forecast inpatient glycemic control.Method: Observed and calculated point-of-care blood glucose data trends were determined over 62 weeks. Mean absolute percent error was used to calculate differences between observed and forecasted values. Comparisons were drawn between model results and linear regression forecasting.Results: The forecasted mean glucose trends observed during the first 24 and 48 weeks of projections compared favorably to the results provided by linear regression forecasting. However, in some scenarios, the damped trend method changed inferences compared with linear regression. In all scenarios, mean absolute percent error values remained below the 10% accepted by demand industries.Conclusion: Results indicate that forecasting methods historically applied within demand industries can project future inpatient glycemic control. Additional study is needed to determine if forecasting is useful in the analyses of other glucometric parameters and, if so, how to apply the techniques to quality improvement. Lay abstract: Hyperglycemia (high blood sugars) in the hospital can lead to complications, such as more surgical infections or longer hospital stays. Therefore, it is important to project how hyperglycemia may change over time to develop plans to intervene early. This study uses a mathematical technique used in industry called damped trend exponential smoothing analysis that allows forecasting of blood sugars into the future. At a population level, the method could allow hospitals to predict if hyperglycemia will get worse so that plans could be developed early to proactively prevent the problem from occurring.