Multivariate Statistical Analysis to Detect Insulin Infusion Set Failure
2011 (English)In: 2011 American Control Conference, ACC 2011, San Francisco, CA, USA, 2011, 1952-1957 p.Conference paper (Refereed)
Multivariate statistical analysis techniques are applied to insulin infusion set failure detection (IISF), a challenging problem faced by individuals with type 1 diabetes that are on continuous insulin infusion pump therapy. Bivariate classification (BC), principal component analysis (PCA), and a combined approach were applied to simulated glucose concentrations for 10 patients, based on a nonlinear physiological model of insulin and glucose dynamics. The PCA algorithm had fewer false alarms than BC, while detecting most drifting (ramp) infusion set failures before complete failure occurred.
Place, publisher, year, edition, pages
San Francisco, CA, USA, 2011. 1952-1957 p.
Type 1 Diabetes, Failure detection, Multivariate statistical analysis, Bivariate classification
IdentifiersURN: urn:nbn:se:kth:diva-46487ScopusID: 2-s2.0-80053146069ISBN: 978-1-4577-0080-4OAI: oai:DiVA.org:kth-46487DiVA: diva2:453788
2011 American Control Conference, ACC 2011. San Francisco, CA. 29 June 2011 through 1 July 2011
QC 201111142011-11-032011-11-032011-11-14Bibliographically approved